Learning Spiking Neural Systems with the Event-Driven Forward-Forward Process

03/30/2023
by   Alexander Ororbia, et al.
0

We develop a novel credit assignment algorithm for information processing with spiking neurons without requiring feedback synapses. Specifically, we propose an event-driven generalization of the forward-forward and the predictive forward-forward learning processes for a spiking neural system that iteratively processes sensory input over a stimulus window. As a result, the recurrent circuit computes the membrane potential of each neuron in each layer as a function of local bottom-up, top-down, and lateral signals, facilitating a dynamic, layer-wise parallel form of neural computation. Unlike spiking neural coding, which relies on feedback synapses to adjust neural electrical activity, our model operates purely online and forward in time, offering a promising way to learn distributed representations of sensory data patterns with temporal spike signals. Notably, our experimental results on several pattern datasets demonstrate that the even-driven forward-forward (ED-FF) framework works well for training a dynamic recurrent spiking system capable of both classification and reconstruction.

READ FULL TEXT

page 7

page 9

page 10

research
05/31/2017

SuperSpike: Supervised learning in multi-layer spiking neural networks

A vast majority of computation in the brain is performed by spiking neur...
research
01/04/2023

The Predictive Forward-Forward Algorithm

We propose the predictive forward-forward (PFF) algorithm for conducting...
research
11/03/2020

Vision-Based Control for Robots by a Fully Spiking Neural System Relying on Cerebellar Predictive Learning

The cerebellum plays a distinctive role within our motor control system ...
research
08/23/2019

Spiking Neural Predictive Coding for Continual Learning from Data Streams

For energy-efficient computation in specialized neuromorphic hardware, w...
research
12/20/2021

Accurate online training of dynamical spiking neural networks through Forward Propagation Through Time

The event-driven and sparse nature of communication between spiking neur...
research
03/11/2022

Ensemble plasticity and network adaptability in SNNs

Artificial Spiking Neural Networks (ASNNs) promise greater information p...
research
05/12/2020

Fostering Event Compression using Gated Surprise

Our brain receives a dynamically changing stream of sensorimotor data. Y...

Please sign up or login with your details

Forgot password? Click here to reset