Standard value function approaches to finding policies for Partially Observable Markov Decision Processes (POMDPs) are generally considered to be intractable for large models. The intractability of these algorithms is to a large extent a consequence of computing an exact, optimal policy over the entire belief space. However, in real-world POMDP problems, computing the optimal policy for the full belief space is often unnecessary for good control even for problems with complicated policy classes. The beliefs experienced by the controller often lie near a structured, low-dimensional manifold embedded in the high-dimensional belief space. Finding a good approximation to the optimal value function for only this manifold can be much easier than computing the full value function. We introduce a new method for solving large-scale POMDPs by reducing the dimensionality of the belief space. We use Exponential family Principal Components Analysis (Collins, Dasgupta, & Schapire, 2002) to represent sparse, high-dimensional belief spaces using low-dimensional sets of learned features of the belief state. We then plan only in terms of the low-dimensional belief features. By planning in this low-dimensional space, we can find policies for POMDP models that are orders of magnitude larger than models that can be handled by conventional techniques. We demonstrate the use of this algorithm on a synthetic problem and on mobile robot navigation tasks. 1.

In this paper we report preliminary results from an ongoing study that investigates the performance of machine learning classifiers on a diverse set of Natural Language Processing (NLP) tasks. First, we compare a number of popular existing learning methods (Neural networks, Memory-based learning, Rule induction, Decision trees, Maximum Entropy, Winnow Perceptrons, Naive Bayes and Support Vector Machines), and discuss their properties vis a vis typical NLP data sets. Next, we turn to methods to optimize the parameters of single learning methods through cross-validation and evolutionary algorithms. Then we investigate how we can get the best of all single methods through combination of the tested systems in classifier ensembles. Finally we discuss new and more thorough methods of automatically constructing ensembles of classifiers based on the techniques used for parameter optimization.

An extension to memory-based learning is described in which automatically induced rules are used as binary features. These features have an "active" value when the left-hand side of the underlying rule applies to the instance. The RIPPER rule induction algorithm is adopted for the selection of the underlying rules. The similarity of a memory instance to a new instance is measured by taking the sum of the weights of the matching rules both instances share. We report on experiments that indicate that (i) the method works equally well or better than RIPPER on various language learning and other benchmark datasets; (ii) the method does not necessarily perform better than default memory-based learning, but (iii) when multi-valued features are combined with the rule- based features, some slight to significant improvements are observed.

This document is intended as a quick reference guide of the FAMBL algorithm and its current implementation, version 2.2. FAMBL is a memory-based learning algorithm that carefully generalizes over instances. It merges nearest-neighbour instances (exemplars) of the same class into generalized exemplars. In FAMBL, these are called families. FAMBL combines earlier approaches to generalized exemplars, NGE (Salzberg, 1991) and RISE (Domingos, 1995), with some new ideas and heuristics..

trefwoorden: neural networks, brain-like computing, language learning, cognitive models of language processing, evolutionary methods, speech and music perception

FAMBL, Family-Based Learner, version 2.3, is a freely available software package for research or educational purposes only. FAMBL comes WITHOUT ANY WARRANTY. Author nor distributor accept responsibility to anyone for the consequences of using it or for whether it serves any particular purpose or works at all. c○1997–2004 ILK / Tilburg University. 1 1 FAMBL: Family-Based Learning This document is intended as a quick reference guide of the FAMBL algorithm and its current implementation, version 2.3. FAMBL is a memory-based learning algorithm that carefully generalizes over instances. It merges nearest-neighbour instances (exemplars) of the same class into generalized exemplars. In FAMBL, these are called families. FAMBL combines earlier