Bio-inspired Human-Level Machine Learning

˘Ć Abstract ˘Ć

How can brain computation be so fast, flexible, and robust? What kinds of representational and organizational principles facilitate the biological brain to learn so efficiently and flexibly on the sub-second time scale and so reliably on the continuous lifetime scale? Understanding these principles and constructing computational models that implement these principles in a natural way will achieve scientific breakthroughs in computational architectures and algorithms that enable true human-level robust intelligence. In this project, we aim to develop bio-inspired machine learning technology that is competitive to human learning in its performance (speed, flexibility, reliability, robustness) and style (online, incremental, predictive, self-teaching). We construct a ˇ°human-likeˇ± machine learning model based on dynamic ˇ°neuralˇ± populations (neural assemblies) and implement this model in ˇ°molecularˇ± populations (molecular assemblies) using in vitro DNA computing. We validate the molecular machine learning model on simulating high-level ˇ°cognitiveˇ± information processing involving language, vision, and decision-making. The proposed project can innovate the existing knowledge and technology in computational intelligence, cognitive science, and engineering. The notion of bio-inspired human-level machine learning combined with molecular-computing implementation based on population coding and dynamic coordination, offers an interesting, novel paradigm to address the flexible and reliable computing. In particular, the dynamic molecular assembly model of cognitive memory and learning will provide a new tool to simulate dynamical cognitive systems.

 

˘Ć Overall Concept  ˘Ć

 

structure


˘Ć Publications ˘Ć

  • Zhang, B.-T. (2013). Communication as moving target tracking: Dynamic Bayesian inference with an action-perception-learning cycle, In: Wachsmuth, I. et al. (Eds.), Alignment in Communication: Towards a New Theory of Communication, Chapter 7, Simon & Shuster, 2013 [PDF]
  • Zhang, B.-T. (2013). Information-theoretic objective functions for lifelong learning, AAAI 2013 Spring Symposium on Lifelong Machine Learning, March 25-27, Stanford University, AAAI Press. [PDF]
  • Zhang, B.-T. (2012). Higher-order predictive information for learning an infinite stream of episodes, NIPS Workshop, Lake Tahoe [PDF]
  • Lee, J.-H., Lee, E.S., Ryu, J.-H., Chun, H.-S., Zhang, B.-T. (2013). Molecular computational simulation of cognitive processes for anagram solving, The 19th International Conference on DNA Computing and Molecular Programming (DNA19), Phoenix, poster presentation. [PDF]
  • Ryu, J.-H., Lee, J.-H., & Zhang, B.-T. (2013). Integrated encoding of semantic and orthographic distances in a DNA language model, The 19th International Conference on DNA Computing and Molecular Programming (DNA19), Phoenix, poster presentation. [PDF]
  • Lim, H.-W., Lee, S. H., Yang, K.-A., Yoo, S.-I., Park, T. H., & Zhang, B.-T. (2013). Biomolecular computation with molecular beacons for quantitative analysis of target nucleic acids, BioSystems, 111:11-17. [PDF]
  • Lee, I.-H., Lee, S.H., Park, T.H., & Zhang, B.-T. (2013). Non-linear molecular pattern classification using molecular beacons with multiple targets, BioSystems, 114(3):206-213. [PDF]
  • Lee, B. J., Ha, J. W., Kim, K. M., Zhang, B. T. (2013). Evolutionary concept learning from cartoon videos by multimodal hypernetworks, IEEE Congress on Evolutionary Computation (CEC 2013), pp. 1186-1192. [PDF]

Project Title Bio-Inspired Human-Level Machine Learning
Duration Sep 2012 - Sep 2015
Funding Air Force Research Laboratory
Principal Investigator Prof. Byoung-Tak Zhang
Researchers Ji-Hoon Lee
Je-Hwan Ryu
Hyo-Sun Chun
Christina Baek
Sang-Woo Lee

Contact Prof. Byoung-Tak Zhang
E-Mail btzhang@snu.ac.kr
Phone +82-2-880-1847
Fax +82-2-875-2240