Spiking Neural Predictive Coding for Continual Learning from Data Streams

08/23/2019
by   Alexander Ororbia, et al.
0

For energy-efficient computation in specialized neuromorphic hardware, we present the Spiking Neural Coding Network, an instantiation of a family of artificial neural models strongly motivated by the theory of predictive coding. The model, in essence, works by operating in a never-ending process of "guess-and-check", where neurons predict the activity values of one another and then immediately adjust their own activities to make better future predictions. The interactive, iterative nature of our neural system fits well into the continuous time formulation of data sensory stream prediction and, as we show, the model's structure yields a simple, local synaptic update rule, which could be used to complement or replace online spike-timing dependent plasticity rules. In this article, we experiment with an instantiation of our model that consists of leaky integrate-and-fire units. However, the general framework within which our model is situated can naturally incorporate more complex, formal neurons such as the Hodgkin-Huxley model. Our experimental results in pattern recognition demonstrate the potential of the proposed model when binary spike trains are the primary paradigm for inter-neuron communication. Notably, our model is competitive in terms of classification performance, capable of conducting online semi-supervised learning, and more computationally economical and biologically-plausible than popular artificial neural networks.

READ FULL TEXT
research
12/17/2018

A Biologically Plausible Supervised Learning Method for Spiking Neural Networks Using the Symmetric STDP Rule

Spiking neural networks (SNNs) possess energy-efficient potential due to...
research
07/30/2019

Temporal coding in spiking neural networks with alpha synaptic function

The timing of individual neuronal spikes is essential for biological bra...
research
03/30/2023

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

We develop a novel credit assignment algorithm for information processin...
research
10/13/2017

Efficient Computation in Adaptive Artificial Spiking Neural Networks

Artificial Neural Networks (ANNs) are bio-inspired models of neural comp...
research
12/04/2015

An Online Unsupervised Structural Plasticity Algorithm for Spiking Neural Networks

In this article, we propose a novel Winner-Take-All (WTA) architecture e...
research
06/28/2021

Integrate-and-Fire Neurons for Low-Powered Pattern Recognition

Embedded systems acquire information about the real world from sensors a...

Please sign up or login with your details

Forgot password? Click here to reset