Welcome!
Our team’s research spans various theoretical and practical aspects of Machine Learning. We focus on designing and analyzing machine learning algorithms and deep learning techniques. In particular, we work on deep neural network efficiency and robustness, and continual learning methods. Our secondary mission is to explore applications and advances of novel machine learning approaches in real-time problems. Our research is generously supported by the National Science Foundation (NSF), University of Maine, MSGC/NASA, UMaine Space Initiative, and Cisco.
Our project codes are available on our Github!
Summer Bootcamp: Introduction on Deep Learning, July 18th-19th, 2023, Roux Institute, Portland.
Prospective Students:
We are always looking for highly motivated students with an interest/background in Machine Learning, Data Science, and AI to join our group.
The focus of our research is on the following areas:
-
Deep Neural Network Compression
-
Adversarial Machine Learning and Network Robustness
-
Continual/Sequential Learning models
-
Graph Summarization and Subgraph Learning
-
Online Feature Selection of Streaming Big Data
-
Graph-Based and Fast Estimation of Information-Theoretic Measures
-
High-Dimensional Network Structure Learning with Applications in Biology
-
Learning Bounds on BER to Improve Deep Neural Network Performance
-
Quantifying and Analyzing the Interaction Content of Big Data Sets
-
Applicants with a background or interest in related research are welcome to apply. If you are interested to join our group please send your cover letter and CV to salimeh.yasaei@maine.edu.
Recent News
