Fast and energy-efficient neuromorphic deep learning with first-spike times

Göltz, J.; Kriener, L.; Baumbach, A.; Billaudelle, S.; Breitwieser, O.; Cramer, B.; Dold, D.; Kungl, A. F.; Senn, W.; Schemmel, J.; Meier, K.; Petrovici, M. A. (2021). Fast and energy-efficient neuromorphic deep learning with first-spike times. Nature machine intelligence, 3(9), pp. 823-835. Springer Nature 10.1038/s42256-021-00388-x

Preview	Text G_ltz2021Fastandene.pdf - Submitted Version Available under License Publisher holds Copyright. Author holds Copyright Download (7MB) | Preview
	Text s42256-021-00388-x.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Author holds Copyright Download (4MB)

For a biological agent operating under environmental pressure, energy consumption and reaction times are of critical importance. Similarly, engineered systems are optimized for short time-to-solution and low energy-to-solution characteristics. At the level of neuronal implementation, this implies achieving the desired results with as few and as early spikes as possible. With time-to-first-spike coding, both of these goals are inherently emerging features of learning. Here, we describe a rigorous derivation of a learning rule for such first-spike times in networks of leaky integrate-and-fire neurons, relying solely on input and output spike times, and show how this mechanism can implement error backpropagation in hierarchical spiking networks. Furthermore, we emulate our framework on the BrainScaleS-2 neuromorphic system and demonstrate its capability of harnessing the system’s speed and energy characteristics. Finally, we examine how our approach generalizes to other neuromorphic platforms by studying how its performance is affected by typical distortive effects induced by neuromorphic substrates.

Interest & Impact

Downloads

399 since deposited on 12 Jan 2022
129 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item