Stanford Adaptive Networks Colloquium

[Mark Gluck]

         Stanford University Interdisciplinary Colloquium Series:
                 ADAPTIVE NETWORKS AND THEIR APPLICATIONS
   

**************************************************************************
May 20 (Friday, 2:15pm):
     STEVEN GALLANT                      "Sequential Associative Memories"
      College of Computer Science
      Northeastern Univ.
      Boston, MA 02115

**************************************************************************

                            ABSTRACT

Humans are very good at manipulating sequential information, but
sequences present special problems for connectionist models.
As an  approach to sequential problems we have examined totally
connected subnetworks of cells called Sequential Associative
Memories (SAM's).  The coefficients for SAM cells are unmodifi-
able and are generated at random.
A subnetwork of SAM cells performs two tasks:
1.  Their activations determine a state for the network that
permits previous inputs and outputs to be recalled, and
2.  They increase the dimensionality of input and output
representations to make it possible for other (modifiable) cells
in the network to learn difficult tasks.
The second function is similar to the Distributed Method, a way
of generating intermediate cells for non-sequential problems.
Results from several experiments are presented.  The first is a
robotic control task that required a network to produce one of
several sequences of outputs when input cells were set to a
corresponding `plan number'.
The second experiment was to learn a sequential version of the
parity function that would generalize to arbitrarily long input
strings.
Finally we attempted to teach a network how to add arbitrarily
long pairs of binary numbers.  Here we were successful if the
network contained a cell dedicated to the notion of `carry';
otherwise the network performed at less than 100% for unseen se-
quences longer than those used during training.
Each of these tasks required a representation of state, and hence
a network with feedback.  All were learned using subnetworks of
SAM cells.
                         *      *      *
Location: 
 Room 380-380C which can be reached through the lower level courtyard between 
 the Psychology and Mathematical Sciences buildings.

Information:
 To be placed on an electronic mail distribution list for 
 information about these and other adaptive network events in the Stanford
 area, send email to netlist at psych.stanford.edu. For additional information,
 contact Mark Gluck, Bldg. 420-316; (415) 725-2434 or email to
 gluck at psych.stanford.edu