A fast learning algorithm of self-learning spiking neural network

This paper studies the effects of different bio-synaptic membrane potential mechanisms on the inference speed of both spiking feedforward neural networks (SFNNs) and spiking convolutional neural networks (SCNNs). These mechanisms inspired by biological neuron phenomenon, such as electronic conduction in neurons, chemical neurotransmitter attenuation between presynaptic and postsynaptic neurons, are considered to be modeled in mathematical and applied to artificial spiking networks. In the field of spiking neural networks, we model some biological neural membrane potential updating strategies based on integrate-and-fire (I&F) spiking neuron, which includes spiking neuron model with membrane potential decay (MemDec), spiking neuron model with synaptic input current superposition at spiking time (SynSup) and spiking neuron model with synaptic input current accumulation(SynAcc). Experiment results show that compared with the general I&F model (one of the most commonly used spiking neuron models), SynSup and SynAcc can effectively improve the learning speed in the inference stage of SCNNs and SFNNs.

show abstract

Section: Inference Latency 185mentioning

confidence: 99%

Improved integrate-and-fire neuron models for inference acceleration of spiking neural networks

Zhou¹,

Zhang

2020

Appl Intell

View full text Add to dashboard Cite

show abstract

“…However, in SNNs, signals are presented by streams of spike events, and flow layer by layer via spikes 190 which created by neurons, ultimately, drive firing of output neurons that collect evidence over time. This mechanism gives SNN some advantages such as efficient processing of timevarying inputs [22] and high computational performance on specialized hardware [23]. 195 However, it also implies that even for a time-invariant input, network output maybe varies over time, especially at the beginning of the spike signal input to the network because that sufficient spike evidence has not been collected by the output neurons.…”

Section: Inference Latency 185mentioning

confidence: 99%