Ming Shao, PhD

Assistant Professor

Computer & Information Science

508-910-6893

ntibpAvnbtte/fev

Dion 303A


Education

2016Northeastern UniversityPhD in Electrical and Computer Engineering
2010Beihang UniversityME in Computer Science
2007Beihang UniversityBS in Applied Mathematics
2006Beihang UniversityBE in Computer Science

Teaching

Programs

Teaching

Courses

Models of sequential, parallel, and distributed computations. The Chomsky hierarchy of formal languages and their accepting machines are studied in detail. The relationship of these languages and machines to computer programs is presented. Influence of a Turing machine and related formalisms on modern computing are studied. Decidability of decision problems is explained. Several models of parallel and distributed computations are introduced and compared.

Models of sequential, parallel, and distributed computations. The Chomsky hierarchy of formal languages and their accepting machines are studied in detail. The relationship of these languages and machines to computer programs is presented. Influence of a Turing machine and related formalisms on modern computing are studied. Decidability of decision problems is explained. Several models of parallel and distributed computations are introduced and compared.

Theory and principles for constructing usable software systems. Cognitive and effective aspects of users. The impact of user characteristics on design decisions. The construction and evaluation of the user interface. Sensory and perceptual aspects of interfaces, task structure, input modalities, screen layout, and user documentation. Individual concerns for systems such as personal productivity tools, real-time control systems, instructional software, and games.

Foundations of computer vision. Image formats, projection models, regions, filters, edge detection, segmentation, shape description and representation, object recognition and understanding, and stereo-vision are discussed.

Foundations of computer vision. Image formats, projection models, regions, filters, edge detection, segmentation, shape description and representation, object recognition and understanding, and stereo-vision are discussed.

Coverage of advanced topics of data mining and its applications. The course will review related mathematics and then focus on data mining core algorithms and advanced modeling including regression, dimensionality reduction, support vector machines, clustering, graph theory, and frequent pattern mining. The course will also explore several real-world problems and discuss strategies for large-scale data.

Advanced coverage of machine learning algorithms and applications to computer vision, data mining and social media. Specifically, the course focuses on data pre-processing, feature extraction, supervised/unsupervised learning, graphical model, deep learning, and other advanced machine learning topics. The course will also explore several real-world problems, e.g., visual detection/recognition, topics discovery, social media analytics using machine learning approaches.

Advanced coverage of machine learning algorithms and applications to computer vision, data mining and social media. Specifically, the course focuses on data pre-processing, feature extraction, supervised/unsupervised learning, graphical model, deep learning, and other advanced machine learning topics. The course will also explore several real-world problems, e.g., visual detection/recognition, topics discovery, social media analytics using machine learning approaches.

An introduction to data analysis with a focus on visualization. Topics include: visualization of scalar, vector and tensor data; software tools for image, volume and information visualization and analysis; descriptive statistics; time dependent data; data patterns; analyzing propositions, correlations, and spatial relationships. Application of these topics to natural sciences and engineering are discussed. This course will also introduce programming basics including data types, variable declarations, arithmetic expressions, conditional statements, function prototypes, standard libraries, stacks, queues, file processing, structures, unions, unix systems, file systems, and some I/0.

Research

Research Interests

  • Transfer learning, and multi-modality recognition
  • Social media analytics: kinship verification, occupation recognition
  • Auto-encoder and deep feature learning
  • Graph approximation and clustering
  • Outlier detection and analysis

Ming Shao received B.E. degree in Computer Science, B.S. degree in Applied Mathematics, and M.E. degree in Computer Science from Beihang University, Beijing, China, in 2006, 2007, and 2010, respectively. He received Ph.D. degree in Computer Engineering from Northeastern University, Boston MA, 2016. He is a tenure-track Assistant Professor affiliated with College of Engineering at the University of Massachusetts Dartmouth since 2016 Fall. His current research interests include predictive modeling, adversarial machine learning, robust visual representation learning, and health informatics. He was the recipient of the Presidential Fellowship of State University of New York at Buffalo from 2010 to 2012, and the best paper award winner of IEEE ICDM 2011 Workshop on Large Scale Visual Analytics, and best paper award candidate of ICME 2014. He has served as the reviewers for many IEEE Transactions journals including TPAMI, TKDE, TNNLS, TIP, and TMM. He has also served on the program committee for the conferences including AAAI, IJCAI, ECAI, CVPR, ICCV, ICLR, ICDM, IEEE BigData, CIKM, ACM-MM, etc. He is the Associate Editor of SPIE Journal of Electronic Imaging, and IEEE Computational Intelligence Magazine. He is a member of IEEE.

External links

Request edits to your profile