Towards spike-based machine intelligence with neuromorphic computing

By Kaushik Roy, Akhilesh R. Jaiswal, Priyadarshini Panda. Nature, 2019

2,181 citations recorded by the source corpus.

Subfields: Cellular and Molecular Neuroscience, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/0ebca477733c79e13900d1b4e00b67a9b7bf8abd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cellular and Molecular Neuroscience

In Electrical and Electronic Engineering

Citations in the corpus

Going Deeper With Directly-Trained Larger Spiking Neural Networks (2020, methodology): “Inspired by human neurons’ working patterns, spiking neural networks (SNNs) have been considered as a promising model in artiﬁcial intelligence and theoretical neuro-science (Roy, Jaiswal, and Panda 2019).”
The Heidelberg Spiking Data Sets for the Systematic Evaluation of Spiking Neural Networks (2019, background): “To instantiate such functional connectivity in-silico, a growing number of SNNs training algorithms have been developed [2]–[8] both for conventional computers and neuromorphic hardware [9]–[14].”
The remarkable robustness of surrogate gradient learning for instilling complex function in spiking neural networks (2020, background): “…results suggest that most biological networks exhibit sparse spiking activity, a feature that is presumed to underlie their superior energy efficiency (Boahen, 2017; Cramer, Billaudelle et al., 2020; Neftci, 2018; Roy, Jaiswal, & Panda, 2019; Schemmel et al., 2010; Sterling & Laughlin, 2017).”
Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks (2020, background): “Due to their distinctive properties, such as temporal information processing capability, low power consumption [49], and high biological plausibility [16], SNNs increasingly arouse researchers’ great interest in recent years.”
Training Spiking Neural Networks Using Lessons From Deep Learning (2021, methodology): “From the engineer’s perspective, neuron models derived from experimental results have allowed us to design extremely energy-efficient networks when running on hardware tailored to SNNs [219], [220], [221], [222], [223], [224], [225].”
Spike-driven Transformer (2023, methodology): “Bio-inspired Spiking Neural Networks can proﬁt from advanced deep learning and neuroscience knowledge concurrently [28, 5, 7, 29].”
Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks (2024, methodology): “Brain-inspired neuromorphic computing, e.g., biologically plausible spiking neural networks (SNNs), has attracted tremendous attention (Roy et al., 2019) and achieved promising results with deep architectures and gradient-based methods recently (Shrestha & Orchard, 2018; Zheng et al., 2021; Fang et…”
Attention Spiking Neural Networks (2022, background): “event frames since it can skip the computation of the zero areas in each input [6].”