"Lorien Y. Pratt" <pratt@paul.rutgers.edu> (04/18/91)
Archive-name: ai/neural-nets/pratt-phoneme/1991-04-05 Archive: cheops.cis.ohio-state.edu:/pub/neuroprose/pratt*91* [128.146.8.62] Original-posting-by: "Lorien Y. Pratt" <pratt@paul.rutgers.edu> Reposted-by: emv@msen.com (Edward Vielmetti, MSEN) The following two papers are now available via FTP from the neuroprose archives. The first is for AAAI91, so written towards an AI/Machine learning audience. The second is for IJCNN91, so more neural network-oriented. There is some overlap between them: the AAAI paper reports briefly on the study describved in more detail in the IJCNN paper. Instructions for retrieval are at the end of this message. --Lori #@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@#@ Direct Transfer of Learned Information Among Neural Networks To appear: Proceedings of AAAI-91 Lorien Y. Pratt and Jack Mostow and Candace A. Kamm Abstract A touted advantage of symbolic representations is the ease of transferring learned information from one intelligent agent to another. This paper investigates an analogous problem: how to use information from one neural network to help a second network learn a related task. Rather than translate such information into symbolic form (in which it may not be readily expressible), we investigate the direct transfer of information encoded as weights. Here, we focus on how transfer can be used to address the important problem of improving neural network learning speed. First we present an exploratory study of the somewhat surprising effects of pre-setting network weights on subsequent learning. Guided by hypotheses from this study, we sped up back-propagation learning for two speech recognition tasks. By transferring weights from smaller networks trained on subtasks, we achieved speedups of up to an order of magnitude compared with training starting with random weights, even taking into account the time to train the smaller networks. We include results on how transfer scales to a large phoneme recognition problem. @%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@%@ Improving a Phoneme Classification Neural Network through Problem Decomposition To appear: Proceedings of IJCNN-91 L. Y. Pratt and C. A. Kamm Abstract In the study of neural networks, it is important to determine whether techniques that have been validated on smaller experimental tasks can be scaled to larger real-world problems. In this paper we discuss how a methodology called {\em problem decomposition} can be applied to AP-net, a neural network for mapping acoustic spectra to phoneme classes. The network's task is to recognize phonemes from a large corpus of multiple-speaker, continuously-spoken sentences. We review previous AP-net systems and present results from a decomposition study in which smaller networks trained to recognize subsets of phonemes are combined into a larger network for the full signal-to-phoneme mapping task. We show that, by using this problem decomposition methodology, comparable performance can be obtained in significantly fewer arithmetic operations. %^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^%^% To retrieve: unix> ftp cheops.cis.ohio-state.edu (or 128.146.8.62) Name: anonymous Password: neuron ftp> cd pub/neuroprose ftp> binary ftp> get pratt.aaai91.ps.Z ftp> get pratt.ijcnn91.ps.Z ftp> quit unix> uncompress pratt.aaai91.ps.Z pratt.ijcnn91.ps.Z unix> lpr pratt.aaai91.ps pratt.ijcnn91.ps -- comp.archives file verification cheops.cis.ohio-state.edu -rw-r--r-- 1 3169 274 95707 Apr 3 16:11 /pub/neuroprose/pratt.aaai91.ps.Z -rw-r--r-- 1 3169 274 73013 Apr 3 16:12 /pub/neuroprose/pratt.ijcnn91.ps.Z found pratt-phoneme ok cheops.cis.ohio-state.edu:/pub/neuroprose/pratt*91*