Visual Pattern Recognition with on On-chip Learning: towards a Fully Neuromorphic Approach
This work advances neuromorphic computing by enabling fully on-chip learning for pattern recognition, though it is incremental as it builds on prior hardware-in-the-loop methods.
The authors tackled visual pattern recognition using a spiking neural network with on-chip learning on neuromorphic hardware, achieving robustness with no accuracy drop under 130% input noise and tolerance to 20% neuron parameter noise.
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.