How does the biological mind work? How does the brain build a model of the world to instantly and robustly act on it? What kinds of processing and organizational mechanisms allow the brain to learn so rapidly, flexibly, and continuously in a noisy, dynamic, and changing environment? How can we build smart machines that perceive, think, act, and learn like the human brain and mind? In the Biointelligence Lab and the Cognitive Robotics and ArtificialIntelligence Center (CRAIC) we pursue these questions using diverse methods of cognitive modeling, computational neuroscience, robotics, and computer science.
We build robotic surrogates by “cloning” the embodied and situated mind using wearable sensors, such as smart glasses, watches, brain scanners, body sensors, and mobile devices. We collect human activity data by long-term life-tracking in the real world. Based on these observational data, we reverse-engineer the brain architecture by exploring the plausible neurocognitive models that best explain the mind in working. We also use videos and cartoons to study how the cognitive brain constructs episodic memory and mental imagery from a long sequence of context-rich events while watching dramas and movies.
Our current efforts center around the deep, recurrent, and sparse hypernetwork architectures and learning algorithms that self-organize their structures instantly, incrementally, and continuously in a self-supervised way by perception-action cycle. The ultimate goal is to discover a large-scale, neurocognitive computational model of the brain that autonomously develops or evolves into human-level machine intelligence in lifelong interactions with the environment.
🎓 Education
- 1992: PhD in Computer Science (Informatik), University of Bonn, Germany
- 1988: MS in Computer Science & Engineering, Seoul National University
- 1986: BS in Computer Science & Engineering, Seoul National University
🧑🏫 Current Position
- POSCO Chair Professor of Computer Science
- Director, SNU AI Institute (AIIS)
- Professor, Computer Science and Engineering, SNU (since 1997)
- Director, Video Intelligence Center (VIC) (2017–Present)
📞 Contact
Office
Room 303-453 (해동첨단공학관)
School of Computer Science and Engineering, Seoul National University
Seoul 151-744, Korea
Phone
+82-2-880-1833 (office)
+82-2-880-1847 (secretary)
Fax
+82-2-875-2240
Email
btzhang@bi.snu.ac.kr
Selected Talks and Tutorials
International
- Cognitive AI, 2019 Nanjing Forum, November 23, 2019
- Empowering Cognitive AI Robots with Deep Learning, CJK Forum at CNCC 2019, October 18, 2019
- Video Turing Test: A Challenge for Human-Level AI, AIRC International Symposium, February 22, 2019
- Teaching Robots to See, Hear, Talk & Act Like Humans Using Videos, AIST Artificial Intelligence Research Center, February 13, 2018
- Cognitive AI: Beyond Symbolism and Connectionism Toward Human-Level Intelligence, Max Planck Haus, Tuebingen, January 19, 2018
- Cloning Humans to Build Personal AI Robots, AIST, Tokyo, February 25, 2016
- Deep Learning for the Web, tutorial at WWW 2015, May 18, 2015
- Bio-Inspired Human Level Machine Learning, AFOSR program review, November 2014
- Learning with Hypernetworks, German-Korean Workshop on Machine Learning in Life Sciences, August 2007
- Molecular Evolutionary Computation in vitro and in silico, DNA Computing 13, June 2007
Domestic
- 실세계 인공지능, 기술경영인 하계포럼, July 12, 2019
- 차세대 AI 기술 및 국내외 기술동향, AI사업단워크샵, July 9, 2019
- 인공지능의 현재와 미래, 진대제 AMP, June 25, 2019
- Deep learning AI for Autonomous Robots, Hyundai Motor seminar, November 20, 2018
- AI 3.0: From Virtual to Real, Global AI Summit 2018, June 12, 2018
- 인지로봇 인공지능 기술, Samsung SDS technical seminar, April 25, 2018
- Challenges in Machine Learning, AI Korea 2017, November 15, 2017
- Powering AI Robots with Deep Learning, NVIDIA Deep Learning Day, October 31, 2017
- Deep Learning Theories of Cognitive Brain, Korean Cognitive Science Society BRIDGE school, October 14, 2017
- Robots with Free Will, joint symposium of the Korean Cognitive Science Society and Philosophy Research Society, April 29, 2017