Slax: a composable JAX library for rapid and flexible prototyping of spiking neural networks
Spiking neural networks (SNNs) offer rich temporal dynamics and unique capabilities, but their training presents challenges. While backpropagation through time with surrogate gradients is the defacto standard for training SNNs, it scales poorly with long time sequences. Alternative learning rules an...
Saved in:
Main Authors: | Thomas M Summe, Siddharth Joshi |
---|---|
Format: | Article |
Language: | English |
Published: |
IOP Publishing
2025-01-01
|
Series: | Neuromorphic Computing and Engineering |
Subjects: | |
Online Access: | https://doi.org/10.1088/2634-4386/ada9a8 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
SPICE-Level Demonstration of Unsupervised Learning With Spintronic Synapses in Spiking Neural Networks
by: Salah Daddinounou, et al.
Published: (2025-01-01) -
Multilayer magnetic skyrmion devices for spiking neural networks
by: Aijaz H Lone, et al.
Published: (2025-01-01) -
Enhancing navigation performance in unknown environments using spiking neural networks and reinforcement learning with asymptotic gradient method
by: Xiaode Liu, et al.
Published: (2025-01-01) -
Assessing ECG Interpretation Expertise in Medical Practitioners Through Eye Movement Data and Neuromorphic Models
by: Syed Mohsin Bokhari, et al.
Published: (2025-01-01) -
Efficient Hardware Implementation of a Multi-Layer Gradient-Free Online-Trainable Spiking Neural Network on FPGA
by: Ali Mehrabi, et al.
Published: (2024-01-01)