Creating innovative bio-convergent technologies for better human life

연사 박덕근 교수 
소속 Computer Science, University of Texas at Arlington 
일시 2022년 6월 22일 (수) 11:00am~12:00pm 
장소 정문술 빌딩 201호 

신경과학-인공지능 융합 연구센터(센터장: 이상완 교수님) 세미나가 열림을 알려 드립니다. 

 

- 일시: 6월 22일 수요일 11-12시

- 장소: 정문술 빌딩 201호

- 제목: Cognitive Architecture for Operant Conditioning

- 연사: Prof. Deokgun Park (Computer Science, The University of Texas at Arlington)

- 초록:

In this talk, I will present my research on cognitive architecture for operant conditioning. To lay the foundation for the discussion, I will start by reviewing the definitions and tests for AI and propose a new definition and the test for human-level artificial intelligence (HLAI). I claim that the essence of HLAI is the capability to learn from others' experiences via language. Based on the definition, a test based on the language acquisition task will be proposed with the simulated environment to run the test practically. The next milestone toward programming HLAI would be enabling operant conditioning inspired by the ‘Skinner box’ experiment. To achieve this goal, I will explain two lessons that we can learn from the biological brain. First, the working principle of the neocortex can be modeled as Modulated Heterarchical Prediction Memory (mHPM). In mHPM, autoregressive universal modules in sparse distributed memory (SDM) representations are connected in a heterarchical network and updated in a local and distributed way instead of the current deep learning trend of end-to-end optimization based on the single objective function. The second lesson is that we need a non-homogeneous cognitive architecture for innate and learned behaviors instead of the current homogeneous architecture. I will explain the role of innate components such as the hippocampus, reward system, hypothalamus, and amygdala.

- 약력:

Dr. Deokgun Park is an assistant professor in the Computer Science and Engineering Department at the University of Texas at Arlington (UTA). He leads the Human Data Interaction Lab at UTA, which studies Human-Level Artificial Intelligence. Dr. Park earned his doctoral degree from the University of Maryland in 2018. He completed his M.S. in Interdisciplinary Engineering at Purdue University and M.S. in Biomedical Engineering at Seoul National University, where he also obtained a B.S. degree in Electrical Engineering. He worked at the Government and industry research labs, and startups. And his patents have been licensed to companies, including Samsung Electronics.