초록 ▼

A neuron network which achieves learning by means of a modified Boltzmann algorithm. The network may comprise interconnected input, hidden and output layers of neurons, the neurons being “on-off”or threshold electronic devices which are symmetrically connected by means of adjustable-weight synapse p

A neuron network which achieves learning by means of a modified Boltzmann algorithm. The network may comprise interconnected input, hidden and output layers of neurons, the neurons being “on-off”or threshold electronic devices which are symmetrically connected by means of adjustable-weight synapse pairs. The synapses comprise the source-drain circuits of a plurality of paralleled FETs which differ in resistance or conductance in a binary sequence. The synapses are controlled by the output of an Up-Down counter, the reading of which is controlled by the results of a correlation of the states of the two neurons connected by the synapse pairs following the application of a set of plus and minus training signals to selected neurons of said network. A noise generator comprising a thermal noise source is provided for each neuron for the purpose of simulated annealing of the network.

대표청구항 ▼

A neuron network comprising interconnected input, hidden and output layers of neurons, said neurons comprising “on-off”or threshold electronic devices, all of said neurons which are connected being symmetrically connected by means of automatically-adjustable synapse pairs, each of said synapses comp

A neuron network comprising interconnected input, hidden and output layers of neurons, said neurons comprising “on-off”or threshold electronic devices, all of said neurons which are connected being symmetrically connected by means of automatically-adjustable synapse pairs, each of said synapses comprises a plurality of drain-source circuits of field effect transistors, said source-drain circuits having resistances or conductances which differ from each other by ratios of 2 to 1, whereby different combinations of said source-drain circuits can be switched in parallel to provide any resistance or conductance, in a binary sequence, for each of said synapses, said synapses being controlled by the output of an Up-Down counter, and means to control the reading of said counter depending on the results of a correlation of the states of each connected pair of said neurons following the application of sets of training signals to said neurons network.