Oral presentation

FS Focused Session "AI Electronics" » FS.1 Focused Session "AI Electronics"

[15a-B414-1~9] FS.1 Focused Session "AI Electronics"

Wed. Mar 15, 2023 9:00 AM - 11:30 AM B414 (Building No. 2)

△：Presentation by Applicant for JSAP Young Scientists Presentation Award
▲：English Presentation
▼：Both of Above
No Mark：None of Above

+Add all to schedule

9:00 AM - 9:15 AM

△ [15a-B414-1] Biologically plausible training algorithm for deep spiking neural networks

〇Katsuma Inoue¹, Yongbo Zhang¹, Mitsumasa Nakajima², Yasuo Kuniyoshi¹, Kohei Nakajima¹ (1.Graduate School of IST. Univ. of Tokyo, 2.NTT Device Technology Labs.)

9:15 AM - 9:30 AM

△ [15a-B414-2] Fabrication and Training of 3D Conductive Polymer Networks for Neuromorphic Wetware

〇(DC)Naruki Hagiwara¹, Kota Ando¹, Tetsuya Asai¹, Megumi Akai-Kasaya^1,2 (1.Hokkaido Univ., 2.Osaka Univ.)

9:30 AM - 9:45 AM

[15a-B414-3] Stochastic Resonance Effects of Floating Gate (FG) Technology-based Neurons in Summing Network

〇Akira Goda¹, Chihiro Matsui¹, Ken Takeuchi¹ (1.Univ. Tokyo)

9:45 AM - 10:00 AM

△ [15a-B414-4] Linear Writing Method of Digital ReRAM and Write Non-ideality Aware Training Algorithm for Neural Networks

〇(M1)Ayumu Yamada¹, Naoko Misawa¹, Shunsaku Muraoka², Ken Kawai², Chihiro Matsui¹, Ken Takeuchi¹ (1.Univ. Tokyo, 2.NTCJ)

10:00 AM - 10:15 AM

△ [15a-B414-5] Synchrotron-Radiation Nanotomography of Neuronal Networks of Schizophrenia Cases and its Application to the Neural Network Design

〇(BC)Yo Maruta¹, Rino Saiga¹, Ryuta Mizutani¹, Yoshiro Yamamoto², Susumu Takekoshi³, Chie Inomoto³, Naoya Nakamura³, Makoto Arai⁴, Mitsuhiro Miyashita⁴, Kenichi Oshima⁴, Masanari Itokawa⁴, Youta Torii⁵, Itaru Kushima⁵, Norio Ozaki⁵, Shuji Iritani⁶, Yuichi Yamashita⁷, Masayuki Uesugi⁸, Akihisa Takeuchi⁸, Kentaro Uesugi⁸, Yasuko Terada⁸, Yoshio Suzuki⁹, Viktor Nikitin¹⁰, Francesco De Carlo¹⁰ (1.Sch of Engineering, Tokai Univ, 2.Sch of Science, Tokai Univ, 3.Sch of Medicine, Tokai Univ, 4.Tokyo Metropolitan Institute of Medical Sci, 5.Grad Sch of Medicine, Nagoya Univ, 6.Okehazama Hospital Fujita Kokoro Care Center, 7.National Center of Neurology and Psychiatry, 8.JASRI/SPring-8, 9.KEK, 10.Argonne National Lab)

10:30 AM - 10:45 AM

△ [15a-B414-6] Device Error Compensation for Computation-in-Memory 1
Compensation of Write Variation of Non-volatile Memory by Neural Network Algorithm Aware Layer-wise Retraining in Computation-in-Memory

〇Shinsei Yoshikiyo¹, Naoko Misawa¹, Chihiro Matsui¹, Ken Takeuchi¹ (1.Univ. Tokyo)

10:45 AM - 11:00 AM

[15a-B414-7] Device Error Compensation for Computation-in-Memory 2
Difference in Inter-Layer Error Tolerance and Input-Output Distribution Due to Shortcut Connection

〇Shinsei Yoshikiyo¹, Ayumu Yamada¹, Naoko Misawa¹, Chihiro Matsui¹, Ken Takeuchi¹ (1.Univ. Tokyo)

11:00 AM - 11:15 AM

△ [15a-B414-8] Acceleration of Quantum-Inspired Ising Machines Using Extraction-Type Majority Voting Logic by Parameter Optimization

〇Asaki Yoshida¹, Moe Shimada¹, Ryoya Yonemoto¹, Jun-ichi Shirakashi¹ (1.Tokyo Univ. Agr. & Tech.)

11:15 AM - 11:30 AM

[15a-B414-9] FPGA Implementation of Fully-Connected Ising Machine Using Extraction-Type Majority Voting Logic

〇Ryoya Yonemoto¹, Asaki Yoshida¹, Moe Shimada¹, Jun-ichi Shirakashi¹ (1.Tokyo Univ. Arg. & Tech.)

Session information

[15a-B414-1~9] FS.1 Focused Session "AI Electronics"

△ [15a-B414-1] Biologically plausible training algorithm for deep spiking neural networks

△ [15a-B414-2] Fabrication and Training of 3D Conductive Polymer Networks for Neuromorphic Wetware

[15a-B414-3] Stochastic Resonance Effects of Floating Gate (FG) Technology-based Neurons in Summing Network

△ [15a-B414-4] Linear Writing Method of Digital ReRAM and Write Non-ideality Aware Training Algorithm for Neural Networks

△ [15a-B414-5] Synchrotron-Radiation Nanotomography of Neuronal Networks of Schizophrenia Cases and its Application to the Neural Network Design

△ [15a-B414-6] Device Error Compensation for Computation-in-Memory 1
Compensation of Write Variation of Non-volatile Memory by Neural Network Algorithm Aware Layer-wise Retraining in Computation-in-Memory

[15a-B414-7] Device Error Compensation for Computation-in-Memory 2
Difference in Inter-Layer Error Tolerance and Input-Output Distribution Due to Shortcut Connection

△ [15a-B414-8] Acceleration of Quantum-Inspired Ising Machines Using Extraction-Type Majority Voting Logic by Parameter Optimization

[15a-B414-9] FPGA Implementation of Fully-Connected Ising Machine Using Extraction-Type Majority Voting Logic

Authenticate

Session information

[15a-B414-1~9] FS.1 Focused Session "AI Electronics"

△ [15a-B414-1] Biologically plausible training algorithm for deep spiking neural networks

△ [15a-B414-2] Fabrication and Training of 3D Conductive Polymer Networks for Neuromorphic Wetware

[15a-B414-3] Stochastic Resonance Effects of Floating Gate (FG) Technology-based Neurons in Summing Network

△ [15a-B414-4] Linear Writing Method of Digital ReRAM and Write Non-ideality Aware Training Algorithm for Neural Networks

△ [15a-B414-5] Synchrotron-Radiation Nanotomography of Neuronal Networks of Schizophrenia Cases and its Application to the Neural Network Design

△ [15a-B414-6] Device Error Compensation for Computation-in-Memory 1Compensation of Write Variation of Non-volatile Memory by Neural Network Algorithm Aware Layer-wise Retraining in Computation-in-Memory

[15a-B414-7] Device Error Compensation for Computation-in-Memory 2Difference in Inter-Layer Error Tolerance and Input-Output Distribution Due to Shortcut Connection

△ [15a-B414-8] Acceleration of Quantum-Inspired Ising Machines Using Extraction-Type Majority Voting Logic by Parameter Optimization

[15a-B414-9] FPGA Implementation of Fully-Connected Ising Machine Using Extraction-Type Majority Voting Logic

Authenticate

△ [15a-B414-6] Device Error Compensation for Computation-in-Memory 1
Compensation of Write Variation of Non-volatile Memory by Neural Network Algorithm Aware Layer-wise Retraining in Computation-in-Memory

[15a-B414-7] Device Error Compensation for Computation-in-Memory 2
Difference in Inter-Layer Error Tolerance and Input-Output Distribution Due to Shortcut Connection