2024/12/19 by Gabriel Béna, Wunderlich Timo, Timo Wunderlich +10 · 1 voice · 3 citations
Engineering · #Advanced Memory and Neural Computing #Artificial intelligence #Artificial neural network #Backpropagation #Computer science #Event (particle physics) #Ferroelectric and Negative Capacitance Devices #Neuromorphic engineering #Physics
paper · pdf · doi:10.48550/arxiv.2412.15021
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2024/12/19 · openalex created_date 2024/12/21 · openalex updated_date 2026/08/06
Neuromorphic computing aims to replicate the brain's capabilities for energy efficient and parallel information processing, promising a solution to the increasing demand for faster and more efficient computational systems. Efficient training of neural networks on neuromorphic hardware requires the development of training algorithms that retain the sparsity of spike-based communication during training. Here, we report on the first implementation of event-based backpropagation on the SpiNNaker2 neuromorphic hardware platform. We use EventProp, an algorithm for event-based backpropagation in spiking neural networks (SNNs), to compute exact gradients using sparse communication of error signals between neurons. Our implementation computes multi-layer networks of leaky integrate-and-fire neurons using discretized versions of the differential equations and their adjoints, and uses event packets to transmit spikes and error signals between network layers. We demonstrate a proof-of-concept of batch-parallelized, on-chip training of SNNs using the Yin Yang dataset, and provide an off-chip implementation for efficient prototyping, hyper-parameter search, and hybrid training methods.