pratt@zztop.rutgers.edu (Lorien Y. Pratt) (09/21/88)
Fall, 1988
Neural Networks Colloquium Series
at Rutgers
Some comments and variations on back propagation
------------------------------------------------
Stephen Jose Hanson
Bellcore
Cognitive Science Lab, Princeton University
Room 705 Hill center, Busch Campus
Friday September 30, 1988 at 11:10 am
Refreshments served before the talk
Abstract
Backpropagation is presently one of the most widely used learning
techniques in connectionist modeling. Its popularity, however, is
beset with many criticisms and concerns about its use and potential
misuse. There are 4 sorts of criticisms that one hears:
(1) it is a well known statistical technique
(least squares)
(2) it is ignorant <about the world in which it is
learning--thus design of i/o is critical>
(3) it is slow--(local minima, its NP complete)
(4) it is ad hoc--hidden units as "fairy dust"
I believe these four types of criticisms are based on fundamental
misunderstandings about the use and relation of learning methods to the
world, the relation of ontogeny to phylogeny, the relation of simple
neural models to neuroscience and the nature of "weak" learning
theories. I will discuss these issues in the context of some
variations on backpropagation.
P.S. Don't forget the talk this Friday (the 23rd) by Dave Touretzky
--
-------------------------------------------------------------------
Lorien Y. Pratt Computer Science Department
pratt@paul.rutgers.edu Rutgers University
Busch Campus
(201) 932-4634 Piscataway, NJ 08854