Spiking Neural Networks are the next generation of machine learning, according to the litterature.
After the feed-forward perceptrons of the last century and the bi-directional deep networks trained
using gradient descent of today, this 3rd generation of neural networks uses biologically-realistic
models of neurons to carry out computation.
A spiking neural network (SNN) operates using spikes, which are discrete events that take place at
points in time, rather than continuous values. The occurrence of a spike is determined by differential
equations that represent the membrane potential of the neuron.
Essentially, once a neuron reaches a certain potential, it spikes, and the potential of that neuron is reset.
In this article, I will detail how this kind of network can be modelled using Tensorflow.
(more…)