Convergence for iterative reinforcement learning algorithms like TD(O) depends on the sampling strategy for the transitions. However, in practical applications it is convenient to take transition data from arbitrary sources without losing convergence. In this paper we investigate the problem of repeated synchronous updates based on a fixed set of transitions. Our main theorem yields sufficient conditions of convergence for combinations of reinforcement learning algorithms and linear function approximation. This allows to analyse if a certain reinforcement learning algorithm and a certain function approximator are compatible.

We study an explicit parametric model of documents, queries, and relevancy assessment for Information Retrieval (IR). Mean-field methods are applied to analyze the model and derive efficient practical algorithms to estimate the parameters in the problem. The hyperparameters are estimated by a fast approximate leave-one-out cross-validation procedure based on the cavity method. The algorithm is further evaluated on several benchmark databases by comparing with standard algorithms in IR.

This paper presents two new formulations of multiple-instance learning as a maximum margin problem. The proposed extensions of the Support Vector Machine (SVM) learning approach lead to mixed integer quadratic programs that can be solved heuristically. Our generalization of SVMs makes a state-of-the-art classification technique, including nonlinear classification via kernels, available to an area that up to now has been largely dominated by special purpose methods. We present experimental results on a pharmaceutical data set and on applications in automated image indexing and document categorization.

We introduce the notion of Morton-style factorial coding and illustrate how it may help understand information integration and perceptual coding in the brain. We show that by focusing on average responses one may miss the existence of factorial coding mechanisms that become only apparent when analyzing spike count histograms. We show evidence suggesting that the classical/nonclassical receptive field organization in the cortex effectively enforces the development of Morton-style factorial codes. This may provide some cues to help understand perceptual coding in the brain and to develop new unsupervised learning algorithms. While methods like ICA (Bell & Sejnowski, 1997) develop independent codes, in Morton-style coding the goal is to make two or more external aspects of the world become independent when conditioning on internal representations.

We propose analysis of information in speech using three sources - language (phone), speaker and channeL Information in speech is measured as mutual information between the source and the set of features extracted from speech signaL We assume that distribution of features can be modeled using Gaussian distribution. The mutual information is computed using the results of analysis of variability in speech. We observe similarity in the results of phone variability and phone information, and show that the results of the proposed analysis have more meaningful interpretations than the analysis of variability. 1 Introduction Speech signal carries information about the linguistic message, the speaker, the communication channeL In the previous work [1, 2], we proposed analysis of information in speech as analysis of variability in a set of features extracted from the speech signal. The variability was measured as covariance of the features, and analysis was performed using using multivariate analysis of variance (MANOVA). Total variability was divided into three types of variabilities, namely, intra-phone (or phone) variability, speaker variability, and channel variability.

Many control problems take place in continuous state-action spaces, e.g., as in manipulator robotics, where the control objective is often defined as finding a desired trajectory that reaches a particular goal state. While reinforcement learning offers a theoretical framework to learn such control policies from scratch, its applicability to higher dimensional continuous state-action spaces remains rather limited to date. Instead of learning from scratch, in this paper we suggest to learn a desired complex control policy by transforming an existing simple canonical control policy. For this purpose, we represent canonical policies in terms of differential equations with well-defined attractor properties. By nonlinearly transforming the canonical attractor dynamics using techniques from nonparametric regression, almost arbitrary new nonlinear policies can be generated without losing the stability properties of the canonical system. We demonstrate our techniques in the context of learning a set of movement skills for a humanoid robot from demonstrations of a human teacher. Policies are acquired rapidly, and, due to the properties of well formulated differential equations, can be reused and modified online under dynamic changes of the environment. The linear parameterization of nonparametric regression moreover lends itself to recognize and classify previously learned movement skills.

There exist many approaches to clustering, but the important issue of feature selection, i.e., selecting the data attributes that are relevant for clustering, is rarely addressed. Feature selection for clustering is difficult due to the absence of class labels. We propose two approaches to feature selection in the context of Gaussian mixture-based clustering. In the first one, instead of making hard selections, we estimate feature saliencies. An expectation-maximization (EM) algorithm is derived for this task. The second approach extends Koller and Sahami's mutual-informationbased feature relevance criterion to the unsupervised case. Feature selection is then carried out by a backward search scheme. This scheme can be classified as a "wrapper", since it wraps mixture estimation in an outer layer that performs feature selection. Experimental results on synthetic and real data show that both methods have promising performance.

We developed a robust control policy design method in high-dimensional state space by using differential dynamic programming with a minimax criterion. As an example, we applied our method to a simulated five link biped robot. The results show lower joint torques from the optimal control policy compared to a hand-tuned PD servo controller. Results also show that the simulated biped robot can successfully walk with unknown disturbances that cause controllers generated by standard differential dynamic programming and the hand-tuned PD servo to fail. Learning to compensate for modeling error and previously unknown disturbances in conjunction with robust control design is also demonstrated.

We propose a new algorithm to estimate the intrinsic dimension of data sets. The method is based on geometric properties of the data and requires neither parametric assumptions on the data generating model nor input parameters to set. The method is compared to a similar, widelyused algorithm from the same family of geometric techniques. Experiments show that our method is more robust in terms of the data generating distribution and more reliable in the presence of noise.

AdaBoost [3] minimizes an upper error bound which is an exponential function of the margin on the training set [14]. However, the ultimate goal in applications of pattern classification is always minimum error rate. On the other hand, AdaBoost needs an effective procedure for learning weak classifiers, which by itself is difficult especially for high dimensional data. In this paper, we present a novel procedure, called FloatBoost, for learning a better boosted classifier. FloatBoost uses a backtrack mechanism after each iteration of AdaBoost to remove weak classifiers which cause higher error rates. The resulting float-boosted classifier consists of fewer weak classifiers yet achieves lower error rates than AdaBoost in both training and test. We also propose a statistical model for learning weak classifiers, based on a stagewise approximation of the posterior using an overcomplete set of scalar features. Experimental comparisons of FloatBoost and AdaBoost are provided through a difficult classification problem, face detection, where the goal is to learn from training examples a highly nonlinear classifier to differentiate between face and nonface patterns in a high dimensional space. The results clearly demonstrate the promises made by FloatBoost over AdaBoost.