HTM: Hierarchical Temporal Memory

• Sparse binary vector employing a two-dimensional topographic semantic space
• Binary representation which enables semantic operations to be performed efficiently

There are three basic elements to a competitive learning rule:

• A set of neurons are all the same except for some randomly distributed synaptic weights, and which therefore respond differently to a given set of input patterns.
  • Like perceptrons in a Neural Network: all are the same, only the weights are different.
• A limit imposed on the "strength" of each neuron
• A mechanism that permits the neurons to compete for the right to respond to a given subset of inputs, s.t. only one output neuron (or only one neuron per group), is active at a time. The neuron that wins the competition is called a "winner-take-all" neuron.

Accordingly, the individual neurons of the network learn to specialize on ensembles of similar patterns and in doing so become "feature detectors" for different classes of input patterns.

One way of implementing this is a Neural Network where the hidden layers simply sets the output of the neuron with the largest value to 1, and all the rest of the neurons are set to 0.

Neocortex

part of the brain involved in higer-order brain functions such as sensory perception, cognition, generation of motor commands, spatial reasoning and language.