Multiaction learning automata possessing ergodicity of the mean

Multiaction learning automata which update their action probabilities on the basis of the responses they get from an environment are considered in this paper. The automata update the probabilities according to whether the environment responds with a reward or a penalty. Learning automata are said to possess ergodicity of the mean if the mean action probability is the state probability (or unconditional probability) of an ergodic Markov chain. In an earlier paper [11] we considered the problem of a two-action learning automaton being ergodic in the mean (EM). The family of such automata was characterized completely by proving the necessary and sufficient conditions for automata to be EM. In this paper, we generalize the results of [11] and obtain necessary and sufficient conditions for the multiaction learning automaton to be EM. These conditions involve two families of probability updating functions. It is shown that for the automaton to be EM the two families must be linearly dependent. The vector defining the linear dependence is the only vector parameter which controls the rate of convergence of the automaton. Further, the technique for reducing the variance of the limiting distribution is discussed. Just as in the two-action case, it is shown that the set of absolutely expedient schemes and the set of schemes which possess ergodicity of the mean are mutually disjoint.

An innovative clustering technique for unsupervized learning in the context of remotely sensed earth resources data analysis

A new clustering technique, based on the concept of immediato neighbourhood, with a novel capability to self-learn the number of clusters expected in the unsupervized environment, has been developed. The method compares favourably with other clustering schemes based on distance measures, both in terms of conceptual innovations and computational economy. Test implementation of the scheme using C-l flight line training sample data in a simulated unsupervized mode has brought out the efficacy of the technique. The technique can easily be implemented as a front end to established pattern classification systems with supervized learning capabilities to derive unified learning systems capable of operating in both supervized and unsupervized environments. This makes the technique an attractive proposition in the context of remotely sensed earth resources data analysis wherein it is essential to have such a unified learning system capability.

New algorithms of the Q-learning type

We propose two algorithms for Q-learning that use the two-timescale stochastic approximation methodology. The first of these updates Q-values of all feasible state–action pairs at each instant while the second updates Q-values of states with actions chosen according to the ‘current’ randomized policy updates. A proof of convergence of the algorithms is shown. Finally, numerical experiments using the proposed algorithms on an application of routing in communication networks are presented on a few different settings.

Mechanism design for cost optimal PAC learning in the presence of strategic noisy annotators

We consider the problem of Probably Ap-proximate Correct (PAC) learning of a bi-nary classifier from noisy labeled exam-ples acquired from multiple annotators(each characterized by a respective clas-sification noise rate). First, we consider the complete information scenario, where the learner knows the noise rates of all the annotators. For this scenario, we derive sample complexity bound for the Mini-mum Disagreement Algorithm (MDA) on the number of labeled examples to be ob-tained from each annotator. Next, we consider the incomplete information sce-nario, where each annotator is strategic and holds the respective noise rate as a private information. For this scenario, we design a cost optimal procurement auc-tion mechanism along the lines of Myer-son’s optimal auction design framework in a non-trivial manner. This mechanism satisfies incentive compatibility property,thereby facilitating the learner to elicit true noise rates of all the annotators.

Resolution and sensitivity of the eyes of the Asian honeybees Apis florea, Apis cerana and Apis dorsata

Bees of the genus Apis are important foragers of nectar and pollen resources. Although the European honeybee, Apis mellifera, has been well studied with respect to its sensory abilities, learning behaviour and role as pollinators, much less is known about the other Apis species. We studied the anatomical spatial resolution and absolute sensitivity of the eyes of three sympatric species of Asian honeybees, Apis cerana, Apis florea and Apis dorsata and compared them with the eyes of A. mellifera. Of these four species, the giant honeybee A. dorsata (which forages during moonlit nights) has the lowest spatial resolution and the most sensitive eyes, followed by A. mellifera, A. cerana and the dwarf honeybee, A. florea (which has the smallest acceptance angles and the least sensitive eyes). Moreover, unlike the strictly diurnal A. cerana and A. florea, A. dorsata possess large ocelli, a feature that it shares with all dim-light bees. However, the eyes of the facultatively nocturnal A. dorsata are much less sensitive than those of known obligately nocturnal bees such as Megalopta genalis in Panama and Xylocopa tranquebarica in India. The differences in sensitivity between the eyes of A. dorsata and other strictly diurnal Apis species cannot alone explain why the former is able to fly, orient and forage at half-moon light levels. We assume that additional neuronal adaptations, as has been proposed for A. mellifera, M. genalis and X. tranquebarica, might exist in A. dorsata.

A Team of Continuous-Action Learning Automata for Noise-Tolerant Learning of Half-Spaces

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.

Two elementary proofs of the Wigner theorem on symmetry in quantum mechanics

In quantum theory, symmetry has to be defined necessarily in terms of the family of unit rays, the state space. The theorem of Wigner asserts that a symmetry so defined at the level of rays can always be lifted into a linear unitary or an antilinear antiunitary operator acting on the underlying Hilbert space. We present two proofs of this theorem which are both elementary and economical. Central to our proofs is the recognition that a given Wigner symmetry can, by post-multiplication by a unitary symmetry, be taken into either the identity or complex conjugation. Our analysis often focuses on the behaviour of certain two-dimensional subspaces of the Hilbert space under the action of a given Wigner symmetry, but the relevance of this behaviour to the larger picture of the whole Hilbert space is made transparent at every stage.

Two timescale analysis of the Alopex algorithm for optimization

Alopex is a correlation-based gradient-free optimization technique useful in many learning problems. However, there are no analytical results on the asymptotic behavior of this algorithm. This article presents a new version of Alopex that can be analyzed using techniques of two timescale stochastic approximation method. It is shown that the algorithm asymptotically behaves like a gradient-descent method, though it does not need (or estimate) any gradient information. It is also shown, through simulations, that the algorithm is quite effective.

Infinite push: a new support vector ranking algorithm that directly optimizes accuracy at the absolute top of the list

Ranking problems have become increasingly important in machine learning and data mining in recent years, with applications ranging from information retrieval and recommender systems to computational biology and drug discovery. In this paper, we describe a new ranking algorithm that directly maximizes the number of relevant objects retrieved at the absolute top of the list. The algorithm is a support vector style algorithm, but due to the different objective, it no longer leads to a quadratic programming problem. Instead, the dual optimization problem involves l1, ∞ constraints; we solve this dual problem using the recent l1, ∞ projection method of Quattoni et al (2009). Our algorithm can be viewed as an l∞-norm extreme of the lp-norm based algorithm of Rudin (2009) (albeit in a support vector setting rather than a boosting setting); thus we refer to the algorithm as the ‘Infinite Push’. Experiments on real-world data sets confirm the algorithm’s focus on accuracy at the absolute top of the list.