From Wikipedia, the free encyclopedia

A Hopfield net is a form of recurrent artificial neural network invented by John Hopfield. Hopfield nets serve as content-addressable memory systems with binary threshold units. They are guaranteed to converge to a local minimum, but convergence to one of the stored patterns is not guaranteed.

Contents 1 Structure 2 Running 3 Training 4 References 5 See also 6 External links

The 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 units' input exceeds their threshold. Hopfield nets can either have units that take on values of 1 or -1, or units that take on values of 1 or 0. So, the two possible definitions for unit i's activation, a_i, are:

(1)

(2)

Where:

• w_ij is the strength of the connection weight from unit j to unit i (the weight of the connection).
• s_j is the state of unit j.
• θ_i is the threshold of unit i.

The connections in a Hopfield net typically have the following restrictions:

• (no unit has a connection with itself)
• (connections are symmetric)

The requirement that weights be symmetric is typically used, as it will guarantee that the energy function decreases monotonically while following the activation rules, and the network may exhibit some periodic or chaotic behaviour if non-symmetric weights are used. However, Hopfield found that this chaotic behaviour was confined to relatively small parts of the phase space, and did not impair the network's abilities to act as a content-addressable associative memory system.

Hopfield nets have a scalar value associated with each state of the network referred to as the "energy", E, of the network, where:

This value is called the "energy" because the definition ensures that if units are randomly chosen to update their activations the network will converge to states which are local minima in the energy function (which is considered to be a Lyapunov function). Thus, if a state is a local minimum in the energy function it is a stable state for the network. Note that this energy function belongs to a general class of models in physics, under the name of Ising models.

At each step, pick a node at random. The node's behavior is then deterministic: it moves to a state to minimize the energy of itself and its neighbors. (In contrast, the Boltzmann machine has a stochastic update rule.)

Training a Hopfield net involves lowering the energy of states that the net should "remember". This allows the net to serve as a content addressable memory system, that is to say, the network will converge to a "remembered" state if it is given only part of the state. For example, if we train a Hopfield net with five units so that the state (1, 0, 1, 0, 1) is an energy minimum, and we give the network the state (1, 0, 0, 0, 1) it will converge to (1, 0, 1, 0, 1). Thus, the network is properly trained when the energy of states which the network should remember are local minima.

J. J. Hopfield, "Neural networks and physical systems with emergent collective computational abilities", Proceedings of the National Academy of Sciences of the USA, vol. 79 no. 8 pp. 2554-2558, April 1982.

• Ising model
• Boltzmann machine — like a Hopfield net but uses annealed Gibbs sampling instead of gradient descent

• Chapter 13 The Hopfield model of Neural Networks - A Systematic Introduction by Raul Rojas (ISBN 978-3540605058)
• A good introduction to associative memory and Hopfield networks
• The Hopfield networks page at PRIS, Singapore
• Hopfield Neural Network Applet
• The Travelling Salesman Problem - Hopfield Neural Network JAVA Applet
• Neural Lab Graphical Interface - Hopfield Neural Network graphical interface (Python & gtk)