18 Facts About Hopfield network

Hopfield network is a form of recurrent artificial neural network and a type of spin glass system popularised by John Hopfield in 1982 as described earlier by Little in 1974 based on Ernst Ising's work with Wilhelm Lenz on the Ising model.

Units in Hopfield nets are binary threshold units, i e the units only take on two different values for their states, and the value is determined by whether or not the unit's input exceeds its threshold.

Discrete Hopfield nets describe relationships between binary neurons.

Hopfield network modeled neural nets for continuous values, in which the electric output of each neuron is not binary but some value between 0 and 1.

Hopfield network found that this type of network was able to store and reproduce memorized states.

Notice that every pair of units i and j in a Hopfield network has a connection that is described by the connectivity weight.

Furthermore, under repeated updating the Hopfield network will eventually converge to a state which is a local minimum in the energy function.

Convergence is generally assured, as Hopfield network proved that the attractors of this nonlinear dynamical system are stable, not periodic or chaotic as in some other systems.

Training a Hopfield network net involves lowering the energy of states that the net should "remember".

For example, if we train a Hopfield net with five units so that the state is an energy minimum, and we give the network the state it will converge to.

Storkey showed that a Hopfield network trained using this rule has a greater capacity than a corresponding network trained using the Hebbian rule.

The weight matrix of an attractor neural Hopfield network is said to follow the Storkey learning rule if it obeys:.

Network capacity of the Hopfield network model is determined by neuron amounts and connections within a given network.

Therefore, the Hopfield network model is shown to confuse one stored item with that of another upon retrieval.

Ulterior models inspired by the Hopfield network were later devised to raise the storage limit and reduce the retrieval error rate, with some being capable of one-shot learning.

The entire Hopfield network contributes to the change in the activation of any single node.

The Hopfield network still requires a sufficient number of hidden neurons.

Simple example of the modern Hopfield network can be written in terms of binary variables that represent the active and inactive state of the model neuron.