Spike Accumulation Forwarding for Effective Training of Spiking Neural Networks

no code implementations • 4 Oct 2023 • Ryuji Saiin, Tomoya Shirakawa, Sota Yoshihara, Yoshihide Sawada, Hiroyuki Kusumoto

Our proposed method can solve these problems; namely, SAF can halve the number of operations during the forward process, and it can be theoretically proven that SAF is consistent with the Spike Representation and OTTT, respectively.

Theoretical Error Analysis of Entropy Approximation for Gaussian Mixture

no code implementations • 26 Feb 2022 • Takashi Furuya, Hiroyuki Kusumoto, Koichi Taniguchi, Naoya Kanno, Kazuma Suetake

Notably, Gal and Ghahramani [2016] proposed the approximate entropy that is the sum of the entropies of unimodal Gaussian distributions.

Variational Inference

Spectral Pruning for Recurrent Neural Networks

1 code implementation • 23 May 2021 • Takashi Furuya, Kazuma Suetake, Koichi Taniguchi, Hiroyuki Kusumoto, Ryuji Saiin, Tomohiro Daimon

Recurrent neural networks (RNNs) are a class of neural networks used in sequential tasks.

Edge-computing