Centre for Artificial Intelligence Research

Artificial morality and causality, deep reinforcement learning to optimize hydropower production and other complex systems, deep information understanding and knowledge (data mining and big data).

New novel idea for Cloud Computing: How can we use Kalman filter in security of Cloud Computing

2012

Cloud is a virtual image about some amount of undefined powers, that is widespread and had unknown power and inexact amount of hardware and software configurations, and because of we have not any information about clouds location and time dimensions and also the amounts of its sources we tell that Cloud Computing. This technology presents lots of abilities and opportunities such as processing power, storage and accessing it from everywhere, supporting, working - team group - with the latest versions of software and etc., by the means of internet. On the other hand, in such a large scale networks we should consider the reliability and powerfulness of such networks in facing with events such …

Low-Power Audio Keyword Spotting using Tsetlin Machines

2021

The emergence of Artificial Intelligence (AI) driven Keyword Spotting (KWS) technologies has revolutionized human to machine interaction. Yet, the challenge of end-to-end energy efficiency, memory footprint and system complexity of current Neural Network (NN) powered AI-KWS pipelines has remained ever present. This paper evaluates KWS utilizing a learning automata powered machine learning algorithm called the Tsetlin Machine (TM). Through significant reduction in parameter requirements and choosing logic over arithmetic based processing, the TM offers new opportunities for low-power KWS while maintaining high learning efficacy. In this paper we explore a TM based keyword spotting (KWS) pipe…

Publish-subscribe smartphone sensing platform for the acute phase of a disaster: A framework for emergency management support

2014

The advanced sensors embedded in modern smartphones opens up for novel research opportunities, as for instance manifested in the field of mobile phone sensing. Most notable is perhaps research activities within human activity recognition and context-aware applications. Along a similar vein, the SmartRescue project targets monitoring of both hazard developments as well as tracking of people in a disaster, taking advantage of smartphone sensing, processing and communication capabilities. The goal is to help crisis managers and the public in early hazard detection, hazard prediction, and in the forming of risk minimizing evacuation plans when disaster strikes. In this paper we propose a novel …

A User-Centric Approach for Personalized Service Provisioning in Pervasive Environments

2011

Published version of an article published in Wireless Personal Communications (2011). Also available from the publisher at http://dx.doi.org/10.1007/s11277-011-0387-3 The vision of pervasive environments is being realized more than ever with the proliferation of services and computing resources located in our surrounding environments. Identifying those services that deserve the attention of the user is becoming an increasingly-challenging task. In this paper, we present an adaptive multi-criteria decision making mechanism for recommending relevant services to the mobile user. In this context, "Relevance" is determined based on a user-centric approach that combines both the reputation of the…

A Tsetlin Machine with Multigranular Clauses

2019

The recently introduced Tsetlin Machine (TM) has provided competitive pattern recognition accuracy in several benchmarks, however, requires a 3-dimensional hyperparameter search. In this paper, we introduce the Multigranular Tsetlin Machine (MTM). The MTM eliminates the specificity hyperparameter, used by the TM to control the granularity of the conjunctive clauses that it produces for recognizing patterns. Instead of using a fixed global specificity, we encode varying specificity as part of the clauses, rendering the clauses multigranular. This makes it easier to configure the TM because the dimensionality of the hyperparameter search space is reduced to only two dimensions. Indeed, it tur…

Adaptive sparse representation of continuous input for tsetlin machines based on stochastic searching on the line

2021

This paper introduces a novel approach to representing continuous inputs in Tsetlin Machines (TMs). Instead of using one Tsetlin Automaton (TA) for every unique threshold found when Booleanizing continuous input, we employ two Stochastic Searching on the Line (SSL) automata to learn discriminative lower and upper bounds. The two resulting Boolean features are adapted to the rest of the clause by equipping each clause with its own team of SSLs, which update the bounds during the learning process. Two standard TAs finally decide whether to include the resulting features as part of the clause. In this way, only four automata altogether represent one continuous feature (instead of potentially h…

Stochastic Learning for SAT- Encoded Graph Coloring Problems

2010

The graph coloring problem (GCP) is a widely studied combinatorial optimization problem due to its numerous applications in many areas, including time tabling, frequency assignment, and register allocation. The need for more efficient algorithms has led to the development of several GC solvers. In this paper, the authors introduce a team of Finite Learning Automata, combined with the random walk algorithm, using Boolean satisfiability encoding for the GCP. The authors present an experimental analysis of the new algorithm’s performance compared to the random walk technique, using a benchmark set containing SAT-encoding graph coloring test sets.

An Iterative Information Retrieval Approach from Social Media in Crisis Situations

2019

During to past few years, social media have gained a pivotal role in crisis communication. Its usage has ranged from informing the public about the status of a crisis and what precaution need to be taken, to family members checking on the safety of loved ones. Despite the widespread use of social media in crises situations and the clear potential benefit from collecting potential critical information from social media, emergency management services (EMSs) are still reluctant to use social media as a source of information to improve their situational awareness. One of the reasons for the reluctance is that crises management are typically overloaded with information. Adding social media will …

The regression Tsetlin machine: a novel approach to interpretable nonlinear regression

2019

Relying simply on bitwise operators, the recently introduced Tsetlin machine (TM) has provided competitive pattern classification accuracy in several benchmarks, including text understanding. In this paper, we introduce the regression Tsetlin machine (RTM), a new class of TMs designed for continuous input and output, targeting nonlinear regression problems. In all brevity, we convert continuous input into a binary representation based on thresholding, and transform the propositional formula formed by the TM into an aggregated continuous output. Our empirical comparison of the RTM with state-of-the-art regression techniques reveals either superior or on par performance on five datasets. Thi…

Using Tsetlin Machine to discover interpretable rules in natural language processing applications

2021

Tsetlin Machines (TM) use finite state machines for learning and propositional logic to represent patterns. The resulting pattern recognition approach captures information in the form of conjunctive clauses, thus facilitating human interpretation. In this work, we propose a TM-based approach to three common natural language processing (NLP) tasks, namely, sentiment analysis, semantic relation categorization and identifying entities in multi-turn dialogues. By performing frequent itemset mining on the TM-produced patterns, we show that we can obtain a global and a local interpretation of the learning, one that mimics existing rule-sets or lexicons. Further, we also establish that our TM base…

Increasing sample efficiency in deep reinforcement learning using generative environment modelling

2020

Towards safe reinforcement-learning in industrial grid-warehousing

2020

Abstract Reinforcement learning has shown to be profoundly successful at learning optimal policies for simulated environments using distributed training with extensive compute capacity. Model-free reinforcement learning uses the notion of trial and error, where the error is a vital part of learning the agent to behave optimally. In mission-critical, real-world environments, there is little tolerance for failure and can cause damaging effects on humans and equipment. In these environments, current state-of-the-art reinforcement learning approaches are not sufficient to learn optimal control policies safely. On the other hand, model-based reinforcement learning tries to encode environment tra…

A Relational Tsetlin Machine with Applications to Natural Language Understanding

2021

TMs are a pattern recognition approach that uses finite state machines for learning and propositional logic to represent patterns. In addition to being natively interpretable, they have provided competitive accuracy for various tasks. In this paper, we increase the computing power of TMs by proposing a first-order logic-based framework with Herbrand semantics. The resulting TM is relational and can take advantage of logical structures appearing in natural language, to learn rules that represent how actions and consequences are related in the real world. The outcome is a logic program of Horn clauses, bringing in a structured view of unstructured data. In closed-domain question-answering, th…

Using Learning Automata to Enhance Local-Search Based SAT Solvers with Learning Capability

2010

In this work, we have introduced a new approach based on combining Learning Automata with Random Walk and GSAT w/Random Walk. In order to get a comprehensive overview of the new algorithms' performance, we used a set of benchmark problems containing different problems from various domains. In these benchmark problems, both RW and GSATRW suffers from stagnation behaviour which directly affects their performance. This phenomenon is, however, only observed for LA-GSATRW on the largest problem instances. Finally, the

Emergency Analysis: Multitask Learning with Deep Convolutional Neural Networks for Fire Emergency Scene Parsing

2021

In this paper, we introduce a novel application of using scene semantic image segmentation for fire emergency situation analysis. To analyse a fire emergency scene, we propose to use deep convolutional image segmentation networks to identify and classify objects in a scene based on their build material and their vulnerability to catch fire. We introduce our own fire emergency scene segmentation dataset for this purpose. It consists of real world images with objects annotated on the basis of their build material. We use state-of-the-art segmentation models: DeepLabv3, DeepLabv3+, PSPNet, FCN, SegNet and UNet to compare and evaluate their performance on the fire emergency scene parsing task. …

A Novel Multi-step Finite-State Automaton for Arbitrarily Deterministic Tsetlin Machine Learning

2020

Due to the high energy consumption and scalability challenges of deep learning, there is a critical need to shift research focus towards dealing with energy consumption constraints. Tsetlin Machines (TMs) are a recent approach to machine learning that has demonstrated significantly reduced energy usage compared to neural networks alike, while performing competitively accuracy-wise on several benchmarks. However, TMs rely heavily on energy-costly random number generation to stochastically guide a team of Tsetlin Automata (TA) to a Nash Equilibrium of the TM game. In this paper, we propose a novel finite-state learning automaton that can replace the TA in TM learning, for increased determinis…

A solution to the stochastic point location problem in metalevel nonstationary environments.

2008

This paper reports the first known solution to the stochastic point location (SPL) problem when the environment is nonstationary. The SPL problem involves a general learning problem in which the learning mechanism (which could be a robot, a learning automaton, or, in general, an algorithm) attempts to learn a "parameter," for example, lambda*, within a closed interval. However, unlike the earlier reported results, we consider the scenario when the learning is to be done in a nonstationary setting. For each guess, the environment essentially informs the mechanism, possibly erroneously (i.e., with probability p), which way it should move to reach the unknown point. Unlike the results availabl…

Indoor Space Classification Using Cascaded LSTM

2020

Author's accepted manuscript. © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Indoor space classification is an important part of localization that helps in precise location extraction, which has been extensively utilized in industrial and domestic domain. There are various approaches that employ Bluetooth Low Energy (BLE), Wi-Fi, magnetic field, object detecti…

The Regression Tsetlin Machine: A Tsetlin Machine for Continuous Output Problems

2019

The recently introduced Tsetlin Machine (TM) has provided competitive pattern classification accuracy in several benchmarks, composing patterns with easy-to-interpret conjunctive clauses in propositional logic. In this paper, we go beyond pattern classification by introducing a new type of TMs, namely, the Regression Tsetlin Machine (RTM). In all brevity, we modify the inner inference mechanism of the TM so that input patterns are transformed into a single continuous output, rather than to distinct categories. We achieve this by: (1) using the conjunctive clauses of the TM to capture arbitrarily complex patterns; (2) mapping these patterns to a continuous output through a novel voting and n…

On Using a Hierarchy of Twofold Resource Allocation Automata to Solve Stochastic Nonlinear Resource Allocation Problems

2007

Recent trends in AI attempt to solve difficult NP-hard problems using intelligent techniques so as to obtain approximately-optimal solutions. In this paper, we consider a family of such problems which fall under the general umbrella of "knapsack-like" problems, and demonstrate how we can solve all of them fast and accurately using a hierarchy of Learning Automata (LA). In a multitude of real-world situations, resources must be allocated based on incomplete and noisy information, which often renders traditional resource allocation techniques ineffective. This paper addresses one such class of problems, namely, Stochastic Non-linear Fractional Knapsack Problems. We first present a completely …

Positionless aspect based sentiment analysis using attention mechanism.

2021

Abstract Aspect-based sentiment analysis (ABSA) aims at identifying fine-grained polarity of opinion associated with a given aspect word. Several existing articles demonstrated promising ABSA accuracy using positional embedding to show the relationship between an aspect word and its context. In most cases, the positional embedding depends on the distance between the aspect word and the remaining words in the context, known as the position index sequence. However, these techniques usually employ both complex preprocessing approaches with additional trainable positional embedding and complex architectures to obtain the state-of-the-art performance. In this paper, we simplify preprocessing by …

Word-level human interpretable scoring mechanism for novel text detection using Tsetlin Machines

2021

Recent research in novelty detection focuses mainly on document-level classification, employing deep neural networks (DNN). However, the black-box nature of DNNs makes it difficult to extract an exact explanation of why a document is considered novel. In addition, dealing with novelty at the word-level is crucial to provide a more fine-grained analysis than what is available at the document level. In this work, we propose a Tsetlin machine (TM)-based architecture for scoring individual words according to their contribution to novelty. Our approach encodes a description of the novel documents using the linguistic patterns captured by TM clauses. We then adopt this description to measure how …

Learning automata based energy-efficient AI hardware design for IoT applications

2020

Energy efficiency continues to be the core design challenge for artificial intelligence (AI) hardware designers. In this paper, we propose a new AI hardware architecture targeting Internet of Things applications. The architecture is founded on the principle of learning automata, defined using propositional logic. The logic-based underpinning enables low-energy footprints as well as high learning accuracy during training and inference, which are crucial requirements for efficient AI with long operating life. We present the first insights into this new architecture in the form of a custom-designed integrated circuit for pervasive applications. Fundamental to this circuit is systematic encodin…

A two-armed bandit collective for hierarchical examplar based mining of frequent itemsets with applications to intrusion detection

2014

Published version of a chapter in the book: Transactions on Computational Collective Intelligence XIV. Also available from the publisher at: http://dx.doi.org/10.1007/978-3-662-44509-9_1 In this paper we address the above problem by posing frequent item-set mining as a collection of interrelated two-armed bandit problems. We seek to find itemsets that frequently appear as subsets in a stream of itemsets, with the frequency being constrained to support granularity requirements. Starting from a randomly or manually selected examplar itemset, a collective of Tsetlin automata based two-armed bandit players - one automaton for each item in the examplar - learns which items should be included in …

Causality-based Social Media Analysis for Normal Users Credibility Assessment in a Political Crisis

2019

Information trustworthiness assessment on political social media discussions is crucial to maintain the order of society, especially during emergent situations. The polarity nature of political topics and the echo chamber effect by social media platforms allow for a deceptive and a dividing environment. During a political crisis, a vast amount of information is being propagated on social media, that leads up to a high level of polarization and deception by the beneficial parties. The traditional approaches to tackling misinformation on social media usually lack a comprehensive problem definition due to its complication. This paper proposes a probabilistic graphical model as a theoretical vi…

Using the Tsetlin Machine to Learn Human-Interpretable Rules for High-Accuracy Text Categorization With Medical Applications

2019

Medical applications challenge today's text categorization techniques by demanding both high accuracy and ease-of-interpretation. Although deep learning has provided a leap ahead in accuracy, this leap comes at the sacrifice of interpretability. To address this accuracy-interpretability challenge, we here introduce, for the first time, a text categorization approach that leverages the recently introduced Tsetlin Machine. In all brevity, we represent the terms of a text as propositional variables. From these, we capture categories using simple propositional formulae, such as: if "rash" and "reaction" and "penicillin" then Allergy. The Tsetlin Machine learns these formulae from a labelled tex…

Adaptive Continuous Feature Binarization for Tsetlin Machines Applied to Forecasting Dengue Incidences in the Philippines

2020

The Tsetlin Machine (TM) is a recent interpretable machine learning algorithm that requires relatively modest computational power, yet attains competitive accuracy in several benchmarks. TMs are inherently binary; however, many machine learning problems are continuous. While binarization of continuous data through brute-force thresholding has yielded promising accuracy, such an approach is computationally expensive and hinders extrapolation. In this paper, we address these limitations by standardizing features to support scale shifts in the transition from training data to real-world operation, typical for e.g. forecasting. For scalability, we employ sampling to reduce the number of binariz…

Measuring the Novelty of Natural Language Text Using the Conjunctive Clauses of a Tsetlin Machine Text Classifier

2020

Most supervised text classification approaches assume a closed world, counting on all classes being present in the data at training time. This assumption can lead to unpredictable behaviour during operation, whenever novel, previously unseen, classes appear. Although deep learning-based methods have recently been used for novelty detection, they are challenging to interpret due to their black-box nature. This paper addresses \emph{interpretable} open-world text classification, where the trained classifier must deal with novel classes during operation. To this end, we extend the recently introduced Tsetlin machine (TM) with a novelty scoring mechanism. The mechanism uses the conjunctive clau…

Interpretability in Word Sense Disambiguation using Tsetlin Machine

2021

A Framework for Assessing the Condition of Crowds Exposed to a Fire Hazard Using a Probabilistic Model

2014

Published version of an article in the journal: International Journal of Machine Learning and Computing. Also available from the publisher at: http://dx.doi.org/10.7763/IJMLC.2014.V4.379 open Access Allocating limited resources in an optimal manner when rescuing victims from a hazard is a complex and error prone task, because the involved hazards are typically evolving over time; stagnating, building up or diminishing. Typical error sources are: miscalculation of resource availability and the victims’ condition. Thus, there is a need for decision support when it comes to rapidly predicting where the human fatalities are likely to occur to ensure timely rescue. This paper proposes a probabil…

A Conclusive Analysis of the Finite-Time Behavior of the Discretized Pursuit Learning Automaton

2019

Author's accepted version (post-print). © 20XX IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Available from 20/03/2021. This paper deals with the finite-time analysis (FTA) of learning automata (LA), which is a topic for which very little work has been reported in the literature. This is as opposed to the asymptotic steady-state analysis for which there are, probabl…

Comparing Different Crowd Emergency Evacuation Models Based on Human Centered Sensing Criteria

2014

Emergency evacuation of crowds is a fascinating phenomenon that has attracted researchers from various fields. Better understanding of this class of crowd behavior opens up for improving evacuation policies and smarter design of buildings, increasing safety. Recently, a new class of disruptive technology has appeared: Human-centered sensing which allows crowd behavior to be monitored in real-time, and provides the basis for real-time crowd control. The question then becomes: to what degree can previous crowd models incorporate this development, and what areas need further research? In this paper, the authors provide a survey that describes some widely used crowd models and discuss the advan…

CostNet: An End-to-End Framework for Goal-Directed Reinforcement Learning

2020

Reinforcement Learning (RL) is a general framework concerned with an agent that seeks to maximize rewards in an environment. The learning typically happens through trial and error using explorative methods, such as \(\epsilon \)-greedy. There are two approaches, model-based and model-free reinforcement learning, that show concrete results in several disciplines. Model-based RL learns a model of the environment for learning the policy while model-free approaches are fully explorative and exploitative without considering the underlying environment dynamics. Model-free RL works conceptually well in simulated environments, and empirical evidence suggests that trial and error lead to a near-opti…

Safer Reinforcement Learning for Agents in Industrial Grid-Warehousing

2020

In mission-critical, real-world environments, there is typically a low threshold for failure, which makes interaction with learning algorithms particularly challenging. Here, current state-of-the-art reinforcement learning algorithms struggle to learn optimal control policies safely. Loss of control follows, which could result in equipment breakages and even personal injuries.

Successive Reduction of Arms in Multi-Armed Bandits

2011

The relevance of the multi-armed bandit problem has risen in the past few years with the need for online optimization techniques in Internet systems, such as online advertisement and news article recommendation. At the same time, these applications reveal that state-of-the-art solution schemes do not scale well with the number of bandit arms. In this paper, we present two types of Successive Reduction (SR) strategies - 1) Successive Reduction Hoeffding (SRH) and 2) Successive Reduction Order Statistics (SRO). Both use an Order Statistics based Thompson Sampling method for arm selection, and then successively eliminate bandit arms from consideration based on a confidence threshold. While SRH…

On the Convergence of Tsetlin Machines for the XOR Operator.

2022

The Tsetlin Machine (TM) is a novel machine learning algorithm with several distinct properties, including transparent inference and learning using hardware-near building blocks. Although numerous papers explore the TM empirically, many of its properties have not yet been analyzed mathematically. In this article, we analyze the convergence of the TM when input is non-linearly related to output by the XOR-operator. Our analysis reveals that the TM, with just two conjunctive clauses, can converge almost surely to reproducing XOR, learning from training data over an infinite time horizon. Furthermore, the analysis shows how the hyper-parameter T guides clause construction so that the clauses c…

Closed-Form Expressions for Global and Local Interpretation of Tsetlin Machines

2021

Tsetlin Machines (TMs) capture patterns using conjunctive clauses in propositional logic, thus facilitating interpretation. However, recent TM-based approaches mainly rely on inspecting the full range of clauses individually. Such inspection does not necessarily scale to complex prediction problems that require a large number of clauses. In this paper, we propose closed-form expressions for understanding why a TM model makes a specific prediction (local interpretability). Additionally, the expressions capture the most important features of the model overall (global interpretability). We further introduce expressions for measuring the importance of feature value ranges for continuous feature…

Bayesian Unification of Gradient and Bandit-based Learning for Accelerated Global Optimisation

2017

Bandit based optimisation has a remarkable advantage over gradient based approaches due to their global perspective, which eliminates the danger of getting stuck at local optima. However, for continuous optimisation problems or problems with a large number of actions, bandit based approaches can be hindered by slow learning. Gradient based approaches, on the other hand, navigate quickly in high-dimensional continuous spaces through local optimisation, following the gradient in fine grained steps. Yet, apart from being susceptible to local optima, these schemes are less suited for online learning due to their reliance on extensive trial-and-error before the optimum can be identified. In this…

Hydropower Optimization Using Split-Window, Meta-Heuristic and Genetic Algorithms

2019

In this paper, we try to find the most efficient optimization algorithm that can be used to resolve the hydropower optimization problem. We propose a novel optimization technique is called the Split-window method. The method is relatively simple and reduces the complexity of the optimization problem by split-ting the planning horizon (and datasets) into equal windows and assigning the same values to policies(actions) within each part. After splitting, a meta-heuristic technique is used to optimize the actions, and the dataset is split again until a split contains only one instance (timestep). The unique values to be optimized during each iteration is equal to the number of splits which make…

On Obtaining Classification Confidence, Ranked Predictions and AUC with Tsetlin Machines

2020

Tsetlin machines (TMs) are a promising approach to machine learning that uses Tsetlin Automata to produce patterns in propositional logic, leading to binary (hard) classifications. In many applications, however, one needs to know the confidence of classifications, e.g. to facilitate risk management. In this paper, we propose a novel scheme for measuring TM confidence based on the logistic function, calculated from the propositional logic patterns that match the input. We then use this scheme to trade off precision against recall, producing area under receiver operating characteristic curves (AUC) for TMs. Empirically, using four real-world datasets, we show that AUC is a more sensitive meas…

Integer Weighted Regression Tsetlin Machines

2020

The Regression Tsetlin Machine (RTM) addresses the lack of interpretability impeding state-of-the-art nonlinear regression models. It does this by using conjunctive clauses in propositional logic to capture the underlying non-linear frequent patterns in the data. These, in turn, are combined into a continuous output through summation, akin to a linear regression function, however, with non-linear components and binary weights. However, the resolution of the RTM output is proportional to the number of clauses employed. This means that computation cost increases with resolution. To address this problem, we here introduce integer weighted RTM clauses. Our integer weighted clause is a compact r…

Deep Q-Learning With Q-Matrix Transfer Learning for Novel Fire Evacuation Environment

2021

We focus on the important problem of emergency evacuation, which clearly could benefit from reinforcement learning that has been largely unaddressed. Emergency evacuation is a complex task which is difficult to solve with reinforcement learning, since an emergency situation is highly dynamic, with a lot of changing variables and complex constraints that makes it difficult to train on. In this paper, we propose the first fire evacuation environment to train reinforcement learning agents for evacuation planning. The environment is modelled as a graph capturing the building structure. It consists of realistic features like fire spread, uncertainty and bottlenecks. We have implemented the envir…

Extending the Tsetlin Machine With Integer-Weighted Clauses for Increased Interpretability

2020

Despite significant effort, building models that are both interpretable and accurate is an unresolved challenge for many pattern recognition problems. In general, rule-based and linear models lack accuracy, while deep learning interpretability is based on rough approximations of the underlying inference. Using a linear combination of conjunctive clauses in propositional logic, Tsetlin Machines (TMs) have shown competitive performance on diverse benchmarks. However, to do so, many clauses are needed, which impacts interpretability. Here, we address the accuracy-interpretability challenge in machine learning by equipping the TM clauses with integer weights. The resulting Integer Weighted TM (…

Multi-layer intrusion detection system with ExtraTrees feature selection, extreme learning machine ensemble, and softmax aggregation

2019

Abstract Recent advances in intrusion detection systems based on machine learning have indeed outperformed other techniques, but struggle with detecting multiple classes of attacks with high accuracy. We propose a method that works in three stages. First, the ExtraTrees classifier is used to select relevant features for each type of attack individually for each (ELM). Then, an ensemble of ELMs is used to detect each type of attack separately. Finally, the results of all ELMs are combined using a softmax layer to refine the results and increase the accuracy further. The intuition behind our system is that multi-class classification is quite difficult compared to binary classification. So, we…

Emergency Detection with Environment Sound Using Deep Convolutional Neural Networks

2020

In this paper, we propose a generic emergency detection system using only the sound produced in the environment. For this task, we employ multiple audio feature extraction techniques like the mel-frequency cepstral coefficients, gammatone frequency cepstral coefficients, constant Q-transform and chromagram. After feature extraction, a deep convolutional neural network (CNN) is used to classify an audio signal as a potential emergency situation or not. The entire model is based on our previous work that sets the new state of the art in the environment sound classification (ESC) task (Our paper is under review in the IEEE/ACM Transactions on Audio, Speech and Language Processing and also avai…

Mining Interpretable Rules for Sentiment and Semantic Relation Analysis Using Tsetlin Machines

2020

Tsetlin Machines (TMs) are an interpretable pattern recognition approach that captures patterns with high discriminative power from data. Patterns are represented as conjunctive clauses in propositional logic, produced using bandit-learning in the form of Tsetlin Automata. In this work, we propose a TM-based approach to two common Natural Language Processing (NLP) tasks, viz. Sentiment Analysis and Semantic Relation Categorization. By performing frequent itemset mining on the patterns produced, we show that they follow existing expert-verified rule-sets or lexicons. Further, our comparison with other widely used machine learning techniques indicates that the TM approach helps maintain inter…

The Bayesian Learning Automaton — Empirical Evaluation with Two-Armed Bernoulli Bandit Problems

2009

The two-armed Bernoulli bandit (TABB) problem is a classical optimization problem where an agent sequentially pulls one of two arms attached to a gambling machine, with each pull resulting either in a reward or a penalty. The reward probabilities of each arm are unknown, and thus one must balance between exploiting existing knowledge about the arms, and obtaining new information.

Convolutional Regression Tsetlin Machine: An Interpretable Approach to Convolutional Regression

2021

The Convolutional Tsetlin Machine (CTM), a variant of Tsetlin Machine (TM), represents patterns as straightforward AND-rules, to address the high computational complexity and the lack of interpretability of Convolutional Neural Networks (CNNs). CTM has shown competitive performance on MNIST, Fashion-MNIST, and Kuzushiji-MNIST pattern classification benchmarks, both in terms of accuracy and memory footprint. In this paper, we propose the Convolutional Regression Tsetlin Machine (C-RTM) that extends the CTM to support continuous output problems in image analysis. C-RTM identifies patterns in images using the convolution operation as in the CTM and then maps the identified patterns into a real…

MMSS: A storytelling simulation software to mitigate misinformation on social media

2022

This paper proposes a modular python implementation of a storytelling simulation. The software evaluates misinformation mitigation strategies over social media and visualizes the investigated scenarios’ potential outcomes. Our software integrates information diffusion and control models components. The control model mitigates users’ exposure to misinformation with social fairness awareness, while the diffusion model predicts the outcome from the control model. During the interaction of both models, a graph coloring algorithm traces the interaction within specific time intervals. Then, it generates meta-data to construct visuals of predicted near-future states of the social network to help s…

Environment Sound Classification using Multiple Feature Channels and Attention based Deep Convolutional Neural Network

2020

In this paper, we propose a model for the Environment Sound Classification Task (ESC) that consists of multiple feature channels given as input to a Deep Convolutional Neural Network (CNN) with Attention mechanism. The novelty of the paper lies in using multiple feature channels consisting of Mel-Frequency Cepstral Coefficients (MFCC), Gammatone Frequency Cepstral Coefficients (GFCC), the Constant Q-transform (CQT) and Chromagram. Such multiple features have never been used before for signal or audio processing. And, we employ a deeper CNN (DCNN) compared to previous models, consisting of spatially separable convolutions working on time and feature domain separately. Alongside, we use atten…

Robust Interpretable Text Classification against Spurious Correlations Using AND-rules with Negation

2022

The state-of-the-art natural language processing models have raised the bar for excellent performance on a variety of tasks in recent years. However, concerns are rising over their primitive sensitivity to distribution biases that reside in the training and testing data. This issue hugely impacts the performance of the models when exposed to out-of-distribution and counterfactual data. The root cause seems to be that many machine learning models are prone to learn the shortcuts, modelling simple correlations rather than more fundamental and general relationships. As a result, such text classifiers tend to perform poorly when a human makes minor modifications to the data, which raises questi…

Increasing the Inference and Learning Speed of Tsetlin Machines with Clause Indexing

2020

The Tsetlin Machine (TM) is a machine learning algorithm founded on the classical Tsetlin Automaton (TA) and game theory. It further leverages frequent pattern mining and resource allocation principles to extract common patterns in the data, rather than relying on minimizing output error, which is prone to overfitting. Unlike the intertwined nature of pattern representation in neural networks, a TM decomposes problems into self-contained patterns, represented as conjunctive clauses. The clause outputs, in turn, are combined into a classification decision through summation and thresholding, akin to a logistic regression function, however, with binary weights and a unit step output function. …

Learning Automata-based Misinformation Mitigation via Hawkes Processes

2021

AbstractMitigating misinformation on social media is an unresolved challenge, particularly because of the complexity of information dissemination. To this end, Multivariate Hawkes Processes (MHP) have become a fundamental tool because they model social network dynamics, which facilitates execution and evaluation of mitigation policies. In this paper, we propose a novel light-weight intervention-based misinformation mitigation framework using decentralized Learning Automata (LA) to control the MHP. Each automaton is associated with a single user and learns to what degree that user should be involved in the mitigation strategy by interacting with a corresponding MHP, and performing a joint ra…

Combining a context aware neural network with a denoising autoencoder for measuring string similarities

2020

Abstract Measuring similarities between strings is central for many established and fast-growing research areas, including information retrieval, biology, and natural-language processing. The traditional approach to string similarity measurements is to define a metric with respect to a word space that quantifies and sums up the differences between characters in two strings; surprisingly, these metrics have not evolved a great deal over the past few decades. Indeed, the majority of them are still based on making a simple comparison between character and character distributions without considering the words context. This paper proposes a string metric that encompasses similarities between str…

Public Transport Passenger Count Forecasting in Pandemic Scenarios Using Regression Tsetlin Machine. Case Study of Agder, Norway

2021

Challenged by the effects of the COVID-19 pandemic, public transport is suffering from low ridership and staggering economic losses. One of the factors which triggered such losses was the lack of preparedness among governments and public transport providers. The losses can be minimized if the passenger count can be predicted with a higher accuracy and the public transport provision adapted to the demand in real time. The present paper explores the use of a novel machine learning algorithm, namely Regression Tsetlin Machine, in using historical passenger transport data from the current COVID-19 pandemic and pre-pandemic period, combined with a calendar of pandemic-related events (e.g. daily …

Explainable Reinforcement Learning with the Tsetlin Machine

2021

The Tsetlin Machine is a recent supervised machine learning algorithm that has obtained competitive results in several benchmarks, both in terms of accuracy and resource usage. It has been used for convolution, classification, and regression, producing interpretable rules. In this paper, we introduce the first framework for reinforcement learning based on the Tsetlin Machine. We combined the value iteration algorithm with the regression Tsetlin Machine, as the value function approximator, to investigate the feasibility of training the Tsetlin Machine through bootstrapping. Moreover, we document robustness and accuracy of learning on several instances of the grid-world problem.

From Arithmetic to Logic based AI: A Comparative Analysis of Neural Networks and Tsetlin Machine

2020

Neural networks constitute a well-established design method for current and future generations of artificial intelligence. They depends on regressed arithmetic between perceptrons organized in multiple layers to derive a set of weights that can be used for classification or prediction. Over the past few decades, significant progress has been made in low-complexity designs enabled by powerful hardware/software ecosystems. Built on the foundations of finite-state automata and game theory, Tsetlin Machine is increasingly gaining momentum as an emerging artificial intelligence design method. It is fundamentally based on propositional logic based formulation using booleanized input features. Rec…

Towards Model-Based Reinforcement Learning for Industry-Near Environments

2019

Deep reinforcement learning has over the past few years shown great potential in learning near-optimal control in complex simulated environments with little visible information. Rainbow (Q-Learning) and PPO (Policy Optimisation) have shown outstanding performance in a variety of tasks, including Atari 2600, MuJoCo, and Roboschool test suite. Although these algorithms are fundamentally different, both suffer from high variance, low sample efficiency, and hyperparameter sensitivity that, in practice, make these algorithms a no-go for critical operations in the industry.

Interpretable Option Discovery Using Deep Q-Learning and Variational Autoencoders

2021

Deep Reinforcement Learning (RL) is unquestionably a robust framework to train autonomous agents in a wide variety of disciplines. However, traditional deep and shallow model-free RL algorithms suffer from low sample efficiency and inadequate generalization for sparse state spaces. The options framework with temporal abstractions [18] is perhaps the most promising method to solve these problems, but it still has noticeable shortcomings. It only guarantees local convergence, and it is challenging to automate initiation and termination conditions, which in practice are commonly hand-crafted.

On the Convergence of Tsetlin Machines for the IDENTITY- and NOT Operators

2020

The Tsetlin Machine (TM) is a recent machine learning algorithm with several distinct properties, such as interpretability, simplicity, and hardware-friendliness. Although numerous empirical evaluations report on its performance, the mathematical analysis of its convergence is still open. In this article, we analyze the convergence of the TM with only one clause involved for classification. More specifically, we examine two basic logical operators, namely, the "IDENTITY"- and "NOT" operators. Our analysis reveals that the TM, with just one clause, can converge correctly to the intended logical operator, learning from training data over an infinite time horizon. Besides, it can capture arbit…

Intrusion Detection with Interpretable Rules Generated Using the Tsetlin Machine

2020

The rapid deployment in information and communication technologies and internet-based services have made anomaly based network intrusion detection ever so important for safeguarding systems from novel attack vectors. To this date, various machine learning mechanisms have been considered to build intrusion detection systems. However, achieving an acceptable level of classification accuracy while preserving the interpretability of the classification has always been a challenge. In this paper, we propose an efficient anomaly based intrusion detection mechanism based on the Tsetlin Machine (TM). We have evaluated the proposed mechanism over the Knowledge Discovery and Data Mining 1999 (KDD’99) …

The Weighted Tsetlin Machine: Compressed Representations with Weighted Clauses

2019

The Tsetlin Machine (TM) is an interpretable mechanism for pattern recognition that constructs conjunctive clauses from data. The clauses capture frequent patterns with high discriminating power, providing increasing expression power with each additional clause. However, the resulting accuracy gain comes at the cost of linear growth in computation time and memory usage. In this paper, we present the Weighted Tsetlin Machine (WTM), which reduces computation time and memory usage by weighting the clauses. Real-valued weighting allows one clause to replace multiple, and supports fine-tuning the impact of each clause. Our novel scheme simultaneously learns both the composition of the clauses an…

The Regression Tsetlin Machine: A Tsetlin Machine for Continuous Output Problems

2019

The recently introduced Tsetlin Machine (TM) has provided competitive pattern classification accuracy in several benchmarks, composing patterns with easy-to-interpret conjunctive clauses in propositional logic. In this paper, we go beyond pattern classification by introducing a new type of TMs, namely, the Regression Tsetlin Machine (RTM). In all brevity, we modify the inner inference mechanism of the TM so that input patterns are transformed into a single continuous output, rather than to distinct categories. We achieve this by: (1) using the conjunctive clauses of the TM to capture arbitrarily complex patterns; (2) mapping these patterns to a continuous output through a novel voting and n…

The Convolutional Tsetlin Machine

2019

Convolutional neural networks (CNNs) have obtained astounding successes for important pattern recognition tasks, but they suffer from high computational complexity and the lack of interpretability. The recent Tsetlin Machine (TM) attempts to address this lack by using easy-to-interpret conjunctive clauses in propositional logic to solve complex pattern recognition problems. The TM provides competitive accuracy in several benchmarks, while keeping the important property of interpretability. It further facilitates hardware-near implementation since inputs, patterns, and outputs are expressed as bits, while recognition and learning rely on straightforward bit manipulation. In this paper, we ex…

FlashRL: A Reinforcement Learning Platform for Flash Games

2017

Reinforcement Learning (RL) is a research area that has blossomed tremendously in recent years and has shown remarkable potential in among others successfully playing computer games. However, there only exists a few game platforms that provide diversity in tasks and state-space needed to advance RL algorithms. The existing platforms offer RL access to Atari- and a few web-based games, but no platform fully expose access to Flash games. This is unfortunate because applying RL to Flash games have potential to push the research of RL algorithms. This paper introduces the Flash Reinforcement Learning platform (FlashRL) which attempts to fill this gap by providing an environment for thousands of…

A Neural Turing~Machine for Conditional Transition Graph Modeling

2019

Graphs are an essential part of many machine learning problems such as analysis of parse trees, social networks, knowledge graphs, transportation systems, and molecular structures. Applying machine learning in these areas typically involves learning the graph structure and the relationship between the nodes of the graph. However, learning the graph structure is often complex, particularly when the graph is cyclic, and the transitions from one node to another are conditioned such as graphs used to represent a finite state machine. To solve this problem, we propose to extend the memory based Neural Turing Machine (NTM) with two novel additions. We allow for transitions between nodes to be inf…

Increasing the Inference and Learning Speed of Tsetlin Machines with Clause Indexing

2020

The Tsetlin Machine (TM) is a machine learning algorithm founded on the classical Tsetlin Automaton (TA) and game theory. It further leverages frequent pattern mining and resource allocation principles to extract common patterns in the data, rather than relying on minimizing output error, which is prone to overfitting. Unlike the intertwined nature of pattern representation in neural networks, a TM decomposes problems into self-contained patterns, represented as conjunctive clauses. The clause outputs, in turn, are combined into a classification decision through summation and thresholding, akin to a logistic regression function, however, with binary weights and a unit step output function. …

Towards a Deep Reinforcement Learning Approach for Tower Line Wars

2017

There have been numerous breakthroughs with reinforcement learning in the recent years, perhaps most notably on Deep Reinforcement Learning successfully playing and winning relatively advanced computer games. There is undoubtedly an anticipation that Deep Reinforcement Learning will play a major role when the first AI masters the complicated game plays needed to beat a professional Real-Time Strategy game player. For this to be possible, there needs to be a game environment that targets and fosters AI research, and specifically Deep Reinforcement Learning. Some game environments already exist, however, these are either overly simplistic such as Atari 2600 or complex such as Starcraft II fro…

A Novel Multi-Step Finite-State Automaton for Arbitrarily Deterministic Tsetlin Machine Learning

2020

Due to the high energy consumption and scalability challenges of deep learning, there is a critical need to shift research focus towards dealing with energy consumption constraints. Tsetlin Machines (TMs) are a recent approach to machine learning that has demonstrated significantly reduced energy usage compared to neural networks alike, while performing competitively accuracy-wise on several benchmarks. However, TMs rely heavily on energy-costly random number generation to stochastically guide a team of Tsetlin Automata to a Nash Equilibrium of the TM game. In this paper, we propose a novel finite-state learning automaton that can replace the Tsetlin Automata in TM learning, for increased d…

A Regression Tsetlin Machine with Integer Weighted Clauses for Compact Pattern Representation

2020

The Regression Tsetlin Machine (RTM) addresses the lack of interpretability impeding state-of-the-art nonlinear regression models. It does this by using conjunctive clauses in propositional logic to capture the underlying non-linear frequent patterns in the data. These, in turn, are combined into a continuous output through summation, akin to a linear regression function, however, with non-linear components and unity weights. Although the RTM has solved non-linear regression problems with competitive accuracy, the resolution of the output is proportional to the number of clauses employed. This means that computation cost increases with resolution. To reduce this problem, we here introduce i…

The Dreaming Variational Autoencoder for Reinforcement Learning Environments

2018

Reinforcement learning has shown great potential in generalizing over raw sensory data using only a single neural network for value optimization. There are several challenges in the current state-of-the-art reinforcement learning algorithms that prevent them from converging towards the global optima. It is likely that the solution to these problems lies in short- and long-term planning, exploration and memory management for reinforcement learning algorithms. Games are often used to benchmark reinforcement learning algorithms as they provide a flexible, reproducible, and easy to control environment. Regardless, few games feature a state-space where results in exploration, memory, and plannin…

Optimal sampling for estimation with constrained resources using a learning automaton-based solution for the nonlinear fractional knapsack problem

2010

Published version of an article from the journal: Applied intelligence. The original publication is available at Springerlink. http://dx.doi.org/10.1007/s10489-010-0228-1 While training and estimation for Pattern Recognition (PR) have been extensively studied, the question of achieving these when the resources are both limited and constrained is relatively open. This is the focus of this paper. We consider the problem of allocating limited sampling resources in a “real-time” manner, with the explicit purpose of estimating multiple binomial proportions (the extension of these results to non-binomial proportions is, in our opinion, rather straightforward). More specifically, the user is prese…

Thompson Sampling Guided Stochastic Searching on the Line for Deceptive Environments with Applications to Root-Finding Problems

2017

The multi-armed bandit problem forms the foundation for solving a wide range of on-line stochastic optimization problems through a simple, yet effective mechanism. One simply casts the problem as a gambler that repeatedly pulls one out of N slot machine arms, eliciting random rewards. Learning of reward probabilities is then combined with reward maximization, by carefully balancing reward exploration against reward exploitation. In this paper, we address a particularly intriguing variant of the multi-armed bandit problem, referred to as the {\it Stochastic Point Location (SPL) Problem}. The gambler is here only told whether the optimal arm (point) lies to the "left" or to the "right" of the…

Solving Stochastic Nonlinear Resource Allocation Problems Using a Hierarchy of Twofold Resource Allocation Automata.

2010

Published version of an article in the journal: IEEE Transactions on Computers. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works In a multitude of real-world situations, resources must be allocated based on incomplete and noisy information. However, in many cases, incomplete and noisy information render traditional resource allocation techniques ineffective. The decentralized Learning Automata Knapsack Ga…

Learning automata-based solutions to the optimal web polling problem modelled as a nonlinear fractional knapsack problem

2011

Accepted version of an article from the journal: Engineering Applications of Artificial Intelligence. Definitive published version on Elsevier Science Direct: http://dx.doi.org/10.1016/j.engappai.2011.05.018 We consider the problem of polling web pages as a strategy for monitoring the world wide web. The problem consists of repeatedly polling a selection of web pages so that changes that occur over time are detected. In particular, we consider the case where we are constrained to poll a maximum number of web pages per unit of time, and this constraint is typically dictated by the governing communication bandwidth, and by the speed limitations associated with the processing. Since only a fra…

Learning automata based energy-efficient AI hardware design for IoT applications: Learning Automata based AI Hardware

2020

Generalized Bayesian pursuit: A novel scheme for multi-armed Bernoulli bandit problems

2011

Published version of a chapter in the book: IFIP Advances in Information and Communication Technology. Also available from the publisher at: http;//dx.doi.org/10.1007/978-3-642-23960-1_16 In the last decades, a myriad of approaches to the multi-armed bandit problem have appeared in several different fields. The current top performing algorithms from the field of Learning Automata reside in the Pursuit family, while UCB-Tuned and the ε -greedy class of algorithms can be seen as state-of-the-art regret minimizing algorithms. Recently, however, the Bayesian Learning Automaton (BLA) outperformed all of these, and other schemes, in a wide range of experiments. Although seemingly incompatible, in…

Service selection in stochastic environments: a learning-automaton based solution

2011

Published version of an article from the journal: Applied Intelligence. Also available from the publisher on SpringerLink: http://dx.doi.org/10.1007/s10489-011-0280-5 In this paper, we propose a novel solution to the problem of identifying services of high quality. The reported solutions to this problem have, in one way or the other, resorted to using so-called “Reputation Systems” (RSs). Although these systems can offer generic recommendations by aggregating user-provided opinions about the quality of the services under consideration, they are, understandably, prone to “ballot stuffing” and “badmouthing” in a competitive marketplace. In general, unfair ratings may degrade the trustworthine…

Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling

2020

Using logical clauses to represent patterns, Tsetlin Machines (TMs) have recently obtained competitive performance in terms of accuracy, memory footprint, energy, and learning speed on several benchmarks. Each TM clause votes for or against a particular class, with classification resolved using a majority vote. While the evaluation of clauses is fast, being based on binary operators, the voting makes it necessary to synchronize the clause evaluation, impeding parallelization. In this paper, we propose a novel scheme for desynchronizing the evaluation of clauses, eliminating the voting bottleneck. In brief, every clause runs in its own thread for massive native parallelism. For each training…

Explainable Tsetlin Machine framework for fake news detection with credibility score assessment

2021

The proliferation of fake news, i.e., news intentionally spread for misinformation, poses a threat to individuals and society. Despite various fact-checking websites such as PolitiFact, robust detection techniques are required to deal with the increase in fake news. Several deep learning models show promising results for fake news classification, however, their black-box nature makes it difficult to explain their classification decisions and quality-assure the models. We here address this problem by proposing a novel interpretable fake news detection framework based on the recently introduced Tsetlin Machine (TM). In brief, we utilize the conjunctive clauses of the TM to capture lexical and…

The Tsetlin Machine -- A Game Theoretic Bandit Driven Approach to Optimal Pattern Recognition with Propositional Logic

2018

Although simple individually, artificial neurons provide state-of-the-art performance when interconnected in deep networks. Arguably, the Tsetlin Automaton is an even simpler and more versatile learning mechanism, capable of solving the multi-armed bandit problem. Merely by means of a single integer as memory, it learns the optimal action in stochastic environments through increment and decrement operations. In this paper, we introduce the Tsetlin Machine, which solves complex pattern recognition problems with propositional formulas, composed by a collective of Tsetlin Automata. To eliminate the longstanding problem of vanishing signal-to-noise ratio, the Tsetlin Machine orchestrates the au…

Verifying Properties of Tsetlin Machines

2023

Tsetlin Machines (TsMs) are a promising and interpretable machine learning method which can be applied for various classification tasks. We present an exact encoding of TsMs into propositional logic and formally verify properties of TsMs using a SAT solver. In particular, we introduce in this work a notion of similarity of machine learning models and apply our notion to check for similarity of TsMs. We also consider notions of robustness and equivalence from the literature and adapt them for TsMs. Then, we show the correctness of our encoding and provide results for the properties: adversarial robustness, equivalence, and similarity of TsMs. In our experiments, we employ the MNIST and IMDB …

Deep Reinforcement Learning using Capsules in Advanced Game Environments

2018

Reinforcement Learning (RL) is a research area that has blossomed tremendously in recent years and has shown remarkable potential for artificial intelligence based opponents in computer games. This success is primarily due to vast capabilities of Convolutional Neural Networks (ConvNet), enabling algorithms to extract useful information from noisy environments. Capsule Network (CapsNet) is a recent introduction to the Deep Learning algorithm group and has only barely begun to be explored. The network is an architecture for image classification, with superior performance for classification of the MNIST dataset. CapsNets have not been explored beyond image classification. This thesis introduce…

Closed-Form Expressions for Global and Local Interpretation of Tsetlin Machines with Applications to Explaining High-Dimensional Data

2020

Tsetlin Machines (TMs) capture patterns using conjunctive clauses in propositional logic, thus facilitating interpretation. However, recent TM-based approaches mainly rely on inspecting the full range of clauses individually. Such inspection does not necessarily scale to complex prediction problems that require a large number of clauses. In this paper, we propose closed-form expressions for understanding why a TM model makes a specific prediction (local interpretability). Additionally, the expressions capture the most important features of the model overall (global interpretability). We further introduce expressions for measuring the importance of feature value ranges for continuous feature…

Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling

2021

Using logical clauses to represent patterns, Tsetlin Machine (TM) have recently obtained competitive performance in terms of accuracy, memory footprint, energy, and learning speed on several benchmarks. Each TM clause votes for or against a particular class, with classification resolved using a majority vote. While the evaluation of clauses is fast, being based on binary operators, the voting makes it necessary to synchronize the clause evaluation, impeding parallelization. In this paper, we propose a novel scheme for desynchronizing the evaluation of clauses, eliminating the voting bottleneck. In brief, every clause runs in its own thread for massive native parallelism. For each training e…

On using "Stochastic learning on the line" to design novel distance estimation methods

2018

Nivå1

Towards Model-based Reinforcement Learning for Industry-near Environments

2019

Deep reinforcement learning has over the past few years shown great potential in learning near-optimal control in complex simulated environments with little visible information. Rainbow (Q-Learning) and PPO (Policy Optimisation) have shown outstanding performance in a variety of tasks, including Atari 2600, MuJoCo, and Roboschool test suite. While these algorithms are fundamentally different, both suffer from high variance, low sample efficiency, and hyperparameter sensitivity that in practice, make these algorithms a no-go for critical operations in the industry. On the other hand, model-based reinforcement learning focuses on learning the transition dynamics between states in an environme…

A Scheme for Continuous Input to the Tsetlin Machine with Applications to Forecasting Disease Outbreaks

2019

In this paper, we apply a new promising tool for pattern classification, namely, the Tsetlin Machine (TM), to the field of disease forecasting. The TM is interpretable because it is based on manipulating expressions in propositional logic, leveraging a large team of Tsetlin Automata (TA). Apart from being interpretable, this approach is attractive due to its low computational cost and its capacity to handle noise. To attack the problem of forecasting, we introduce a preprocessing method that extends the TM so that it can handle continuous input. Briefly stated, we convert continuous input into a binary representation based on thresholding. The resulting extended TM is evaluated and analyzed…

Interpretable Tsetlin Machine-based Premature Ventricular Contraction Identification

2023

Neural network-based models have found wide use in automatic long-term electrocardiogram (ECG) analysis. However, such black box models are inadequate for analysing physiological signals where credibility and interpretability are crucial. Indeed, how to make ECG analysis transparent is still an open problem. In this study, we develop a Tsetlin machine (TM) based architecture for premature ventricular contraction (PVC) identification by analysing long-term ECG signals. The architecture is transparent by describing patterns directly with logical AND rules. To validate the accuracy of our approach, we compare the TM performance with those of convolutional neural networks (CNNs). Our numerical …

Stochastic discretized learning-based weak estimation: a novel estimation method for non-stationary environments

2016

- Nivå2