Training probabilistic spiking neural networks with first- to-spike decoding
Document Type
Conference Proceeding
Publication Date
9-10-2018
Abstract
Third-generation neural networks, or Spiking Neural Networks (SNNs), aim at harnessing the energy efficiency of spike-domain processing by building on computing elements that operate on, and exchange, spikes. In this paper, the problem of training a two-layer SNN is studied for the purpose of classification, under a Generalized Linear Model (GLM) probabilistic neural model that was previously considered within the computational neuroscience literature. Conventional classification rules for SNNs operate offline based on the number of output spikes at each output neuron. In contrast, a novel training method is proposed here for a first-to-spike decoding rule, whereby the SNN can perform an early classification decision once spike firing is detected at an output neuron. Numerical results bring insights into the optimal parameter selection for the GLM neuron and on the accuracy-complexity trade-off performance of conventional and first-to-spike decoding.
Identifier
85054215272 (Scopus)
ISBN
[9781538646588]
Publication Title
ICASSP IEEE International Conference on Acoustics Speech and Signal Processing Proceedings
External Full Text Location
https://doi.org/10.1109/ICASSP.2018.8462410
ISSN
15206149
First Page
2986
Last Page
2990
Volume
2018-April
Grant
725731
Fund Ref
Horizon 2020
Recommended Citation
Bagheri, Alireza; Simeone, Osvaldo; and Rajendran, Bipin, "Training probabilistic spiking neural networks with first- to-spike decoding" (2018). Faculty Publications. 8383.
https://digitalcommons.njit.edu/fac_pubs/8383
