Training spiking neural networks using lessons from deep learning

JK Eshraghian, M Ward, EO Neftci… - Proceedings of the …, 2023 - ieeexplore.ieee.org
The brain is the perfect place to look for inspiration to develop more efficient neural
networks. The inner workings of our synapses and neurons provide a glimpse at what the …

Online training through time for spiking neural networks

M Xiao, Q Meng, Z Zhang, D He… - Advances in neural …, 2022 - proceedings.neurips.cc
Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models.
Recent progress in training methods has enabled successful deep SNNs on large-scale …

Towards memory-and time-efficient backpropagation for training spiking neural networks

Q Meng, M Xiao, S Yan, Y Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Spiking Neural Networks (SNNs) are promising energy-efficient models for
neuromorphic computing. For training the non-differentiable SNN models, the …

Bottom-up and top-down approaches for the design of neuromorphic processing systems: tradeoffs and synergies between natural and artificial intelligence

C Frenkel, D Bol, G Indiveri - Proceedings of the IEEE, 2023 - ieeexplore.ieee.org
While Moore's law has driven exponential computing power expectations, its nearing end
calls for new avenues for improving the overall system performance. One of these avenues …

Brains and bytes: Trends in neuromorphic technology

A Mehonic, J Eshraghian - APL Machine Learning, 2023 - pubs.aip.org
The term “neuromorphic” was originally introduced by Mead in the late 1980s, 1 referring to
devices and systems that imitated certain elements of biological neural systems. However …

DenRAM: neuromorphic dendritic architecture with RRAM for efficient temporal processing with delays

S D'Agostino, F Moro, T Torchet, Y Demirağ… - Nature …, 2024 - nature.com
An increasing number of studies are highlighting the importance of spatial dendritic
branching in pyramidal neurons in the neocortex for supporting non-linear computation …

Heterogeneous recurrent spiking neural network for spatio-temporal classification

B Chakraborty, S Mukhopadhyay - Frontiers in Neuroscience, 2023 - frontiersin.org
Spiking Neural Networks are often touted as brain-inspired learning models for the third
wave of Artificial Intelligence. Although recent SNNs trained with supervised …

An energy-efficient mechanical fault diagnosis method based on neural dynamics-inspired metric SpikingFormer for insufficient samples in industrial Internet of Things

C Wang, J Yang, H Jie, Z Zhao… - IEEE Internet of Things …, 2024 - ieeexplore.ieee.org
The Industrial Internet of Things (IIoT) significantly enhances mechanical fault diagnosis.
However, IIoT-based intelligent diagnostic models struggle with sample insufficiency and …

Addressing the speed-accuracy simulation trade-off for adaptive spiking neurons

L Taylor, A King, NS Harper - Advances in Neural …, 2024 - proceedings.neurips.cc
The adaptive leaky integrate-and-fire (ALIF) model is fundamental within computational
neuroscience and has been instrumental in studying our brains $\textit {in silico} $. Due to …

Efficient spiking neural networks with sparse selective activation for continual learning

J Shen, W Ni, Q Xu, H Tang - Proceedings of the AAAI Conference on …, 2024 - ojs.aaai.org
The next generation of machine intelligence requires the capability of continual learning to
acquire new knowledge without forgetting the old one while conserving limited computing …