The Ripple Pond: Enabling Spiking Networks to See

TL;DR

This paper introduces the Ripple Pond Network, a biologically inspired spiking neural network that enables rapid, scale, and rotation invariant object recognition in hardware for mobile and autonomous systems.

Contribution

The paper presents a novel hardware-compatible spiking neural network architecture that combines Ripple Pond and PolyChronous Networks for efficient, invariant object recognition.

Findings

Enables high-speed, low-power recognition suitable for mobile devices

Achieves scale and rotation invariance in object recognition

Operates effectively with low-resolution sensory input

Abstract

In this paper we present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network that, operating together with recently proposed PolyChronous Networks (PCN), enables rapid, unsupervised, scale and rotation invariant object recognition using efficient spatio-temporal spike coding. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilising the spatial properties of physically embedded neural networks and propagating waves of activity therein for information processing, using dimensional collapse of imagery information into amenable temporal patterns and the use of asynchronous frames for information binding.