Emulating Brain-like Rapid Learning in Neuromorphic Edge Computing

TL;DR

This paper presents a neuromorphic approach that emulates brain-like rapid learning through a two-stage process, enabling real-time, data-efficient learning on edge devices using hardware-specific plasticity rules.

Contribution

It introduces a meta-training framework to optimize synaptic plasticity hyperparameters for one-shot learning on neuromorphic hardware, enhancing rapid adaptation capabilities.

Findings

Achieved real-time one-shot learning on neuromorphic hardware.

Significantly outperformed transfer learning in accuracy.

Demonstrated applicability to event-driven vision data.

Abstract

Achieving personalized intelligence at the edge with real-time learning capabilities holds enormous promise in enhancing our daily experiences and helping decision making, planning, and sensing. However, efficient and reliable edge learning remains difficult with current technology due to the lack of personalized data, insufficient hardware capabilities, and inherent challenges posed by online learning. Over time and across multiple developmental stages, the brain has evolved to efficiently incorporate new knowledge by gradually building on previous knowledge. In this work, we emulate the multiple stages of learning with digital neuromorphic technology that simulates the neural and synaptic processes of the brain using two stages of learning. First, a meta-training stage trains the hyperparameters of synaptic plasticity for one-shot learning using a differentiable simulation of the neuromorphic hardware. This meta-training process refines a hardware local three-factor synaptic plasticity rule and its associated hyperparameters to align with the trained task domain. In a subsequent deployment stage, these optimized hyperparameters enable fast, data-efficient, and accurate learning of new classes. We demonstrate our approach using event-driven vision sensor data and the Intel Loihi neuromorphic processor with its plasticity dynamics, achieving real-time one-shot learning of new classes that is vastly improved over transfer learning. Our methodology can be deployed with arbitrary plasticity models and can be applied to situations demanding quick learning and adaptation at the edge, such as navigating unfamiliar environments or learning unexpected categories of data through user engagement.