Classifying Images with Few Spikes per Neuron
Year: 2020
Type: preprint
Abstract: Spiking neural networks (SNNs) promise to provide AI implementations with adrastically reduced energy budget in comparison with standard artificial neural
networks (ANNs). Besides recurrent SNN modules that can be efficiently trained
on-chip, many AI applications require the use of feedforward convolutional
neural networks (CNNs) as preprocessors for visual or other sensory inputs. The
standard solution has been to train a CNN consisting of non-spiking neurons,
typically using the rectified linear ReLU function as activation function, and
then to translate these CNNs with ReLU neurons via rate coding into SNNs.
However this produces SNNs with long latency and small throughput, since the
number of spikes that a neuron has to emit is on the order of the number N of
output values of the corresponding CNN gate which subsequent layers need to be
able to distinguish. We introduce a new ANN-SNN conversion - called
FS-conversion - that needs only log N many time steps for that, which is
optimal from the perspective of information theory. This can be achieved with a
simple variation of the spiking neuron model that has no membrane leak but an
exponentially decreasing firing threshold. We show that for the classification
of images from ImageNet and CIFAR10 this new conversion reduces latency and
drastically increases the throughput compared with rate-based conversion, while
achieving almost the same classification performance as the ANN.
Source: arXiv (Cornell University)
Authors: Christoph Stöckl, Wolfgang Maass
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3004073022
