Adaptive Learning and Optimization for MI: From the Foundations to Complex Systems - Haibo He - WCCI 2016

With the recent development of brain research and modern technologies, scientists and engineers will hopefully find efficient ways to develop brain-like intelligent systems that are highly robust, adaptive, scalable, and fault tolerant to uncertain and unstructured environments. Yet, developing such truly intelligent systems requires significant research on both fundamental understanding of brain intelligence as well as complex engineering design. This talk aims to present the recent research developments in computational intelligence to advance the machine intelligence research and explore their wide applications in complex cyber physical systems across different domains.
Specifically, this talk will focus on a new adaptive dynamic programing (ADP) framework with rich internal goal representation for improved learning and optimization capability over time. This architecture integrates an internal goal generator network to provide a more informative and detailed internal value representation to support the decision-making process. Compared to the existing ADP approaches with a manual or �hand- crafted� reinforcement signal design, our approach can automatically and adaptively develop the internal reinforcement signal over time, therefore improving the learning and control performance. This internal goal network can also be designed in a hierarchical way, to provide a multi-level value representation. Under this ADP framework, I will present numerous applications including smart grid and human-robot interaction, to demonstrate its broader and far-reaching applications.