Atsuya Okazaki

IBM Research - Tokyo — Japan

Engineering · Physical Sciences

6h-index316citations33works1.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Memory and Neural Computing(19), Ferroelectric and Negative Capacitance Devices(16), Neural Networks and Reservoir Computing(10), Neural dynamics and brain function(5), Parallel Computing and Optimization Techniques(4)

Publications33 total

Row-by-row convolutional neural networks for Analog-AI
2025Open Access
Demonstration of transformer-based ALBERT model on a 14nm analog AI inference chip
Nature Communications·2025· 1 citedOpen Access
Analog AI Accelerators for Transformer-based Language Models: Hardware, Workload, and Power Performance
2025
Analog-AI Hardware Accelerators for Low-Latency Transformer-Based Language Models (Invited)
2025· 1 cited
Energy‐Efficient Hardware Implementation of Spiking‐Restricted Boltzmann Machines Using Pseudo‐Synaptic Sampling
Advanced Intelligent Systems·2024· 1 citedOpen Access
Solving Max‐Cut Problem Using Spiking Boltzmann Machine Based on Neuromorphic Hardware with Phase Change Memory
Advanced Science·2024· 5 citedOpen Access
(Invited) Emerging Nonvolatile Memories for Analog Neuromorphic Computing
ECS Meeting Abstracts·2024· 1 cited
Design of Analog-AI Hardware Accelerators for Transformer-based Language Models (Invited)
2023· 7 cited
An analog-AI chip for energy-efficient speech recognition and transcription
Nature·2023· 185 citedOpen Access
Phase Change Memory-based Hardware Accelerators for Deep Neural Networks (invited)
2023· 2 cited
Architectures and Circuits for Analog-memory-based Hardware Accelerators for Deep Neural Networks (Invited)
2023· 1 cited
Analog-AI: Hardware Acceleration for Deep Neural Network Inference
2023
Analog-memory-based 14nm Hardware Accelerator for Dense Deep Neural Networks including Transformers
2022 IEEE International Symposium on Circuits and Systems (ISCAS)·2022· 6 cited
Pattern Training, Inference, and Regeneration Demonstration Using On‐Chip Trainable Neuromorphic Chips for Spiking Restricted Boltzmann Machine
Advanced Intelligent Systems·2022· 9 citedOpen Access
Fully On-Chip MAC at 14 nm Enabled by Accurate Row-Wise Programming of PCM-Based Weights and Parallel Vector-Transport in Duration-Format
IEEE Transactions on Electron Devices·2021· 9 citedOpen Access
Neural Network VLSI using Non-Volatile Memory Devices
The Japan Society of Applied Physics·2021
On-Chip Trainable 1.4M 6T2R PCM Synaptic Array with 1.6K Stochastic LIF Neurons for Spiking RBM
2019· 38 cited
Analysis of Effect of Weight Variation on SNN Chip with PCM-Refresh Method
Neural Processing Letters·2019· 4 cited
VLSI Researches for Machine Learning and Neuromorphic Computing
2019· 4 cited
Performance Analysis of Spiking RBM with Measurement-Based Phase Change Memory Model
Communications in computer and information science·2019· 1 cited
page 1 of 2Next →

Frequent Co-authors

Kohji Hosokawa(21), Masatoshi Ishii(19), Akiyo Nomura(16), Pritish Narayanan(12), Charles Mackin(12), Alexander Friz(12), Hsinyu Tsai(12), Geoffrey W. Burr(12), Stefano Ambrogio(10), Jose Luquin(10), Andrea Fasoli(9), Yasuteru Kohda(9), Sang‐Bum Kim(9), Megumi Ito(9), Vijay Narayanan(8), Takeo Yasuda(7), Wilfried Haensch(7), Malte J. Rasch(7), Junka Okazawa(6), Y. Katayama(6)