Assistant Professor Huang receives two awards

Awards from NSF and JP Morgan
Descriptive Image

Assistant Professor Furong Huang has received an NSF Award for her work entitled Principled Methods for Learning and Understanding of Neural Networks. The work advocates theoretically guaranteed training and understanding of neural networks via techniques from learning theory, nonconvex optimization and consistent latent variable model learning using spectral methods.

The project aims to
• Guarantee training of deep nets
• Analyze generalization ability of compressed deep neural networks
• Provide reliable deep neural networks robust to the worst attackers

Huang was awarded a “2019 J.P. Morgan Faculty Research Award” for her work on ‘Methods to Identify Communities and Trading Behavior over Financial Data Streams’. This is an interdisciplinary research in collaboration with Louiqa Raschid and Alberto Rossi from the business school.

The research focusses on scalability of analysis to multiple data streams and to fuse the data streams so that they represent communities of people and their interactions across financial products. The research aims to address the following challenges:

• Customize and extend machine learning approaches to fuse longitudinal time-series datasets, organized around people and financial products, and to analyze them at scale
• Propose simple templates to identify community patterns
• Connect communities and their behavioral patterns to questions of interest to financial researchers

The Department welcomes comments, suggestions and corrections.  Send email to editor [at] cs [dot] umd [dot] edu.