How does a Connectionist (PDP) model handle memory?

Connectionist model, also known as Parallel Distributed Processing (PDP) models, is a class of computational models often used to model aspects of human perception, cognition, and behaviour, the learning processes underlying such behaviour, and the storage and retrieval of information from memory.

The approach embodies a particular perspective in cognitive science, one that is based on the idea that our understanding of behaviour and of mental states should be informed and constrained by our knowledge of the neural processes that underpin cognition.

The Parallel Distributed Processing Model is a relatively new model regarding the processes of memory. The model postulates that information is not inputted into the memory system in a step by step manner like most models or theories hypothesize but instead, facts or images are distributed to all parts in the memory system at once. Older models hypothesized that information would consolidate first into sensory memory, then move to short-term memory, and then finally go to long-term memory.

This model was developed because of findings that a system of neural connections appeared to be distributed in a parallel array in addition to serial pathways. As such, different types of mental processing are considered to be distributed throughout a highly complex neuro network.

The PDP model has 3 basic principles:

  1. The representation of information is distributed (not local).
  2. Memory and knowledge for specific thing’s are not stored explicitly, but stored in the connections between units.
  3. Learning can occur with gradual changes in connection strength by experience.

These models assume that information processing takes place through interactions of large numbers of simple processing elements called units, each sending excitatory and inhibitory signals to other units.

Rumelhart, Hinton, and McClelland (1986) state that there are 8 major components of the PDP model framework:

  • A set of processing units.
  • A state of activation.
  • An output function for each unit.
  • A pattern of connectivity among units.
  • A propagation rule for propagating patterns of activities through the network of connectivities.
  • An activation rule for combining the inputs impinging on a unit with the current state of that unit to produce a new level of activation for the unit.
  • A learning rule whereby patterns of connectivity are modified by experience.
  • An environment within which the system must operate.
Compare items
  • Total (0)