Thai-Hoang Nguyen

Ph.D in Computer Engineering

Memory Business, Samsung Electronics

Welcome!!!

Welcome to my page! I am currently a researcher at Memory Business, Samsung Electronics. My job/research interests include:

• Development of AI/Machine Learning (AI/ML)-assisted design automation software.
• Developing methodologies for memory design, with a focus on non-volatile memory systems.
• Enhancing the robustness of non-volatile memory-based systems, including work on conventional computer systems, non-von Neumann architectures, and deep neural network accelerators.

Beyond my research, I am passionate about DIY projects. In my free time, I enjoy designing electronic circuits, building robots, developing mobile apps and websites, and writing blogs.

Feel free to contact me about my research or for any inquiries. You can reach me at here.

Recent Blog Posts

How to run LLM model locally using only Macbook Air M1/M2

Harnessing the Power of AI: Setting Up a Large Language Model Locally on Your MacBook Air with Ollama

Posted Sep 21, 2024 5 min read AI, LLM

Publications

For a complete and up-to-date list of publications, check out my Google Scholar.

Thai-Hoang Nguyen, Muhammad Imran, Jaehyuk Choi, Joon-Sung Yang (2023). HYDRA: A Hybrid Resistance Drift Resilient Architecture for Phase Change Memory-Based Neural Network Accelerators. IEEE Transactions on Computers (Accepted).

Cite

Je-Woo Jang, Thai-Hoang Nguyen, Joon-Sung Yang (2023). VECOM: Variation-Resilient Encoding and Offset Compensation Schemes for Reliable ReRAM-Based DNN Accelerator. Proceedings of the 42nd IEEE/ACM International Conference on Computer-Aided Design (ICCAD) (Accepted).

Cite

Thai-Hoang Nguyen, Joon-Sung Yang (2023). Enhancing the Robustness of eNVMs-Based DNNs using Low-Cost and Efficient Hardware. 2023 60th ACM/IEEE Design Automation Conference (DAC-Ph.D Forum).

Cite Poster URL

Thai-Hoang Nguyen, Muhammad Imran, Jaehyuk Choi, Joon-Sung Yang (2023). CRAFT: Criticality-Aware Fault-Tolerance Enhancement Techniques for Emerging Memories-Based Deep Neural Networks. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (Accepted).

Cite DOI Preprint

See all publications

Experience

 

 

 

 

 

BS in Electrical Engineering

Danang University of Science and Technology

Feb 2014 – Feb 2019 Danang, Vietnam

 

 

 

 

 

Combined MS-PhD in Electrical and Computer Engineering

Sungkyunkwan Univerisity

Mar 2019 – Aug 2023 Suwon, South Korea

 

 

 

 

 

Post-doctoral Researcher

Yonsei University

Aug 2023 – Jan 2024 Seoul, South Korea

 

 

 

 

 

Researcher

Memory Business, Samsung Electronics

Jan 2024 – Present Hwaseong, South Korea

Skills

Python

Numpy | Matplotlib | Data Analysis

Deep Learning / Machine Learning Frameworks

Pytorch | TensorFlow | Keras

Digital VLSI design

Verilog | C/C++ | Testing & Verification

Emerging Non-volatile Memory

Reliability | Processing-In Memory

Academic Writing / Reviewing

Latex | Microsoft Office

Qualitative Methods

Thematic analysis | Grounded theory

Contact

• th.nguyen@yonsei.ac.kr
• 1-1 Samsungjeonja-ro, Hwaseong-si, Gyeonggi-do, Hwaseong, South Korea