Our source code is available at github.com/mbalazs98/de....
GitHub - mbalazs98/deventprop
Contribute to mbalazs98/deventprop development by creating an account on GitHub.
github.com
January 23, 2025 at 12:50 PM
Our source code is available at github.com/mbalazs98/de....
Our event-based method enables precise delay learning for spiking neural networks, improving performance on Yin-Yang, SHD, and SSC datasets. We introduce the first gradient based delay learning approach for recurrent connections, achieving 26x faster performance and 50% lower memory usage.
Efficient Event-based Delay Learning in Spiking Neural Networks
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 recur...
arxiv.org
January 23, 2025 at 12:49 PM
Our event-based method enables precise delay learning for spiking neural networks, improving performance on Yin-Yang, SHD, and SSC datasets. We introduce the first gradient based delay learning approach for recurrent connections, achieving 26x faster performance and 50% lower memory usage.