Methods and apparatus for spiking neural computation

摘要

Certain aspects of the present disclosure provide methods and apparatus for spiking neural computation of general linear systems. One example aspect is a neuron model that codes information in the relative timing between spikes. However, synaptic weights are unnecessary. In other words, a connection may either exist (significant synapse) or not (insignificant or non-existent synapse). Certain aspects of the present disclosure use binary-valued inputs and outputs and do not require post-synaptic filtering. However, certain aspects may involve modeling of connection delays (e.g., dendritic delays). A single neuron model may be used to compute any general linear transformation x=AX+BU to any arbitrary precision. This neuron model may also be capable of learning, such as learning input delays (e.g., corresponding to scaling values) to achieve a target output delay (or output value). Learning may also be used to determine a logical relation of causal inputs.

主权项

1. A method of learning using a spiking neural network,
comprising: (a) delaying an input spike in an artificial neuron according to a current delay associated with an input to the artificial neuron, wherein the input spike occurs at an input spike time relative to a reference time for the artificial neuron; (b) emitting an output spike from the artificial neuron based, at least in part, on the delayed input spike; (c) determining an actual time difference between the emission of the output spike from the artificial neuron and the reference time for the artificial neuron; and (d) adjusting the current delay associated with the input based on a difference between a target time difference and the actual time difference, the current delay, and an input spike time for the input spike.