Ryuji Saiin

According to our database, Ryuji Saiin authored at least 8 papers between 2022 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2024

Synaptic Interaction Penalty: Appropriate Penalty Term for Energy-Efficient Spiking Neural Networks.

Kazuma Suetake, Takuya Ushimaru, Ryuji Saiin, Yoshihide Sawada

Trans. Mach. Learn. Res., 2024

Spike Accumulation Forwarding for Effective Training of Spiking Neural Networks.

Ryuji Saiin, Tomoya Shirakawa, Sota Yoshihara, Yoshihide Sawada, Hiroyuki Kusumoto

Trans. Mach. Learn. Res., 2024

Magic for the Age of Quantized DNNs.

Yoshihide Sawada, Ryuji Saiin, Kazuma Suetake

CoRR, 2024

2023

S3NN: Time step reduction of spiking surrogate gradients for training energy efficient single-step spiking neural networks.

Kazuma Suetake, Shin-ichi Ikegawa, Ryuji Saiin, Yoshihide Sawada

Neural Networks, February, 2023

Spiking Synaptic Penalty: Appropriate Penalty Term for Energy-Efficient Spiking Neural Networks.

Kazuma Suetake, Takuya Ushimaru, Ryuji Saiin, Yoshihide Sawada

CoRR, 2023

2022

Rethinking the Role of Normalization and Residual Blocks for Spiking Neural Networks.

Shin-ichi Ikegawa, Ryuji Saiin, Yoshihide Sawada, Naotake Natori

Sensors, 2022

S²NN: Time Step Reduction of Spiking Surrogate Gradients for Training Energy Efficient Single-Step Neural Networks.

Kazuma Suetake, Shin-ichi Ikegawa, Ryuji Saiin, Yoshihide Sawada

CoRR, 2022

Spectral Pruning for Recurrent Neural Networks.

Takashi Furuya, Kazuma Suetake, Koichi Taniguchi, Hiroyuki Kusumoto, Ryuji Saiin, Tomohiro Daimon

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022