Recall system using spiking neuron networks

摘要

Described is a recall system that uses spiking neuron networks to identify an unknown external stimulus. The system operates by receiving a first input signal (having spatial-temporal data) that originates from a known external stimulus. The spatial-temporal data is converted into a first spike train. A first set of polychronous groups (PCGs) are generated as a result of the first spike train. Thereafter, a second input signal originating from an unknown external stimulus is received. The spatial-temporal data of the second input signal is converted into a second spike train. A second set of PCGs are then generated as a result of the second spike train. Finally, the second set of PCGs is recognized as being sufficiently similar to the first set of PCGs to identify the unknown external stimulus as the known external stimulus.

主权项

1. A recall system using spiking neuron networks to identify an unknown external stimulus, the recall system comprising one or more processors and a memory, the memory storing computer code which, when executed by the one or more processors, cause the one or more processors to perform operations of:
receiving a first input signal originating from a known external stimulus, the first input signal having first spatial-temporal data; converting the spatial-temporal data into a first spike train; receiving the first spike train in a spiking neuron network, the spiking neuron network generating a first set of polychronous groups (PCGs) as a result of the first spike train; receiving a second input signal originating from an unknown external stimulus, the second input signal having second spatial-temporal data; converting the second spatial-temporal data into a second spike train; receiving the second spike train in the spiking neuron network, the spiking neuron network generating a second set of PCGs as a result of the second spike train; recognizing the second set of PCGs as being sufficiently similar to the first set of PCGs to identify the unknown external stimulus as the known external stimulus; wherein in converting the spatial-temporal data into a first spike train, the first input signal is converted into frequency-specific spike patterns that are then combined based on a degree of synchrony to generate the first spike train; and wherein in receiving the first spike train in the spiking neuron network, the spiking neuron network is a hierarchical network, with a first layer having neurons that are tonotopically organized, such that spike trains from individual frequency bands are routed to neurons in the first layer according to the frequency bands to generate an initial group of PCGs, with the initial group of PCGs becoming an input to an upper layer in the hierarchical network to generate the first set of PCGs.