Learning Structurally Analogous Tasks

Authors:
Paul W. Munro
Affiliations:
School of Information Sciences, University of Pittsburgh, Pittsburgh, USA 15260
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Year:
2008

Citing 2
Cited 0

Analogy-making as perception: a computer model

Analogy-making as perception: a computer model
Multitask Learning

Machine Learning - Special issue on inductive transfer

Quantified Score

Hi-index	0.00

Visualization

Abstract

A method for training overlapping feedforward networks on analogous tasks is extended and analyzed. The learning dynamics of simultaneous (interlaced) training of similar tasks interact at the shared connections of the networks. The influence of one task on the other can be studied by examining the output of one network in response to a stimulus to the other network. Using backpropagation to train networks with shared hidden layers, a "crosstraining" mechanism for specifying corresponding components between structurally similar environments is introduced. Analysis of the resulting mappings reveals the potential for analogical inference.