This page just summarizes my records in the graduate school. To see my full records, come to my website, www.sungjaecho.info
SUNGJAE CHO / 조성재
BASIC INFORMATION
RESEARCH INTERESTS
  • Connectionist models (PDP models): deep learning, neural information processing
  • Cognitive science: computational models of cognitive processes. I want to understand how the brain works on an algorithmic level.
  • Language models for machine learning
  • Learning inference and knowledge structures
COURSEWORKS

2017-2 [Timetable]

  • Seminar in Cognitive Science (Industrial and Applied Artificial Intelligence) taught by Euijoong Kim (Founder of aidentify), hosted by Je-Kwang Ryu [Syllabus][Evernote]
    • Basic machine learning ideas, one term project
  • Computational Neuroscience (Self-learning Neural Algorithms) by Byoung-Tak Zhang [Syllabus][CourseHome]
  • Deep Learning by Sungroh Yoon [Syllabus]
    • machie learning, CNN, RNN(LSTM), RL(DQN), gernerative models(VAE, GAN)

2018-1

2018-2

  • Seminar in Computational Linguistics (Natural Language Processing using Reinforcement Learning) by Youngsam Kim [Syllabus]
  • Methodology in Cognitive Science by Hong-Gee Kim [Syllabus]
  • Seminar in Methodology on Experimental Psychology (Fundamentals and Applications of Cognitive Modeling) by Sungryong Koh [Syllabus]
  • Reading and Research by Hong-Gee Kim

2019-winter

  • Introduction to Psychology by Sooan Kim [Syllabus]

2019-1

  • Seminar in Experimental Psychology (Dynamics and Cognitive Models) by Sungryong Koh [Syllabus]
  • Dissertation Research by Byoung-Tak Zhang

LAB ROLES
  • Maintaining the front page of BI homepage, Dec. 2017 ~ present
  • Maintaining BI publications page, Aug. 2017 ~ present
  • Managing BI lab participation in the CSE athletic legue 2017
TALKS
  1. Overview on Grounded Language Learning. Korean-German Symposium on Cognitive Robotics in Smart Environments. 2018-01-26. [slides] [symposium]
LAB SEMINAR NOTES
  1. Self-Introduction. 2017-09-29. [PDF]
  2. The Mind's Two Faces. 2017-12-28. [poster] [QA]
  3. Deep Learning for Dialogue Systems: ACL Tutorial. 2018-03-23. [slides]
  4. Chapter 8. Observations of Cortical Mechanisms for Object Recognition and Learning. Large-Scale Neuronal Theories of the Brain. by Christof Koch and Joel L. Davis. 2018-07-26.
  5. Neural Networks for Binary Addition (and Their Internal Process). 2018-08-16. [slides]
  6. Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents. 2019-01-04. [slides] [poster]
  7. Chapter 8. The Multiple Timescales of Memory. Biological Learning and Control (Shadmehr and Mussa-Ivaldi). 2019-01-11.
  8. Problem Difficulty in Arithmetic Cognition: Humans and Connectionist Models. 2019-02-15. [slides]
  9. Inference and estimation in probabilistic time series model (Part 1). 2019-04-30. [slides]
  10. Simulating Problem Difficulty in Arithmetic Cognition Through Dynamic Connectionist Models + Cognitive Modeling. 2019-06-07. [slides]
  11. Modeling Number Sense Acquisition in a Number Board Game by Coordinating Verbal, Visual, and Grounded Action Components. 2019-08-14. [slides]
PUBLICATIONS
  • Simulating problem difficulty in arithmetic cognition through dynamic connectionist models, Sungjae Cho, Jaeseo Lim, Chris Hickey, Jung Ae Park, and Byoung-Tak Zhang, In Proceedings of the 17th International Conference on Cognitive Modeling (ICCM 2019), 2019. [PDF]
  • Problem difficulty in arithmetic cognition: Humans and connectionist models, Sungjae Cho, Jaeseo Lim, Chris Hickey, and Byoung-Tak Zhang, In Proceedings of the 41st Annual Meeting of the Cognitive Science Society (CogSci 2019), pp. 1506-1512, 2019. [PDF]
  • VTT: 비디오 스토리 이해 연구를 위한 비디오 튜링 테스트 데이터셋, 최성호, 조성재, 김진화, 김진아, 장병탁, 2017년 한국소프트웨어종합학술대회 논문집 (KSC2017), pp. 895-897, 2017.12. [PDF]
Last updated in Sep. 12, 2019