Sastry, PS and Nagendra, GD and Manwani, Naresh (2010) A Team of Continuous-Action Learning Automata for Noise-Tolerant Learning of Half-Spaces. In: IEEE Transactions on systems man and cybernetics part b-cybernetics, 40 (1). pp. 19-28.
28.pdf - Published Version
Restricted to Registered users only
Download (293Kb) | Request a copy
Learning automata are adaptive decision making devices that are found useful in a variety of machine learning and pattern recognition applications. Although most learning automata methods deal with the case of finitely many actions for the automaton, there are also models of continuous-action-set learning automata (CALA). A team of such CALA can be useful in stochastic optimization problems where one has access only to noise-corrupted values of the objective function. In this paper, we present a novel formulation for noise-tolerant learning of linear classifiers using a CALA team. We consider the general case of nonuniform noise, where the probability that the class label of an example is wrong may be a function of the feature vector of the example. The objective is to learn the underlying separating hyperplane given only such noisy examples. We present an algorithm employing a team of CALA and prove, under some conditions on the class conditional densities, that the algorithm achieves noise-tolerant learning as long as the probability of wrong label for any example is less than 0.5. We also present some empirical results to illustrate the effectiveness of the algorithm.
|Item Type:||Journal Article|
|Additional Information:||Copyright 2010 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.|
|Keywords:||Continuous-action-set learning automata (CALA); hyperplane classifiers;learning automata; noise-tolerant learning; stochastic optimization; team of automata|
|Department/Centre:||Division of Electrical Sciences > Electrical Engineering|
|Date Deposited:||02 Dec 2009 04:49|
|Last Modified:||19 Sep 2010 05:52|
Actions (login required)