Recent papers on knowledge and learning

[Thomas R. Shultz]

Recent papers on knowledge and learning that may be of interest to readers 
of this list

Shultz, T. R., & Rivest, F. (2001, in press).  Knowledge-based 
cascade-correlation: Using knowledge to speed learning. Connection Science.

Research with neural networks typically ignores the role of knowledge in 
learning by initializing the network with random connection weights. We 
examine a new extension of a well-known generative algorithm, 
cascade-correlation. Ordinary cascade-correlation constructs its own 
network topology by recruiting new hidden units as needed to reduce network 
error. The extended algorithm, knowledge-based cascade-correlation (KBCC), 
recruits previously learned sub-networks as well as single hidden units. 
This paper describes KBCC and assesses its performance on a series of 
small, but clear problems involving discrimination between two classes. The 
target class is distributed as a simple geometric figure. Relevant source 
knowledge consists of various linear transformations of the target 
distribution. KBCC is observed to find, adapt, and use its relevant 
knowledge to significantly speed learning.

=============

Shultz, T. R., & Rivest, F. (2000). Using knowledge to speed learning: A 
comparison of knowledge-based cascade-correlation and multi-task learning. 
Proceedings of the Seventeenth International Conference on Machine Learning 
(pp. 871-878). San Francisco: Morgan Kaufmann.

Cognitive modeling with neural networks unrealistically ignores the role of 
knowledge in learning by starting from random weights. It is likely that 
effective use of knowledge by neural networks could significantly speed 
learning. A new algorithm, knowledge-based cascade-correlation (KBCC), 
finds and adapts its relevant knowledge in new learning. Comparison to 
multi-task learning (MTL) reveals that KBCC uses its knowledge more 
effectively to learn faster.

=============

Preprints and reprints can be found at 
http://www.psych.mcgill.ca/perpg/fac/shultz/default.htm

Cheers,
Tom

--------------------------------------------------------
Thomas R. Shultz, Professor, Department of Psychology,
McGill University, 1205 Penfield Ave., Montreal, Quebec,
Canada H3A 1B1.
E-mail: shultz at psych.mcgill.ca
Updated 7 April 2001: http://www.psych.mcgill.ca/perpg/fac/shultz/default.htm
Phone: 514 398-6139
Fax: 514 398-4896
--------------------------------------------------------