On-chip Few-shot Learning with Surrogate Gradient Descent on a Neuromorphic Processor
This addresses the problem of efficient, online learning for neuromorphic systems, which is incremental as it builds on prior gradient-based methods but adapts them for hardware constraints.
The paper tackled the challenge of enabling gradient-based learning on neuromorphic hardware by implementing on-chip few-shot learning with surrogate gradient descent on Intel's Loihi processor, achieving results comparable to conventional simulations.
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.