For manytypes of learners one can compute the statistically "optimal" way to select data. We review how these techniques have been used with feedforward neural networks [MacKay, 1992# Cohn, 1994]. We then showhow the same principles may be used to select data for two alternative, statistically-based learning architectures: mixtures of Gaussians and locally weighted regression. While the techniques for neural networks are expensive and approximate, the techniques for mixtures of Gaussians and locally weighted regression are both efficient and accurate.

We show that all algorithms that search for an extremum of a cost function perform exactly the same, when averaged over all possible cost functions. In particular, if algorithm A outperforms algorithm B on some cost functions, then loosely speaking there must exist exactly as many other functions where B outperforms A. Starting from this we analyze a number of the other a priori characteristics of the search problem, like its geometry and its information-theoretic aspects. This analysis allows us to derive mathematical benchmarks for assessing a particular search algorithm 's performance. We also investigate minimax aspects of the search problem, the validity of using characteristics of a partial search over a cost function to predict future behavior of the search algorithm on that cost function, and time-varying cost functions. We conclude with some discussion of the justifiability of biologically-inspired search methods.

This paper shows how a text classifier's need for labeled training data can be reduced by a combination of active learning and Expectation Maximization (EM) on a pool of unlabeled data. Query-by-Committee is used to actively select documents for labeling, then EM with a naive Bayes model further improves classification accuracy by concurrently estimating probabilistic labels for the remaining unlabeled documents and using them to improve the model. We also present a metric for better measuring disagreement among committee members; it accounts for the strength of their disagreement and for the distribution of the documents. Experimental results show that our method of combining EM and active learning requires only half as many labeled training examples to achieve the same accuracy as either EM or active learning alone. Keywords: text classification active learning unsupervised learning information retrieval 1 Introduction In many settings for learning text classifiers, obtaining lab...

This report is a repository for the results obtained from a large scale empirical comparison of seven iterative and evolution-based optimization heuristics. Twenty-seven static optimization problems, spanning six sets of problem classes which are commonly explored in genetic algorithm literature, are examined. The problem sets include job-shop scheduling, traveling salesman, knapsack, binpacking, neural network weight optimization, and standard numerical optimization. The search spaces in these problems range from 2^368 to 2^2040. The results indicate that using genetic algorithms for the optimization of static functions does not yield a benefit, in terms of the final answer obtained, over simpler optimization heuristics. Descriptions of the algorithms tested and the encodings of the problems are described in detail for reproducibility.

The key idea behind active learning is that a machine learning algorithm can achieve greater accuracy with fewer labeled training instances if it is allowed to choose the data from which is learns. An active learner may ask queries in the form of unlabeled instances to be labeled by an oracle (e.g., a human annotator). Active learning is well-motivated in many modern machine learning problems, where unlabeled data may be abundant but labels are difficult, time-consuming, or expensive to obtain. This report provides a general introduction to active learning and a survey of the literature. This includes a discussion of the scenarios in which queries can be formulated, and an overview of the query strategy frameworks proposed in the literature to date. An analysis of the empirical and theoretical evidence for active learning, a summary of several problem setting variants, and a discussion

We propose an active learning method with hidden-unit reduction, which is devised specially for multilayer perceptrons (MLP). First, we review our active learning method, and point out that many Fisher-information-based methods applied to MLP have a critical problem: the information matrix may be singular. To solve this problem, we derive the singularity condition of an information matrix, and propose an active learning technique that is applicable to MLP. Its effectiveness is verified through experiments. 1 INTRODUCTION When one trains a learning machine using a set of data given by the true system, its ability can be improved if one selects the training data actively. In this paper, we consider the problem of active learning in multilayer perceptrons (MLP). First, we review our method of active learning (Fukumizu el al., 1994), in which we prepare a probability distribution and obtain training data as samples from the distribution. This methodology leads us to an information-matrix-...

Finding the Bayesian balance between exploration and exploitation in adaptive optimal control is in general intractable. This paper shows how to compute suboptimal estimates based on a certainty equivalence approximation (Cozzolino, Gonzalez-Zubieta & Miller, 1965) arising from a form of dual control. This systematizes and extends existing uses of exploration bonuses in reinforcement learning (Sutton, 1990). The approach has two components: a statistical model of uncertainty in the world and a way of turning this into exploratory behavior. This general approach is applied to two-dimensional mazes with moveable barriers and its performance is compared with Sutton’s DYNA system.

For an agent living in a non-deterministic Markov environment (NME), what is, in theory, the fastest way of acquiring information about its statistical properties? The answer is: to design "optimal" sequences of "experiments" by performing action sequences that maximize expected information gain. This notion is implemented by combining concepts from information theory and reinforcement learning. Experiments show that the resulting method, reinforcement driven information acquisition, can explore certain NMEs much faster than conventional random exploration.

The paper is addressed to AI workers with an interest in biomolecular genetics and also to biomolecular geneticists interested in what AI tools may do for them. The authors are engaged in a collaborative enterprise aimed at partially automating some aspects of scientic work. These aspects include the processes of forming hypotheses, devising trials to discriminate between these competing hypotheses, physically performing these trials and then using the results of these trials to converge upon an accurate hypothesis. As a potential component of the reasoning carried out by an \articial scientist" this paper describes ASEProgol, an Active Learning system which uses Inductive Logic Programming to construct hypothesised rst-order theories and uses a CART-like algorithm to select trials for eliminating ILP derived hypotheses. In simulated yeast growth tests ASE-Progol was used to rediscover how genes participate in the aromatic amino acid pathway of Saccharomyces cerevisiae. The cost of the chemicals consumed in converging upon a hypothesis with an accuracy of around 88% was reduced by ve orders of magnitude when trials were selected by ASE-Progol rather than being sampled at random. While the naive strategy of always choosing the cheapest trial from the set of candidate trials led to lower cumulative costs than ASE-Progol, both the naive strategy and the random strategy took signicantly longer to converge upon a nal hypothesis than ASE-Progol. For example to reach an accuracy of 80%, ASE-Progol required 4 days while random sampling required 6 days and the naive strategy required 10 days. 1 1

HQ-learning is a hierarchical extension of Q()-learning designed to solve certain types of partially observable Markov decision problems (POMDPs). HQ automatically decomposes POMDPs into sequences of simpler subtasks that can be solved by memoryless policies learnable by reactive subagents. HQ can solve partially observable mazes with more states than those used in most previous POMDP work.