Content deleted Content added
more citaton |
mNo edit summary |
||
Line 6:
=== Key properties of connectionist models<ref name=":7">{{Cite journal|url = |title = Connectionist models of cognition|last = Thomas|first = Michael|date = 2014|journal = Cambridge Handbook on Computational Cognitive Modeling|doi = |pmid = |access-date = }}</ref> ===
▲==== 1. Set of processing units (''u)'' to represent individual concepts, such as letters or words, or abstract elements over which meaningful patterns can be defined ====
▲==== 2. State of activation (''a)'' at given time (''t),'' where the state of a set of units is usually represented by a vector of real numbers ''a(t)'' ====
▲==== 3. Pattern of connectivity, where the strength between any two units determines the extent to which the activation state of one unit can affect the activation state of another unit at subsequent time point ====
The strength of the connections between unit i and unit j can be represented by a matrix ''W'' of weight values <math display="inline">w_{ij}</math>''.''
Line 18:
<math display="inline">net_{i} = W * a(t) = \sum_{j}w_{ij}a_{j}</math>
<math>a_{i}(t+1)= F(net_{i}(t))</math>
<math>\Delta w_{ij} = \eta a_{i}a_{j}</math>
where η is the constant of proportionality known as the learning rate
"This is assumed to consist of a set of externally provided events, or a function for generating such events. An event may be
a single pattern, such as a visual input; an ensemble of related patterns, such as the
| |||