Instructors/Speakers Prof. Guang-Bin HUANG Nanyang Technological University Singapore Abstract This talk will analyse the differences and relationships among artificial intelligence and machine learning, and also advocates the intelligence revolution and show its potential impact will be much more influential than agriculture revolution and industrial revolution. ELM theories may have explained the reasons why the brains are globally ordered but may be locally random. This talk will share with audience ELM’s direct biological evidences. Finally this talk will share with audiences the trends of machine learning in which ELM may play some important roles: 1) convergence of machine learning and biological learning; 2) from human and (living) thing intelligence to machine intelligence; 3) from cloud intelligence to local intelligence; 4) from ...

Instructors/Speakers Prof. Raymond Chi-Wing WONG The Hong Kong University of Science and Technology Abstract Nowadays, location-based services (LBSs), which refer to those services that are based on location (or spatial) data, are broadly used in our daily life. In this talk, we will talk about the recent development of LBSs. Some examples are "Search-nearby", "Spatial Crowdsourcing", "Trace Tracking" and "Shortest Distance". We will focus on presenting some important results about shortest distance queries, one fundamental LBS, in the new context of the three-dimensional spatial database which receives a lot of attention from both the academic community and the industry community like Microsoft’s Bing Maps and Google Earth. Biography Raymond Chi-Wing Wong is an Associate Professor in Computer Science and Engineering ...

Instructors/Speakers Prof. Man Lung YIU The Hong Kong Polytechnic University Abstract In rank-aware processing, user preferences are typically represented by a numeric weight per data attribute, collectively forming a weight vector. The score of an option (data record) is defined as the weighted sum of its individual attributes. The highest-scoring options across a set of alternatives (dataset) are shortlisted for the user as the recommended ones. In that setting, the user input is a vector (equivalently, a point) in a d-dimensional preference space, where d is the number of data attributes. In this work, we study the problem of determining in which regions of the preference space the weight vector should lie so that a given option focal record is ...

Instructors/Speakers Prof. Luonan CHEN Professor CAS Key Laboratory of System Biology Institute of Biochemistry and Cell Biology Shanghai Institutes for Biological Sciences, CAS, Shanghai China Abstract Considerable evidence suggests that during the progression of complex diseases, the deteriorations are not necessarily smooth but are abrupt, and may cause a critical transition from one state to another at a tipping point. Here, we develop a model-free method to detect early-warning signals of such critical transitions (or un-occurred diseases), even with only a small number of samples. Specifically, we theoretically derive an index based on a dynamical network biomarker (DNB) that serves as a general early-warning signal indicating an imminent sudden deterioration before the critical transition occurs. Based on theoretical analyses, we ...