[Research Highlights]                                     [Research Focus]                                  [Publications]       

Development of intelligent systems and discovering mechanisms for intelligent behavior is one of the most exciting research areas in science and engineering. With the recent development of brain research and modern technologies, scientists and engineers will hopefully find efficient ways to build brain-like complex systems that are highly robust, adaptive, and fault tolerant to uncertain environments. However, although scientists and engineers have successfully borrowed some ideas from biological intelligent systems, for instance, the designing of the insect-inspired robots, there is still no clear picture about how to design the truly brain-like general-purpose intelligent machines. The biggest challenge comes from how to develop the general models, algorithms, architectures, and organizations that are able to adaptively learn and accumulate knowledge, make predictions in an uncertain and unstructured environment, and adjust actions to maximize some kind of utility function over time to achieve goals (goal-oriented behaviors). Toward this long-term objective, our group mainly focused on the following three aspects of research (A list of recent publications can be accessed here.):


Theory: Understanding the Fundamental Principles of Brain-Like Intelligence

To address the fundamental issues of brain-like intelligence research, we are particularly interested in: 

Adaptive/Approximate dynamic programming;
Bio-inspired learning mechanisms;
Hierarchical organization for learning, memory and prediction;
Embodied intelligence;
Value systems and goal-driven learning;
Self-organizing associative memory architecture;

Design: Advanced Intelligent Systems Prototyping, Design, and Testing

To address the critical hardware design challenges for machine intelligence, we are particularly interested in:

Massively parallel processing structure;
Hardware-oriented intelligent architecture;
FPGA based intelligent systems design;
VLSI design of intelligent modules;
System-level prototype and testing
Software/hardware co-design and simulation;


To bring the computational intelligence closer to real-world complex applications, we are particularly interested in:

Smart grid;
Cyber-physical systems;
Biomedical engineering applications;
Sensor networks;
Cognitive communication networks;
Financial data modeling and analysis;