Self-adaptive Learning for Knowledge Discovery and Machine Intelligence

Dr. Haibo He, Assistant Professor
Stevens Institute of Technology


Abstract

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, and fault tolerant to uncertain and unstructured environments. Yet, building such complex intelligent systems requires serious research on both the fundamental theoretical understanding as well as engineering design. Furthermore, with the continuous expansion of data availability in many large-scale and networked systems, such as Internet, security, multimedia applications, and sensor networks, it becomes critical to advance the fundamental understanding of information representation and knowledge discovery from raw data to support the decision-making processes. To this end, this talk aims to present the latest research developments in the area of machine intelligence research to advance the development of self-adaptive intelligent systems and explore their wide applications across different domains. The major focus of this talk is to introduce an integrative framework for “human learning” and “machine learning”. Specifically, this talk covers numerous aspects of models, architectures and algorithms targeting for knowledge discovery and machine intelligence, including adaptive incremental learning principle, self-organizing network, biologically inspired associative memory and anticipation mechanism. Future research directions and challenges in this field will also be discussed.