Training Probabilistic Spiking Neural Networks with First-to-spike Decoding

10/29/2017
by   Alireza Bagheri, et al.
0

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 SNNs 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/05/2020

SpinAPS: A High-Performance Spintronic Accelerator for Probabilistic Spiking Neural Networks

We discuss a high-performance and high-throughput hardware accelerator f...
research
11/21/2019

Decoding Spiking Mechanism with Dynamic Learning on Neuron Population

A main concern in cognitive neuroscience is to decode the overt neural s...
research
05/13/2023

Quantization in Spiking Neural Networks

In spiking neural networks (SNN), at each node, an incoming sequence of ...
research
03/14/2023

Emergent Bio-Functional Similarities in a Cortical-Spike-Train-Decoding Spiking Neural Network Facilitate Predictions of Neural Computation

Despite its better bio-plausibility, goal-driven spiking neural network ...
research
08/05/2018

Computationally efficient model selection for joint spikes and waveforms decoding

A recent paradigm for decoding behavioral variables or stimuli from neur...

Please sign up or login with your details

Forgot password? Click here to reset