People

Who we are



Kangil Kim | Professor

Assistant Professor,
School of Electrical Engineering & Computer Science,
Gwangju Institute of Science and Technology(GIST)

email: kangil.kim.01[at]gmail[dot]com / kikim01[at]gist[dot]ac[dot]kr

Research Interest

I am interested in generally or widely applicable intelligence model representation, optimization and regularization, model complexity, probabilistic and geometric analysis.

Research Area (keyword)

artificial intelligence, machine learning, evolutionary computation, neural network, probabilistic graphical model, statistical relation learning, logic and grammar model, genetic programming, natural language processing

Education

2012 Ph.D in Computer Science and Engineering, SNU
2006 B.S. in Computer Science, KAIST

Experience

2019~present Assistant Professor, GIST, EECS & AI Graduate School
2016~2019 Assistant Professor, KU, CSE
2013~2016 Senior Researcher, ETRI, AI and NLP
2012~2013 Postdoc Researcher, SNU, Structural Complexity Lab
2011 Visiting Researcher, UPM, Artificial Intelligence Group
2008 Research Intern, NII

Publications

links: google scholar, research gate

Project (led or deeply involved)

  • Explicit knowledge representation interacting with general neural networks (GIST)
  • Analysis of impact of subcost random switching in neural networks (KU)
  • Analysis of temporal sensitivity of regularization for recurrent neural network with long-short term memory (KU)
  • Error condition detection for 3D-printing using deep feedfowrad network (KU)
  • Stability analysis of recurrent neural networks for long term forecasting in environmental problems (KU)
  • Geometric analysis for neural network regularization (KU)
  • Recurrent neural networks with long-short term memory for machine translation (ETRI)
  • Neural networks for syntax analysis (ETRI)
  • Statistical modeling for machine translation (ETRI)
  • Large-size modeling to predict water quality using genetic programming (SNU)
  • Probabilistic bias analysis of formal grammar models in estimation of distribution algorithm in genetic programming (SNU)
  • Probabilistic bias analysis of structured graphical models in estimation of distribution algorithm in genetic programming (SNU)
  • Search optimal graph structure (NII)

Referee Service

IEEE Transactions on Evolutionary Computation
IEEE Transactions on Neural Network and Learning Systems
IEEE Transactions on Audio, Speech and Language Processing
Expert Systems With Applications
EMNLP 2021

Acronyms

GIST (Gwangju Institute of Science and Technology, Korea)
ETRI (Electronics and Telecommunications Research Institute, Korea)
UPM (Polytechnic University of Madrid, Spain)
SNU (Seoul National University, Korea)
NII (National Institute of Informatics, Japan)