paper-with-me

홈 › Papers

Expanding memory in recurrent spiking networks

2023-10-29 · Ismael Balafrej, Fabien Alibart, Jean Rouat

Recurrent spiking neural networks (RSNNs) are notoriously difficult to train because of the vanishing gradient problem that is enhanced by the binary nature of the spikes. In this paper, we review the ability of the current state-of-the-art RSNNs to solve long-term memory tasks, and show that they have strong constraints both in performance, and for their implementation on hardware analog neuromorphic processors. We present a novel spiking neural network that circumvents these limitations. Our biologically inspired neural network uses synaptic delays, branching factor regularization and a novel surrogate derivative for the spiking function. The proposed network proves to be more successful in using the recurrent connections on memory tasks.

📄 PDF Abstract BibTeX arXiv:2310.19067

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Online Training of Spiking Recurrent Neural Networks with Phase-Change Memory Synapses

2021-08-04 · Yigit Demirag, Charlotte Frenkel, Melika Payvand, Giacomo Indiveri

Spiking recurrent neural networks (RNNs) are a promising tool for solving a wide variety of complex cognitive and motor tasks, due to their rich temporal dynamics and sparse processing. However training spiking RNNs on d…

Long Short-Term Memory Spiking Networks and Their Applications

2020-07-09 · Ali Lotfi Rezaabad, Sriram Vishwanath

Recent advances in event-based neuromorphic systems have resulted in significant interest in the use and development of spiking neural networks (SNNs). However, the non-differentiable nature of spiking neurons makes SNNs…

Time SeriesTime Series Analysis

Efficient Event-based Delay Learning in Spiking Neural Networks

2025-01-13 · Balázs Mészáros, James C. Knight, Thomas Nowotny

Spiking Neural Networks (SNNs) are attracting increased attention as a more energy-efficient alternative to traditional Artificial Neural Networks. Spiking neurons are stateful and intrinsically recurrent, making them we…

Gating out sensory noise in a spike-based Long Short-Term Memory network

2018-01-01 · ICLR 2018 1 · Davide Zambrano, Isabella Pozzi, Roeland Nusselder, Sander Bohte

Spiking neural networks are being investigated both as biologically plausible models of neural computation and also as a potentially more efficient type of neural network. While convolutional spiking neural networks have…

Reinforcement Learning

SpikingGamma: Surrogate-Gradient Free and Temporally Precise Online Training of Spiking Neural Networks with Smoothed Delays

2026-02-02 · Roel Koopman, Sebastian Otte, Sander Bohté arxiv

Neuromorphic hardware implementations of Spiking Neural Networks (SNNs) promise energy-efficient, low-latency AI through sparse, event-driven computation. Yet, training SNNs under fine temporal discretization remains a m…