Neural Networks

Hopfield Network

A recurrent network that settles into stored patterns — an early model of associative memory.

Every unit connects to every other, and the network relaxes toward the nearest stored state. Show it a corrupted pattern and it completes it, which made it an early demonstration of content-addressable memory.

Its energy-based framing anticipated a great deal of later work, and modern continuous variants have been shown to relate closely to the attention mechanism.

Also in Neural Networks

Perceptron Backpropagation Feed Forward Boltzmann Machine Self Organising Maps Deep Belief Network

Apply

Begin the first module

Become AI native, it is the real deal today, and if it is not for you, you have lost nothing but learnt a new skill.

Apply