One popular learning algorithm for feedforward neural networks is the backpropagation (BP) algorithm which includes parameters, learning rate (eta), momentum factor (alpha) and steepness parameter (lambda). The appropriate selections of these parameters have large effects on the convergence of the algorithm. Many techniques that adaptively adjust these parameters have been developed to increase speed of convergence. In this paper, we shall present several classes of learning automata based solutions to the problem of adaptation of BP algorithm parameters. By interconnection of learning automata to the feedforward neural networks, we use learning automata scheme for adjusting the parameters eta, alpha, and lambda based on the observation of random response of the neural networks. One of the important aspects of the proposed schemes is its ability to escape from local minima with high possibility during the training period. The feasibility of proposed methods is shown through simulations on several problems.

/pdf/new-learning-automata-based-algorithms-for-adaptation-of-1a4l169l0d.pdf

New learning automata based algorithms for adaptation of backpropagation algorithm parameters

In this paper we examine the behavior of Ad Hoc networks through simulations, using different routing protocols and various topologies. We examine the difference in performance, using CBR application, with packets of different size through a variety of topologies, showing the impact node placement has on networks performance. We show that the choice of routing protocol plays an important role on network’s performance. We also quantify node mobility effects, by looking into both static and fully mobile configurations. Our paper presents a systematic analysis of a variety of different ad hoc network topologies in terms of node placement, node mobility and routing protocols through several simulated scenarios.

IJCSI Publicity Board 2010

A note on learning automata-based schemes for adaptation of BP parameters

This study is concerned with finite Markov decision processes whose dynamics and reward structure are unknown but the state is observable exactly. We establish a learning algorithm which yields an optimal policy and construct an adaptive policy which is optimal under the average expected reward criterion.

https://www.jstor.org/stable/pdfplus/3214080.pdf

Learning algorithms for markov decision processes

ε-Optimality of a general class of learning algorithms

On a general class of absorbing-barrier learning algorithms

Learning algorithms have been extensively studied in Mathematical Psychology [13] [14] [18] for decades and more recently in Learning Automata Theory and Mathematical Statistics [1] [2] [8] [11] [16]. In Mathematical Psychology the interest in learning stems from the desire to understand the observed animal learning and associated changes in their behavior. However, in Learning Automata Theory and Mathematical Statistics the aim is to build algorithms that exhibit prespecified behaviour. Our interests, in this paper, are in the latter approach.

S. Lakshmivarahan

Papers

ε-Optimality of a general class of learning algorithms

On a general class of absorbing-barrier learning algorithms

On a Class of Learning Algorithms with Symmetric Behavior under Success and Failure