Prof. Sheng-Uei Guan
Xi'an Jiaotong-Liverpool University, China
Steven Guan received his BSc. from Tsinghua University and M.Sc. (1987) & Ph.D. from the University of North
Carolina at Chapel Hill. He is currently a Professor at Xi'an Jiaotong-Liverpool University (XJTLU) and Honorary
Professor at University of Liverpool. He served the head of department position at XJTLU for 4.5 years, creating the
department from scratch and now in shape. Before joining XJTLU, he was a tenured professor and chair in intelligent
systems at Brunel University, UK.
Prof. Guan has worked in a prestigious R&D organization for several years, serving as a design engineer, project leader,
and department manager. After leaving the industry, he joined the academia for three and half years. He served as deputy
director for the Computing Center and the chairman for the Department of Information & Communication Technology.
Later he joined the Electrical & Computer Engineering Department at National University of Singapore as an associate
professor for 8 years.
Prof. Guan’s research interests include: machine learning, computational intelligence, big data analytics, mobile
commerce, modeling, networking, personalization, security, and pseudorandom number generation. He has published
extensively in these areas, with 140+ journal papers and 200+ book chapters or conference papers. He has chaired,
delivered keynote speech for 100+ international conferences and served in 180+ international conference committees and
20+ editorial boards. There are quite a few inventions from Prof. Guan including Generalized Minimum Distance
Decoding for Majority Logic Decodable Codes, Prioritized Petri Nets, Self-Modifiable Color Petri Nets, Dynamic Petri
Net Model for Iterative and Interactive Distributed Multimedia Presentation, Incremental Feature Learning, Ordered
Incremental Input/Output Feature Learning, Input/Output Space Partitioning for Machine Learning, Recursive
Supervised Learning, Reduced Pattern Training using Pattern Distributor, Contribution Based Feature Selection,
Incremental Genetic Algorithms, Incremental Multi-Objective Genetic Algorithms, Decremental Multi-objective
Optimization, Multi-objective Optimization with Objective Replacement, Incremental Hyperplane Partitioning for
Classification, Incremental Hyper-sphere Partitioning for Classification, Controllable Cellular Automata for
Pseudorandom Number Generation, Self Programmable Cellular Automata, Configurable Cellular Automata, Layered
Cellular Automata, Transformation Sequencing of Cellular Automata for Pseudorandom Number Generation, Open
Communication with Self-Modifying Protocols, etc.
Input Space Partitioning for Machine Learning
This talk introduces an input attribute grouping method to improve the performance of learning. During training for a specific problem, the input attributes are partitioned into groups according to the degree of inter-attribute promotion or correlation that quantifies the supportive or negative interactions between attributes. After partitioning, multiple sub-networks are trained by taking each group of attributes as their respective inputs. The final classification result is obtained by integrating the results from each sub-network. Experimental results on several UCI datasets demonstrate the effectiveness of the proposed method.