About the Book
This is the fourth and final volume of papers from a series of workshops called "Computational Learning Theory and `Natural' Learning Systems." The purpose of the workshops was to explore the emerging intersection of theoretical learning research and natural learning systems. The workshops drew researchers from three historically distinct styles of learning research: computational learning theory, neural networks, and machine learning (a subfield of AI).
Volume I of the series introduces the general focus of the workshops. Volume II looks at specific areas of interaction between theory and experiment. Volumes III and IV focus on key areas of learning systems that have developed recently. Volume III looks at the problem of "Selecting Good Models." The present volume, Volume IV, looks at ways of "Making Learning Systems Practical." The editors divide the twenty-one contributions into four sections. The first three cover critical problem areas: 1) scaling up from small problems to realistic ones with large input dimensions, 2) increasing efficiency and robustness of learning methods, and 3) developing strategies to obtain good generalization from limited or small data samples. The fourth section discusses examples of real-world learning systems.
ContributorsKlaus Abraham-Fuchs, Yasuhiro Akiba, Hussein Almuallim, Arunava Banerjee, Sanjay Bhansali, Alvis Brazma, Gustavo Deco, David Garvin, Zoubin Ghahramani, Mostefa Golea, Russell Greiner, Mehdi T. Harandi, John G. Harris, Haym Hirsh, Michael I. Jordan, Shigeo Kaneda, Marjorie Klenin, Pat Langley, Yong Liu, Patrick M. Murphy, Ralph Neuneier, E. M. Oblow, Dragan Obradovic, Michael J. Pazzani, Barak A. Pearlmutter, Nageswara S. V. Rao, Peter Rayner, Stephanie Sage, Martin F. Schlang, Bernd Schürmann, Dale Schuurmans, Leon Shklar, V. Sundareswaran, Geoffrey Towell, Johann Uebler, Lucia M. Vaina, Takefumi Yamazaki, Anthony M. Zador.
Table of Contents:
Part 1 Scaling up: Initializing neural networks using decision trees, Arunava Banerjee; Recurrent neural networks with continuous topology adaptation, Kalman filter based training, Dragan Obradovic; Imposing bounds on the number of categories for incremental concept formation, Leon Shklar, Haym Hirsh; Scaling to domains with irrelevant features, Patrick Langley, Stephanie Sage. Part 2 Robust and efficient learning: Mixture models for learning from incomplete data, Zoubin Ghahramans, Russell Greiner; Supervised learning using labelled and unlabelled examples, Geoffrey Towell; Abnormal data points in the data set - an algorithm for robust neural net regression, Yong Liu; Dynamic modelling of chaotic time series by neural networks, Gustavo Deco, Bernd Schurmann; Fast distribution-specific learning, Dale Schurmans, Russell Greiner. Part 3 Improving and analyzing generalization: Exploring the decision forest - an empirical investigation of Occam's razor in decision tree induction, Patrick M. Murphy, Michael J. Pazzani; N-learners problem - system of PAC learners, Nageswara S.V. Rao, E.M. Oblow; The discriminative power of a dynamic model neuron, Anthony M. Zador, Barak A. Pearlmutter; On learning the neural network architecture - a case study, Mostefa Golea; Probabilistic self-structuring and learning, David Garvin, Peter Rayner; A practical approach to evaluating generalization performance, Marjorie Klenin. Part 5 Real world applications: What makes derivational analogy work - an experience report using APU, Sanjay Bhansali, Mehdi T. Harandi; Learning verb translation rules from ambiguous examples and a large semantic hierarchy, Hussein Almuallim et al; Efficient learning of regular expressions from approximate examples, Alvis Brazma; A comparison of RBF and MLP networks for classification of biomagnetic fields, Martin F. Schlang et al; Fast perceptual learning of motion in humans and neural networks, Lucia M. Vaina et al.
About the Author :
Stephen José Hanson is Professor of Psychology (Newark Campus) and Member of the Cognitive Science Center (New Brunswick Campus) at Rutgers University.
