Search results for "machine"
showing 10 items of 2592 documents
BELM: Bayesian Extreme Learning Machine
2011
The theory of extreme learning machine (ELM) has become very popular on the last few years. ELM is a new approach for learning the parameters of the hidden layers of a multilayer neural network (as the multilayer perceptron or the radial basis function neural network). Its main advantage is the lower computational cost, which is especially relevant when dealing with many patterns defined in a high-dimensional space. This brief proposes a bayesian approach to ELM, which presents some advantages over other approaches: it allows the introduction of a priori knowledge; obtains the confidence intervals (CIs) without the need of applying methods that are computationally intensive, e.g., bootstrap…
SAGECELL: Software-Defined Space-Air-Ground Integrated Moving Cells
2018
Ultra-dense networks (UDNs) provide an effective solution to accommodate the explosively growing data traffic of multimedia services and real-time applications. However, the densification of large numbers of static small cells faces many fundamental challenges, including deployment cost, energy consumption and control, and so on. This motivates us to develop software-defined space-air-ground integrated moving cells (SAGECELL), a programmable, scalable, and flexible framework to integrate space, air, and ground resources for matching dynamic traffic demands with network capacity supplies. First, we provide a comprehensive review of state-of-the-art literature. Then the conceptual architectur…
Moving Learning Machine Towards Fast Real-Time Applications: A High-Speed FPGA-based Implementation of the OS-ELM Training Algorithm
2018
Currently, there are some emerging online learning applications handling data streams in real-time. The On-line Sequential Extreme Learning Machine (OS-ELM) has been successfully used in real-time condition prediction applications because of its good generalization performance at an extreme learning speed, but the number of trainings by a second (training frequency) achieved in these continuous learning applications has to be further reduced. This paper proposes a performance-optimized implementation of the OS-ELM training algorithm when it is applied to real-time applications. In this case, the natural way of feeding the training of the neural network is one-by-one, i.e., training the neur…
Noise assisted image processing by ensembles of R-SETs
2017
AbstractWe study how noise can assist the processing of an image in a resistance-single electron transistor (R-SET) model. The image is an 8-bit black and white picture. Every grey level is codified linearly into a sub-threshold input potential applied for a prescribed time window to an ensemble of R-SETs that transforms it into a spiking frequency. The addition of a background white noise potential of high amplitude permits the ensemble to process the image by means of the stochastic resonance phenomenon. Aside from the positive aspects, we analyse the negative impact of using noise and how we can minimize it using redundancy and a longer measuring time. The results are compared with the c…
Perceptual adaptive insensitivity for support vector machine image coding.
2005
Support vector machine (SVM) learning has been recently proposed for image compression in the frequency domain using a constant epsilon-insensitivity zone by Robinson and Kecman. However, according to the statistical properties of natural images and the properties of human perception, a constant insensitivity makes sense in the spatial domain but it is certainly not a good option in a frequency domain. In fact, in their approach, they made a fixed low-pass assumption as the number of discrete cosine transform (DCT) coefficients to be used in the training was limited. This paper extends the work of Robinson and Kecman by proposing the use of adaptive insensitivity SVMs [2] for image coding u…
Dual-model approach for safety-critical embedded systems
2020
Abstract The paper presents the design of digital controllers based on two models: the Petri net model, and the UML state machine. These two approaches differ in many aspects of design flow, such as conceptual modelling, and analysis and synthesis. Each of these approaches can be used individually to design an efficient logic controller, and such solutions are well-known, but their interoperability can contribute to a much better understanding of logic controller design and validation. This is especially important in the case of safety- or life-critical embedded systems, and apart from this, a dual-model controller design can make up redundant system increasing its reliability.
Pain fingerprinting using multimodal sensing: pilot study
2021
Abstract Pain is a complex phenomenon, the experience of which varies widely across individuals. At worst, chronic pain can lead to anxiety and depression. Cost-effective strategies are urgently needed to improve the treatment of pain, and thus we propose a novel home-based pain measurement system for the longitudinal monitoring of pain experience and variation in different patients with chronic low back pain. The autonomous nervous system and audio-visual features are analyzed from heart rate signals, voice characteristics and facial expressions using a unique measurement protocol. Self-reporting is utilized for the follow-up of changes in pain intensity, induced by well-designed physical …
Predicting overweight and obesity in later life from childhood data: A review of predictive modeling approaches
2019
Background: Overweight and obesity are an increasing phenomenon worldwide. Predicting future overweight or obesity early in the childhood reliably could enable a successful intervention by experts. While a lot of research has been done using explanatory modeling methods, capability of machine learning, and predictive modeling, in particular, remain mainly unexplored. In predictive modeling models are validated with previously unseen examples, giving a more accurate estimate of their performance and generalization ability in real-life scenarios. Objective: To find and review existing overweight or obesity research from the perspective of employing childhood data and predictive modeling metho…
Computational Complexity and Communication: Coordination in Two-Player Games
2002
The main contribution of this paper is the development and application of cryptographic techniques to the design of strategic communication mechanisms. One of the main assumptions in cryptography is the limitation of the computational power available to agents. We introduce the concept of limited computational complexity, and by borrowing results from cryptography, we construct a communication protocol to establish that every correlated equilibrium of a two-person game with rational payoffs can be achieved by means of computationally restricted unmediated communication. This result provides an example in game theory where limitations of computational abilities of players are helpful in solv…
Solving dynamic bandit problems and decentralized games using the kalman bayesian learning automaton
2010
Masteroppgave i informasjons- og kommunikasjonsteknologi 2010 – Universitetet i Agder, Grimstad Multi-armed bandit problems have been subject to a lot of research in computer science because it captures the fundamental dilemma of exploration versus exploitation in reinforcement learning. The goal of a bandit problem is to determine the optimal balance between the gain of new information (exploration) and immediate reward maximization (exploitation). Dynamic bandit problems are especially challenging because they involve changing environments. Combined with game theory, where one analyze the behavior of agents in multi-agent settings, bandit problems serves as a framework for benchmarking th…