On-chip Few-shot Learning with Surrogate Gradient Descent on a Neuromorphic Processor

TL;DR

This paper demonstrates on-chip few-shot learning on a neuromorphic processor using surrogate gradients and transfer learning, enabling efficient online gesture recognition with limited samples, comparable to conventional models.

Contribution

It introduces a method for on-chip few-shot learning on neuromorphic hardware using surrogate gradient descent and transfer learning, bridging the gap between biological plausibility and practical implementation.

Findings

Loihi chip can learn gestures online with few samples

Achieves comparable accuracy to simulated models

Demonstrates feasibility of online neuromorphic learning

Abstract

Recent work suggests that synaptic plasticity dynamics in biological models of neurons and neuromorphic hardware are compatible with gradient-based learning (Neftci et al., 2019). Gradient-based learning requires iterating several times over a dataset, which is both time-consuming and constrains the training samples to be independently and identically distributed. This is incompatible with learning systems that do not have boundaries between training and inference, such as in neuromorphic hardware. One approach to overcome these constraints is transfer learning, where a portion of the network is pre-trained and mapped into hardware and the remaining portion is trained online. Transfer learning has the advantage that pre-training can be accelerated offline if the task domain is known, and few samples of each class are sufficient for learning the target task at reasonable accuracies. Here, we demonstrate on-line surrogate gradient few-shot learning on Intel's Loihi neuromorphic research processor using features pre-trained with spike-based gradient backpropagation-through-time. Our experimental results show that the Loihi chip can learn gestures online using a small number of shots and achieve results that are comparable to the models simulated on a conventional processor.