Spiking neural networks trained with surrogate gradients as universal function approximators
Timothee Masquelier a
a CNRS, Université de Rennes 1, Campus de Beaulieu, Rennes, 35000, France
nanoGe Fall Meeting
Proceedings of Materials for Sustainable Development Conference (MAT-SUS) (NFM22)
Neuromorphic Sensory-Processing-Learning Systems inspired in Computation Neuroscience
Barcelona, Spain, 2022 October 24th - 28th
Invited Speaker, Timothee Masquelier, presentation 259
Publication date: 11th July 2022

The recent discovery of surrogate gradient learning (SGL) has been a game changer for spiking neural networks (SNNs). In short, it reconciles SNNs with backpropagation, THE algorithm that caused the deep learning revolution. I will review recent work in which we show that SNNs trained with SGL can solve a broad range of problems, just like Artificial Neural Networks (ANN), but possibly with much much less energy

The recent discovery of surrogate gradient learning (SGL) has been a game changer for spiking neural networks (SNNs). In short, it reconciles SNNs with backpropagation, THE algorithm that caused the deep learning revolution. I will review recent work in which we show that SNNs trained with SGL can solve a broad range of problems, just like Artificial Neural Networks (ANN), but possibly with much much less energy

The recent discovery of surrogate gradient learning (SGL) has been a game changer for spiking neural networks (SNNs). In short, it reconciles SNNs with backpropagation, THE algorithm that caused the deep learning revolution. I will review recent work in which we show that SNNs trained with SGL can solve a broad range of problems, just like Artificial Neural Networks (ANN), but possibly with much much less energy

© FUNDACIO DE LA COMUNITAT VALENCIANA SCITO
We use our own and third party cookies for analysing and measuring usage of our website to improve our services. If you continue browsing, we consider accepting its use. You can check our Cookies Policy in which you will also find how to configure your web browser for the use of cookies. More info