It's only "Hebbian" in the sense of using synaptic weights to control learning and behavioural expression (no excitation patterns, etc.).
Generally, what this means is to create a set of experts with varying parameters; frequently, these are the initial synaptic weights, although other factors (such as the learning rate, momentum etc.) may be varied as well.
Learning algorithms differ from each other in the way in which the adjustment to a synaptic weight of a neuron is formulated. In principle, almost all learning algorithms for neural networks are iterative optimization algorithms.
With an appropriate algorithm (like "back-propagation") its possible to retouch the synaptic weight values to reduce the error. The corrections must be done for all the training input-output sets many times or cycles.
It resembles the brain in two respects: (1) Knowledge is acquired by the network through a learning process, and (2) Interneuron connection strengths known as synaptic weights are used to store the knowledge." (p. 2).
 See also: Neural network, Classification, Regression, Clustering, Generalization
  
|
RSS
