Introduction



CNSL has been jointly listed at the School of Electrical Engineering and Brain Science Research Center.


  • Dual Goals
    • Understanding brain information processing mechanism for auditory, vision, cognition, and behavior 
    • Developing brain-like intelligent systems (Artificial Brain and Artificial Cognitive Systems) 

  • Research Areas

   The main research areas reside in computational models of brain information processing mechanism and their applications to build human-like intelligent systems, i.e., AI, Artificial Brain, or Artificial Cognitive Systems (ACS). These functional models are based on information theory and inspired by findings in cognitive science. Intelligent robots with human-like cognitive functions are examples of ACSs, which improve their functional ability by learning from users and other ACSs.

   Although human-like perception has been regarded as the main achievements on the laboratory, recently the research topics extends further into the higher cognitive functions including knowledge, attention, emotion, situation awareness, decision making, and human behavior. Based on EEG and/or eye-movements it also works on a new field to classify human internal states, such as sympathy, trustworthiness, and memory, for understanding what the people think and who the people is. It also collaborate with American-based NeuroSky Inc. 


  • Main Achievements
    • Architecture and learning algorithm for neural networks, aka machine learning (deep learning)
    • Auditory models for speech feature extraction, sound localization and blind signal separation
    • Top-down selective attention model for robust recognition (How people see what they wants to see?)
    • Multi-modal fusion based on the top-down attention (i.e., audio-visual integration for lip-reading)
    • Feature extraction, selection and adaptation for image, text, emotional speeches, music, and EEG
    • Neuromorphic chips and boards based on the developed models
    • ABrain (Artificial Brain) and OfficeMate (Artificial Secretary) as a testbed of human-like intelligent systems


  • On-Going Research Projects 
  1. Deep Learning for Korean Language and Knowledge Development (2015-2018)
    • Developments of deep/recurrent neural architectures and learning algorithms for Korean language
    • Word/sentence/document representations, synonym suggestion, automatic sentence completion/suggestion, semantic document search, and document summarization
    • Towards artificial intelligence with human-like learning and generalization capabilities
  2. Understanding Human Internal States (Mind): I Know What You Think (2010-2018)
    • Measurements of human internal states, i.e., MIND, by fMRI and/or EEG (Agreement/Disagreement to others, Trustworthiness of others)
    • Utilizing human internal states for new Human-Computer Interface
    • Effects of human-like cues (such as facial expression) to human trust with machine
  3. Brain-based User Authentication: I Know Who You Are (2013-2018)
    • User authentication (verification) and identification based on personal memory and intention  (People may be identified by his/her memory.)
    • Absolutely-safe from rubber hose attack
  4. Situation Awareness (2014-2017)
    • Situation awareness based on environmental sound