Page 82 - Foundations of Cognitive Psychology : Core Readings

The Appeal of Parallel Distributed Processing 81

interconnections between units, a question arises.Is there any reason to assign
one unit to each pattern that we wish to learn? Another possibility is that the
knowledge about any individual pattern is not stored in the connections of a
special unit reserved for that pattern, but is distributed over the connections
among a large number of processing units.On this view, the Jets and Sharks
model represents a special case in which separate units are reserved for each
instance.
Models in which connection information is explicitly thought of as distrib-
uted have been proposed by a number of investigators.The units in these col-
lections may themselves correspond to conceptual primitives, or they may have
no particular meaning as individuals.In either case, the focus shifts to patterns
of activation over these units and to mechanisms whose explicit purpose is to
learn the right connection strengths to allow the right patterns of activation to
become activated under the right circumstances.
In the rest of this section, we will give a simple example of a PDP model in
which the knowledge is distributed.We will first explain how the model would
work, given pre-existing connections, and we will then describe how it could
come to acquire the right connection strengths through a very simple learning
mechanism.A number of models which have taken this distributed approach
have been discussed in Hinton and J.A.Anderson’s (1981) Parallel Models of
Associative Memory .We will consider a simple version of a common type of
distributed model, a pattern associator.
Pattern associators are models in which a pattern of activation over one set of
units can cause a pattern of activation over another set of units without any
intervening units to stand for either pattern as a whole.Pattern associators
would, for example, be capable of associating a pattern of activation on one set
of units corresponding to the appearance of an object with a pattern on another
set corresponding to the aroma of the object, so that, when an object is pre-
sented visually, causing its visual pattern to become active, the model produces
the pattern corresponding to its aroma.
How a Pattern Associator Works For purposes of illustration, we present a very
simple pattern associator in figure 4.12. In this model, there are four units in
each of two pools.The first pool, the A units, will be the pool in which patterns
corresponding to the sight of various objects might be represented.The second
pool, the B units, will be the pool in which the pattern corresponding to the
aroma will be represented.We can pretend that alternative patterns of activa-
tion on the A units are produced upon viewing a rose or a grilled steak, and
alternative patterns on the B units are produced upon sniffing the same objects.
Figure 4.13 shows two pairs of patterns, as well as sets of interconnections
necessary to allow the A member of each pair to reproduce the B member.
The details of the behavior of the individual units vary among different ver-
sions of pattern associators.For present purposes, we’ll assume that the units
can take on positive or negative activation values, with 0 representing a kind of
neutral intermediate value.The strengths of the interconnections between the
units can be positive or negative real numbers.
The effect of an A unit on a B unit is determined by multiplying the activa-
tion of the A unit times the strength of its synaptic connection with the B unit.