Editing Parallel processing (psychology) (section)

== Aspects of a parallel distributed processing model ==
There are eight major aspects of a parallel distributed processing model:<ref name=":3"/>

=== Processing units ===
These units may include abstract elements such as features, shapes and words, and are generally categorised into three types: input, output and hidden units.

* Input units receive signals from either sensory [[Stimulus (physiology)|stimuli]] or other parts of the processing system.
* The output units send signals out of the system.
* The hidden units function entirely inside the system.

=== Activation state ===
This is a representation of the state of the system. The pattern of activation is represented using a [[Vector notation|vector]] of N real numbers, over the set of processing units. It is this pattern that captures what the system is representing at any time.

=== Output functions ===
An output function maps the current state of activation to an output signal. The units interact with their neighbouring units by transmitting signals. The strengths of these signals are determined by their degree of activation. This in turn affects the degree to which they affect their neighbours.

=== Connectivity patterns ===
The pattern of connectivity determines how the system will react to an arbitrary input. The total pattern of connectivity is represented by specifying the weights for every connection. A positive weight represents an excitatory input and a negative weight represents an inhibitory input.

=== Propagation rule ===
A ''net input'' is produced for each type of input using rules that take the output vector and combine it with the connectivity [[Matrix (mathematics)|matrices]]. In the case of a more complex pattern connectivity, the rules are more complex too.

=== Activation rule ===
A new state of activation is produced for every unit by joining the ''net inputs'' of impinging units combined and the current state of activation for that unit.

=== Learning rule ===
The patterns of connectivity are modified using experience. The modifications can be of three types: First, the development of new connections. Second,  the loss of existing connection. Last, the modification of strengths of connections that already exist.  The first two can be considered as special cases of the last one. When the strength of a connection is changed from zero to a positive or negative one, it is like forming a new connection. When the strength of a connection is changed to zero, it is like losing an existing connection.

=== Environmental representation ===
In PDP models, the environment is represented as a ''time-varying [[Stochastic simulation|stochastic function]]'' over the space of input patterns.<ref>{{Cite journal|last1=Snodgrass|first1=Joan Gay|last2=Townsend|first2=James T.|last3=Ashby|first3=F. Gregory|date=1985|title=Stochastic Modeling of Elementary Psychological Processes|url=http://dx.doi.org/10.2307/1422636|journal=The American Journal of Psychology|volume=98|issue=3|pages=480|doi=10.2307/1422636|jstor=1422636 |issn=0002-9556}}</ref> This means that at any given point, there is a possibility that any of the possible set of input patterns is impinging on the input units.  <ref name=":02" />

[[File:Parallel_Processing_Model.png|thumb|An example of a parallel distributed processing (PDP) model|466x466px]]

An example of the PDP model is illustrated in Rumelhart's book 'Parallel Distributed Processing' of individuals who live in the same neighborhood and are part of different gangs. Other information is also included, such as their names, age group, marital status, and occupations within their respective gangs. Rumelhart considered each category as a 'unit' and an individual has connections with each unit. For instance, if more information is sought on an individual named Ralph, that name unit is activated, revealing connections to the other properties of Ralph such as his marital status or age group.<ref name=":3" />