Physical Symbol Systems (Newell, Pylyshyn, Fodor; summarized by Harnad)
A set of arbitrary physical tokens (scratches on
paper, holes on a tape, events in a digital computer, etc.)
that are
manipulated on the basis of explicit rules
that are
likewise physical tokens and strings of tokens.
The rule-governed symbol-token manipulation is based
purely on the shape of the symbol tokens (not
their ``meaning''), i.e., it is purely syntactic, and consists of
rulefully combining and recombining symbol
tokens. There are
primitive atomic symbol tokens and
composite symbol-token strings.
The entire cognitive system and all its parts--the atomic tokens,
the composite tokens, the syntactic manipulations
(both actual and possible) and the rules--are all
semantically interpretable: The syntax can be
systematically assigned a meaning
(e.g., as standing for objects, as describing states of
affairs).
Processes happen sequentially.
There is a central controller which
coordinates the activities of the modules of the cognitive
system and
selects among candidate processes at each point in time.
The cognitive system interacts with the world through interfaces to
perception and action, which operate very differently from
the internal (cognitive) system.
Knowledge is usually programmed into the
cognitive system by someone who has a theory of how
knowledge is organized.
Learning is also possible, but it is not central to most models.
Time is often mapped onto space; that is, the cognitive system has
simultaneous access to all of a pattern of some length (word,
sentence, etc.).
Inputs may also be presented sequentially, but the problem of temporal
short-term memory is side-stepped because the inputs are
preprocessed.
In connectionist models, at least, control is distributed. There is just the illusion of
someone being in charge because the behavior seems
purposeful, and it seems to be possible to write a
centralized program to make it happen.
In connectionist models, the basic processes involve very simple
interactions among primitive elements arranged in a network. Usally the interaction amounts to the spread of activation.
Many of the processes happen in parallel.
The cognitive system may interact with the world through perception and action
components which are similar to the internal (cognitive)
parts of the creature. In some models, the environment and
the creature itself constitute one large dynamical system.
Except in localized connectionist models, knowledge is distributed, usually in the form of
patterns of connectivity among the
primitive elements. The
knowledge in such systems is implicit; it often cannot be simply read off.
Knowledge gets into the cognitive system (except in most localized models)
through learning as the system
discovers the statistical properties of the world around it
or through evolution as
generations of creatures are forced to survive in the world.
The problem of temporal short-term memory
is often addressed,
though the continuous interaction of components of the
cognitive system with each other and the world may not be.
In the most conservative approaches, input patterns are fed to the
cognitive system in the form of a sequence of discrete
events. In the
most radical approaches, the cognitive system exists in the
world in continuous time.
Differences Between Symbolic and Sub-symbolic Models
Control
Symbolic, some statistical: centralized
Connectionist: distributed
Representational units
Symbolic, some statistical: atomic symbols
Localist connectionist: activation of processing units
Distributed connectionist, some statistical: patterns of activation
over sets of processing units, i.e., vectors of
numbers
More complex representations
Symbolic: symbol structures - symbols concatenated
together
Connectionist: patterns of activation
over sets of processing units (concatenation not
possible); the same kind of things as what correspond
to symbols; graded
Statistical: usually absent
Long-term memory
Symbolic: symbol structures in knowledge base
Connectionist/statistical: weights on connections joining units
Short-term (working) memory
Symbolic: temporary symbol structures (local
variable bindings)
Connectionist: pattern of activation over units
Statistical: may be absent
Embedding and recursion
Symbolic: easy; symbol structures can be as deep
as you like
Localist connectionist: easy if new units are created,
but hard otherwise because of the variable binding
problem
Distributed connectionist: hard because of the
fixed size, solutions must "squeeze" representations
of varying complexity into the same units
Statistical: usually absent
Variable binding
Symbolic: easy; variables and their bindings are just
symbols associated in a list
Localist connectionist: hard, if units represent roles
and fillers, there is the problem of crosstalk (but
there is a sort of a solution)
Distributed connectionist: hard (but there are some
possible solutions)
Statistical: usually absent
Basic means of access
Symbolic: pattern matching
Connectionist: parallel spread of activation and
settling
Statistical: usually simple table lookup
Basic means of instantiation
Symbolic: creation of new symbol structures
Localist connectionist: creation of new units
and weighted connections
Distributed connectionist: activation of set of
existing units (generally no facility for creating
new units on the fly) and adjustment of weights
on connections to/from these units
Statistical: usually absent
Where representations come from
Symbolic: wired in
Localist connectionist: wired in
Distributed connectionist / statistical: emerge
during processing/learning;