Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

neuromorphic chips

Neuromorphic chips are specialized semiconductor processors designed to physically emulate the neural architecture and computational mechanisms of the biological brain. Unlike conventional computers based on traditional architectures that separate memory storage from processing units, neuromorphic hardware co-locates memory and computation across networks of artificial neurons and synapses. These chips typically operate using spiking neural networks, which communicate information through discrete, event-driven electrical pulses across both spatial and temporal dimensions rather than continuous clock-driven calculations. Because individual components only activate and consume power when spikes occur, neuromorphic chips achieve massive parallelism, real-time data processing, and exceptional energy efficiency for artificial intelligence and sensory tasks compared to standard processors.

1 item

Spatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks

Spatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks

Yujie Wu, Lei Deng, Guoqi Li, Jun Zhu, Luping Shi

OrganizationsTsinghua UniversityUniversity of California, Santa Barbara

Why you should read this

Proposes a spatio-temporal backpropagation framework with surrogate gradient approximation for iterative leaky integrate-and-fire models, overcoming the non-differentiability of spikes to achieve high-performance direct supervised training of spiking neural networks on both static and neuromorphic benchmarks.

Compared with artificial neural networks (ANNs), spiking neural networks (SNNs) are promising to explore the brain-like behaviors since the spikes could encode more spatio-temporal information. Although pre-training from ANN or direct training based on backpropagation (BP) makes the supervised training of SNNs possible, these methods only exploit the networks' spatial domain information which leads to the performance bottleneck and requires many complicated training skills. Another fundamental issue is that the spike activity is naturally non-differentiable which causes great difficulties in training SNNs. To this end, we build an iterative LIF model that is more friendly for gradient descent training. By simultaneously considering the layer-by-layer spatial domain (SD) and the timing-dependent temporal domain (TD) in the training phase, as well as an approximated derivative for the spike activity, we propose a spatio-temporal backpropagation (STBP) training framework without using any complicated technology. We achieve the best performance of multi-layered perceptron (MLP) compared with existing state-of-the-art algorithms over the static MNIST and the dynamic N-MNIST dataset as well as a custom object detection dataset. This work provides a new perspective to explore the high-performance SNNs for future brain-like computing paradigm with rich spatio-temporal dynamics.

Added

2026-09-25