Search results for "learning"
showing 10 items of 6669 documents
Online fitted policy iteration based on extreme learning machines
2016
Reinforcement learning (RL) is a learning paradigm that can be useful in a wide variety of real-world applications. However, its applicability to complex problems remains problematic due to different causes. Particularly important among these are the high quantity of data required by the agent to learn useful policies and the poor scalability to high-dimensional problems due to the use of local approximators. This paper presents a novel RL algorithm, called online fitted policy iteration (OFPI), that steps forward in both directions. OFPI is based on a semi-batch scheme that increases the convergence speed by reusing data and enables the use of global approximators by reformulating the valu…
Bio-inspired evolutionary dynamics on complex networks under uncertain cross-inhibitory signals
2019
Given a large population of agents, each agent has three possiblechoices between option 1 or 2 or no option. The two options are equally favorable and the population has to reach consensus on one of the two options quickly and in a distributed way. The more popular an option is, the more likely it is to be chosen by uncommitted agents. Agents committed to one option can be attracted by those committed to the other option through a cross-inhibitory signal. This model originates in the context of honeybee swarms, and we generalize it to duopolistic competition and opinion dynamics. The contributions of this work include (i) the formulation of a model to explain the behavioral traits of the ho…
Game Theoretic Decentralized Feedback Controls in Markov Jump Processes
2017
This paper studies a decentralized routing problem over a network, using the paradigm of mean-field games with large number of players. Building on a state-space extension technique, we turn the problem into an optimal control one for each single player. The main contribution is an explicit expression of the optimal decentralized control which guarantees the convergence both to local and to global equilibrium points. Furthermore, we study the stability of the system also in the presence of a delay which we model using an hysteresis operator. As a result of the hysteresis, we prove existence of multiple equilibrium points and analyze convergence conditions. The stability of the system is ill…
A Hierarchical Learning Scheme for Solving the Stochastic Point Location Problem
2012
Published version of a chapter in the book: Advanced Research in Applied Artificial Intelligence. Also available from the publisher at: http://dx.doi.org/10.1007/978-3-642-31087-4_78 This paper deals with the Stochastic-Point Location (SPL) problem. It presents a solution which is novel in both philosophy and strategy to all the reported related learning algorithms. The SPL problem concerns the task of a Learning Mechanism attempting to locate a point on a line. The mechanism interacts with a random environment which essentially informs it, possibly erroneously, if the unknown parameter is on the left or the right of a given point which also is the current guess. The first pioneering work […
Assembly Process Modeling Through Long Short-Term Memory
2021
This paper studies Long Short-Term Memory as a component of an adaptive assembly assistance system suggesting the next manufacturing step. The final goal is an assistive system able to help the inexperienced workers in their training stage or even experienced workers who prefer such support in their manufacturing activity. In contrast with the earlier analyzed context-based techniques, Long Short-Term Memory can be applied in unknown scenarios. The evaluation was performed on the data collected previously in an experiment with 68 participants assembling as target product a customizable modular tablet. We are interested in identifying the most accurate method of next assembly step prediction…
Extreme Learning Machines for Data Classification Tuning by Improved Bat Algorithm
2018
Single hidden layer feed forward neural networks are widely used for various practical problems. However, the training process for determining synaptic weights of such neural networks can be computationally very expensive. In this paper we propose a new learning algorithm for learning the synaptic weights of the single hidden layer feedforward neural networks in order to reduce the learning time. We propose combining the upgraded bat algorithm with the extreme learning machine. The proposed approach reduces the number of evaluations needed to train a neural network and efficiently finds optimal input weights and the hidden biases. The proposed algorithm was tested on standard benchmark clas…
New results on stability analysis and stabilization of time-delay continuous Markovian jump systems with partially known rates matrix
2015
Summary In this note, the problems of stability analysis and controller synthesis of Markovian jump systems with time-varying delay and partially known transition rates are investigated via an input–output approach. First, the system under consideration is transformed into an interconnected system, and new results on stochastic scaled small-gain condition for stochastic interconnected systems are established, which are crucial for the problems considered in this paper. Based on the system transformation and the stochastic scaled small-gain theorem, stochastic stability of the original system is examined via the stochastic version of the bounded realness of the transformed forward system. Th…
Adjusted bat algorithm for tuning of support vector machine parameters
2016
Support vector machines are powerful and often used technique of supervised learning applied to classification. Quality of the constructed classifier can be improved by appropriate selection of the learning parameters. These parameters are often tuned using grid search with relatively large step. This optimization process can be done computationally more efficiently and more precisely using stochastic search metaheuristics. In this paper we propose adjusted bat algorithm for support vector machines parameter optimization and show that compared to the grid search it leads to a better classifier. We tested our approach on standard set of benchmark data sets from UCI machine learning repositor…
Do Randomized Algorithms Improve the Efficiency of Minimal Learning Machine?
2020
Minimal Learning Machine (MLM) is a recently popularized supervised learning method, which is composed of distance-regression and multilateration steps. The computational complexity of MLM is dominated by the solution of an ordinary least-squares problem. Several different solvers can be applied to the resulting linear problem. In this paper, a thorough comparison of possible and recently proposed, especially randomized, algorithms is carried out for this problem with a representative set of regression datasets. In addition, we compare MLM with shallow and deep feedforward neural network models and study the effects of the number of observations and the number of features with a special dat…
Using Inverse Reinforcement Learning with Real Trajectories to Get More Trustworthy Pedestrian Simulations
2020
Reinforcement learning is one of the most promising machine learning techniques to get intelligent behaviors for embodied agents in simulations. The output of the classic Temporal Difference family of Reinforcement Learning algorithms adopts the form of a value function expressed as a numeric table or a function approximator. The learned behavior is then derived using a greedy policy with respect to this value function. Nevertheless, sometimes the learned policy does not meet expectations, and the task of authoring is difficult and unsafe because the modification of one value or parameter in the learned value function has unpredictable consequences in the space of the policies it represents…