/filters:quality(90)/prod01/production-cdn-pxl/media/umassdartmouth/profiles/arts-and-sciences/mathematics/DonghuiYan_0079.jpg?text=945+WebP)
faculty
Donghui Yan, PhD
Associate Professor
Mathematics
Contact
508-999-8746
bw_l>sk_qqb,cbs
Liberal Arts 394F
Education
| University of California, Berkeley | PhD in Statistics |
Teaching
- Statistics
- Machine learning
- Data Science
Teaching
Programs
Programs
- Applied Statistics
- Data Science BS, BS/MS
- Data Science Graduate Certificate
- Data Science MS
- Mathematics BA, BS
Teaching
Courses
A team-based learning experience that gives students the opportunity to synthesize prerequisite course material and to conduct real-world analytics projects using large data sets of diverse types and sources. Students work in independent teams to design, implement, and evaluate an appropriate data integration, analysis, and display system. Oral and written reports and ethical aspects are highlighted.
A team-based learning experience that gives students the opportunity to synthesize prerequisite course material and to conduct real-world analytics projects using large data sets of diverse types and sources. Students work in independent teams to design, implement, and evaluate an appropriate data integration, analysis, and display system. Oral and written reports and ethical aspects are highlighted.
Investigations of a fundamental and/or applied nature representing an original contribution to the scholarly research literature of the field. PhD dissertations are often published in refereed journals or presented at major conferences. A written dissertation must be completed in accordance with the rules of the Graduate School and the College of Engineering. Admission to the course is based on successful completion of the PhD comprehensive examination and submission of a formal proposal endorsed by the student's graduate committee and submitted to the EAS Graduate Program Director.
Rigorous and systematic introduction to the theory and practice of deep learning. Topics include approximation, generalization, optimization, and the mathematical concepts behind the various kinds of learning such as Supervised (regression and classification), unsupervised (clustering, dimension estimation), semi-supervised, and reinforcement. The course addresses the computational aspects of deep learning such as efficient computation of gradients using backpropagation and batch normalization.
Research
Research awards
- $ 457,478 awarded by Office of Naval Research for UMassD MUST IV: Knowledge Augmented Adaptive Learning of Evolving Models for Large Sensor Data Streams
Research
Research interests
- Statistics
- Machine learning
- Data mining
- Data science
- High dimensional statistical inference