A cooperative game of a pair of learning automata

A cooperative game played in a sequential manner by a pair of learning automata is investigated in this paper. The automata operate in an unknown random environment which gives a common pay-off to the automata. Necessary and sufficient conditions on the functions in the reinforcement scheme are given for absolute monotonicity which enables the expected pay-off to be monotonically increasing in any arbitrary environment. As each participating automaton operates with no information regarding the other partner, the results of the paper are relevant to decentralized control.

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.

Diversity in the Early Years: Intercultural Learning and Teaching

"New global contexts are presenting new challenges and new possibilities for young children and those around them. Climate change, armed conflict and poverty combine with new frontiers of discovery in science and technology to create a paradoxical picture of both threat and opportunity for our world and our children. On the one hand, children are experiencing unprecedented patterns of disparity and inequity; yet, on the other hand, they have seemingly limitless possibilities to engage with new technologies and social processes. Seismic shifts such as these are inviting new questions about the conditions that young children need to learn and thrive. Diversity in the Early Years: Intercultural Learning and Teaching explores significant aspects of working with children and adults from diverse backgrounds. It is a valuable resource for teaching early childhood pre-service teachers to raise awareness about issues of diversity - whether diversity of culture, language, education and/or gender - and for helping them to develop their own pedagogical approaches to working with diverse populations."--Publisher website

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.

Performance Modeling based on Multidimensional Surface Learning for Performance Predictions of Parallel Applications in Non-Dedicated Environments

Modeling the performance behavior of parallel applications to predict the execution times of the applications for larger problem sizes and number of processors has been an active area of research for several years. The existing curve fitting strategies for performance modeling utilize data from experiments that are conducted under uniform loading conditions. Hence the accuracy of these models degrade when the load conditions on the machines and network change. In this paper, we analyze a curve fitting model that attempts to predict execution times for any load conditions that may exist on the systems during application execution. Based on the experiments conducted with the model for a parallel eigenvalue problem, we propose a multi-dimensional curve-fitting model based on rational polynomials for performance predictions of parallel applications in non-dedicated environments. We used the rational polynomial based model to predict execution times for 2 other parallel applications on systems with large load dynamics. In all the cases, the model gave good predictions of execution times with average percentage prediction errors of less than 20%

Boosting-based transfer learning for multi-view head-pose classification from surveillance videos

This work proposes a boosting-based transfer learning approach for head-pose classification from multiple, low-resolution views. Head-pose classification performance is adversely affected when the source (training) and target (test) data arise from different distributions (due to change in face appearance, lighting, etc). Under such conditions, we employ Xferboost, a Logitboost-based transfer learning framework that integrates knowledge from a few labeled target samples with the source model to effectively minimize misclassifications on the target data. Experiments confirm that the Xferboost framework can improve classification performance by up to 6%, when knowledge is transferred between the CLEAR and FBK four-view headpose datasets.

Convex analysis for minimizing and learning submodular set functions

The connections between convexity and submodularity are explored, for purposes of minimizing and learning submodular set functions.

First, we develop a novel method for minimizing a particular class of submodular functions, which can be expressed as a sum of concave functions composed with modular functions. The basic algorithm uses an accelerated first order method applied to a smoothed version of its convex extension. The smoothing algorithm is particularly novel as it allows us to treat general concave potentials without needing to construct a piecewise linear approximation as with graph-based techniques.

Second, we derive the general conditions under which it is possible to find a minimizer of a submodular function via a convex problem. This provides a framework for developing submodular minimization algorithms. The framework is then used to develop several algorithms that can be run in a distributed fashion. This is particularly useful for applications where the submodular objective function consists of a sum of many terms, each term dependent on a small part of a large data set.

Lastly, we approach the problem of learning set functions from an unorthodox perspective---sparse reconstruction. We demonstrate an explicit connection between the problem of learning set functions from random evaluations and that of sparse signals. Based on the observation that the Fourier transform for set functions satisfies exactly the conditions needed for sparse reconstruction algorithms to work, we examine some different function classes under which uniform reconstruction is possible.

Bayesian and L1 Approaches to Sparse Unsupervised Learning

The use of L1 regularisation for sparse learning has generated immense research interest, with successful application in such diverse areas as signal acquisition, image coding, genomics and collaborative filtering. While existing work highlights the many advantages of L1 methods, in this paper we find that L1 regularisation often dramatically underperforms in terms of predictive performance when compared with other methods for inferring sparsity. We focus on unsupervised latent variable models, and develop L1 minimising factor models, Bayesian variants of "L1", and Bayesian models with a stronger L0-like sparsity induced through spike-and-slab distributions. These spike-and-slab Bayesian factor models encourage sparsity while accounting for uncertainty in a principled manner and avoiding unnecessary shrinkage of non-zero values. We demonstrate on a number of data sets that in practice spike-and-slab Bayesian methods outperform L1 minimisation, even on a computational budget. We thus highlight the need to re-assess the wide use of L1 methods in sparsity-reliant applications, particularly when we care about generalising to previously unseen data, and provide an alternative that, over many varying conditions, provides improved generalisation performance.

Perceptual learning, roving and the unsupervised bias

Perceptual learning improves perception through training. Perceptual learning improves with most stimulus types but fails when . certain stimulus types are mixed during training (roving). This result is surprising because classical supervised and unsupervised neural network models can cope easily with roving conditions. What makes humans so inferior compared to these models? As experimental and conceptual work has shown, human perceptual learning is neither supervised nor unsupervised but reward-based learning. Reward-based learning suffers from the so-called unsupervised bias, i.e., to prevent synaptic " drift" , the . average reward has to be exactly estimated. However, this is impossible when two or more stimulus types with different rewards are presented during training (and the reward is estimated by a running average). For this reason, we propose no learning occurs in roving conditions. However, roving hinders perceptual learning only for combinations of similar stimulus types but not for dissimilar ones. In this latter case, we propose that a critic can estimate the reward for each stimulus type separately. One implication of our analysis is that the critic cannot be located in the visual system. © 2011 Elsevier Ltd.

Reinforcement learning using a continuous time actor-critic framework with spiking neurons.

Animals repeat rewarded behaviors, but the physiological basis of reward-based learning has only been partially elucidated. On one hand, experimental evidence shows that the neuromodulator dopamine carries information about rewards and affects synaptic plasticity. On the other hand, the theory of reinforcement learning provides a framework for reward-based learning. Recent models of reward-modulated spike-timing-dependent plasticity have made first steps towards bridging the gap between the two approaches, but faced two problems. First, reinforcement learning is typically formulated in a discrete framework, ill-adapted to the description of natural situations. Second, biologically plausible models of reward-modulated spike-timing-dependent plasticity require precise calculation of the reward prediction error, yet it remains to be shown how this can be computed by neurons. Here we propose a solution to these problems by extending the continuous temporal difference (TD) learning of Doya (2000) to the case of spiking neurons in an actor-critic network operating in continuous time, and with continuous state and action representations. In our model, the critic learns to predict expected future rewards in real time. Its activity, together with actual rewards, conditions the delivery of a neuromodulatory TD signal to itself and to the actor, which is responsible for action choice. In simulations, we show that such an architecture can solve a Morris water-maze-like navigation task, in a number of trials consistent with reported animal performance. We also use our model to solve the acrobot and the cartpole problems, two complex motor control tasks. Our model provides a plausible way of computing reward prediction error in the brain. Moreover, the analytically derived learning rule is consistent with experimental evidence for dopamine-modulated spike-timing-dependent plasticity.

Job change and workplace learning in the public sector: the significance of new technology for unskilled work.

Focussing here on local authorities and health services, this paper examines the significance of new technology to unskilled work in the public sector as it is developing and the implications for workplace learning. An argument is developed that new technology is central to a minority of examples of job change, although, significantly, it is more important to staff–initiated change and to workers’ ability to fully participate in life beyond the workplace.

Workplace learning and the employment relationship in the public sector.

Training that is relevant to employers is not necessarily enriching for employees, especially those on the lower salary scales. The authors argue that the analysis of training and development needs to be understood in the context of the employment relationship. Drawing on reasearch evidence from six case studies in the public sector, the article examines the impact of changes in work organisation on workplace learning, managers' and employees' own strategies towards it and the limitations of tools such as appraisal. Since employees' existing qualifications are poorly utilised and their development needs often frustrated, issues concerning job design, occupational progression routes and employee entitlements need to be addressed

Learning from patterns during information technology configuration.

This paper asks how people can be assisted in learning from practice, as a basis for informing future action, when configuring information technology (IT) in organizations. It discusses the use of Alexanderian Patterns as a means of aiding such learning. Three patterns are presented that have been derived from a longitudinal empirical study that has focused on practices surrounding IT configuration. The paper goes on to argue that Alexanderian Patterns offer a valuable means of learning from past experience. It is argued that learning from experience is an important dimension of deciding “what needs to be done” in configuring IT with organizational context. The three patterns outlined are described in some detail, and the implications of each discussed. Although it is argued that patterns, per se, provide a valuable tool for learning from experience, some potential dangers in seeking to codify experience with a patterns approach are also discussed.

How to run successful e-internships: a case for organizational learning.

Purpose – The purpose of this paper is to outline unique learning experience that virtual/e-internships can offer small and medium-sized enterprises and start-up organizations. Design/methodology/approach – We interviewed 18 experts on e-internships (interns and managers of internships) across several countries to learn more about the learning experiences for both organizations and interns. The information from these interviews was also used to formulate a number of recommendations. Findings – The interviews provided insights into how e-internships can provide development opportunities for interns, managers and staff within these organizations. One important benefit pertains to the skill development of both interns and managers. The interns get unique working experiences that also benefit the organizations in terms of their creativity, input and feedback. In return, managers get a unique learning experience that helps them expand their project management skills, interpersonal skills and mentoring. Practical implications – We outline a number of recommendations that consider skill development, the benefit of diversity in numerous forms as well as mutual benefits for enterprises and start-ups. Originality/value – The discussion of the various benefits and conditions under which virtual internships will succeed in organizations provide practitioners an insight into the organizational opportunities available to them given the right investment into e-interns and internship schemes.

Error-driven active learning in growing radial basis function networks for early robot learning

Q. Meng and M.H. Lee, 'Error-driven active learning in growing radial basis function networks for early robot learning', 2006 IEEE International Conference on Robotics and Automation (IEEE ICRA 2006), 2984-90, Orlando, Florida, USA.