Visual Pattern Recognition with on On-chip Learning: towards a Fully Neuromorphic Approach

TL;DR

This paper introduces a neuromorphic spiking neural network capable of learning and recognizing visual patterns directly on hardware, demonstrating robustness to noise and enabling fully on-chip pattern recognition.

Contribution

It presents a novel on-chip learning SNN for visual pattern recognition that operates fully on neuromorphic hardware, advancing the field of autonomous neuromorphic systems.

Findings

Network accurately classifies patterns with no accuracy drop under 130% input noise.

The system maintains performance with up to 20% noise in neuron parameters.

Demonstrates a complete neuromorphic pattern learning and recognition setup.

Abstract

We present a spiking neural network (SNN) for visual pattern recognition with on-chip learning on neuromorphichardware. We show how this network can learn simple visual patterns composed of horizontal and vertical bars sensed by a Dynamic Vision Sensor, using a local spike-based plasticity rule. During recognition, the network classifies the pattern's identity while at the same time estimating its location and scale. We build on previous work that used learning with neuromorphic hardware in the loop and demonstrate that the proposed network can properly operate with on-chip learning, demonstrating a complete neuromorphic pattern learning and recognition setup. Our results show that the network is robust against noise on the input (no accuracy drop when adding 130% noise) and against up to 20% noise in the neuron parameters.