최정욱 > 교수진 | IoT시스템반도체융합인력육성센터

최정욱 | 인공지능 알고리즘 및 하드웨어

학력 Education

2010 - 2015 : Ph.D. at Electrical and Computer Engineering, University of Illinois at Urbana-Champaign (Advisor: Prof. Rob A. Rutenbar)
2008 - 2010 : M.S. at Electrical and Computer Engineering, Seoul National University (Advisor: Prof. Wonyong Sung)
2002 - 2008 : B.S. at Electrical Engineering, Seoul National University

약력/경력 Experience

2019 - Present : Assistant Professor at Department of Electronic Engineering, Hanyang University, Seoul, South Korea.
2015 - 2019 : Research Staff Member at IBM TJ Watson Research Center, Yorktown Heights, NY, US.

관심분야 Research Interest

Compute-efficient deep learning training and inference algorithms (Quantization and Pruning)
High performance and low power neural processor architecture design and implementation
Deep learning performance analysis and dataflow/data-reuse optimization software
Robust deep learning algorithms for in-memory computing (ReRAM and PCRAM)

논문 Journal Article

N. Wang, J. Choi, D. Brand, C. Chen, K. Gopalakrishnan, “Training Deep Neural Networks with 8-bit Floating Point Numbers,”
Conference on Neural Information Processing Systems (NeurIPS), Montréal, Québec, Canada, Dec 2018
J. Choi, S. Venkataramani, V. Srinivasan, K. Gopalakrishnan, Z. Wang, P. Chuang, “Accurate and Efficient 2-Bit Quantized Neural Networks,”
Conference on Systems and Machine Learning (MLSys), Stanford, CA, Mar 2019.
Fleischer, et al., “A Scalable Multi-TeraOPS Deep Learning Processor Core for AI Training and Inference,”
IEEE Symposia on VLSI Technology and Circuits (VLSI), Honolulu, HI, June 18-22, 2018.

연구실 이름 Laboratory Name

연구분야 Field of Research