Hebbian Learning A rule that specifies that the strength of a synapse between two neurons should be proportional to the product of the activations of the two neurons. cd ...
Hebbian learning rule- according to this rule, if a neuron receives input from another neuron and if both are highly active (mathematically have the same sign), the weight between the neurons should be strengthened.
hebbian learning
w(t+1) = w(t) + m y(t) x(t)
This moves w toward inifinity in the direction of the eigevector with largest eigenvalue of the correlation matrix
A more stable version is Oja's rule
w(t+1) = w(t) + m (x(t) - y(t) w(t) ) y(t) ...
Hebbian learning is performed using conditional principal components analysis (CPCA) algorithm with correction factor for sparse expected activity levels.
Hebbian learning is a standard algorithm that does seem to operate in biological neural networks, but it has a problem: it's not very good for training deep networks (those networks which have multiple "hidden layers," i.e.
Neural networks are applied to the problem of learning, using such techniques as Hebbian learning[115] and the relatively new field of Hierarchical Temporal Memory which simulates the architecture of the neocortex.
Virtually all learning rules for models of this type can be considered as a variant of the Hebbian learning rule suggested by Hebb in his classic book Organization of Behaviour (1949) (Hebb, 1949).
It's an action-selection system which uses (approximately) Hebbian learning, but I don't think anyone has used a network quite like this anywhere else.
This network has the property that its dynamics are guaranteed to converge. If the connections are trained using Hebbian learning then the Hopfield network can perform robust content-addressable memory, robust to connection alteration.
 See also: Neural network, Backpropagation, Classification, Percept, Simulation
  
|
RSS
