NELGOct 22, 2020

Brain-Inspired Learning on Neuromorphic Substrates

arXiv:2010.11931v1100 citations
Originality Incremental advance
AI Analysis

This work addresses the problem of enabling efficient online learning on neuromorphic substrates for scalable, low-power temporal data processing, representing an incremental advancement in bridging deep learning and neuromorphic computing.

The paper tackles the challenge of training neuromorphic hardware by developing a mathematical framework that connects Real-Time Recurrent Learning to biologically plausible rules for Spiking Neural Networks, using a sparse approximation to reduce computational complexity and improve applicability.

Neuromorphic hardware strives to emulate brain-like neural networks and thus holds the promise for scalable, low-power information processing on temporal data streams. Yet, to solve real-world problems, these networks need to be trained. However, training on neuromorphic substrates creates significant challenges due to the offline character and the required non-local computations of gradient-based learning algorithms. This article provides a mathematical framework for the design of practical online learning algorithms for neuromorphic substrates. Specifically, we show a direct connection between Real-Time Recurrent Learning (RTRL), an online algorithm for computing gradients in conventional Recurrent Neural Networks (RNNs), and biologically plausible learning rules for training Spiking Neural Networks (SNNs). Further, we motivate a sparse approximation based on block-diagonal Jacobians, which reduces the algorithm's computational complexity, diminishes the non-local information requirements, and empirically leads to good learning performance, thereby improving its applicability to neuromorphic substrates. In summary, our framework bridges the gap between synaptic plasticity and gradient-based approaches from deep learning and lays the foundations for powerful information processing on future neuromorphic hardware systems.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes