Neural weak classifiers for language learning
Towsey, Michael W., D'Este, Claire, & Diederich, Joachim (2000) Neural weak classifiers for language learning. In Workshop on Evolutionary Computation and Cognitive Science (ECCS 2000), Fifth Australasian Cognitive Science Conference, 28th & 29th January, 2000, La Trobe University, Melbourne, Australia.
We describe a neural implementation of the combination of weak classifiers (CWC) algorithm [Ji and Ma, 1997] which is able to learn the one-step-look-ahead task where the input is natural language sentences. The one-step-look-ahead task is more usually implemented with Simple Recurrent Networks [Elman, 1990] whose architecture typically consists of comparitively few neurons but learning requires many thousands of presentations of the training data. Our implementation includes a four layered architecture which consists of (1) an input layer having one neuron for each category, (2) an internally recurrent layer which captures the dynamics of the temporal input, (3) a large hidden layer of weakly classifying perceptrons and (4) a winner-take-all output layer having the same number of neurons as the input.
Impact and interest:
Citation counts are sourced monthly from and citation databases.
Citations counts from theindexing service can be viewed at the linked Google Scholar™ search.
|Item Type:||Conference Item (Poster)|
|Subjects:||Australian and New Zealand Standard Research Classification > INFORMATION AND COMPUTING SCIENCES (080000) > ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING (080100) > Neural Evolutionary and Fuzzy Computation (080108)
Australian and New Zealand Standard Research Classification > INFORMATION AND COMPUTING SCIENCES (080000) > ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING (080100) > Natural Language Processing (080107)
|Divisions:||Past > QUT Faculties & Divisions > Faculty of Science and Technology|
|Copyright Owner:||Copyright 2000 The authors|
|Deposited On:||16 May 2007|
|Last Modified:||10 Aug 2011 13:51|
Repository Staff Only: item control page