Machine Learning Optimization Laboratory

Welcome to the webpage of the Machine Learning Optimization (MeLOs) Laboratory at The University of Texas at San Antonio (UTSA).

Our researchers, led by Dr. Panagiotis (Panos P.) Markopoulos, tackle challenging and impactful problems in the realms of machine learning, data analysis, and signal processing. The mission of MeLOs is to promote the development of efficient and trustworthy artificial intelligence. Our research focus encompasses both fundamental research (theory and algorithms) and practical solutions, spanning a broad range of applications such as computer vision, remote sensing, wireless communications, and healthcare.

MeLOs is a core lab of the UTSA School of Data Science, housed in state-of-the-art facilities at the new San Pedro 1 building.

The greek word μέλος (melos) translates to group member or part of a (musical) composition.

Our expertise is in the areas of machine learning, data analysis, and signal processing. We focus on fundamental machine learning (statistical, computational), but also on practical machine-learning solutions to a wide range of real-world problems.

Current research topics:

• Machine learning with limited, faulty, and corrupted data.

• Incremental, dynamic, and continual machine learning. 

• Learning from multimodal data and deep learning fusion.

• Optimizing neural network size and structure, in view of task and available data. 

• Tensor data analysis and processing.

• Lp-norm formulations for robust unsupervised machine learning and data analysis.

Among other areas, our research finds applications in remote sensing, communication systems, and medicine/healthcare.

• Title: PARTNER: Neuro-Inspired AI for the Edge at UTSA (NAIAD). Funding agency: National Science Foundation. Award period: September 2023 - August 2026.  Total obliged amount: $2,800,000. Role: Co-PI (PI: Dr. Dhireesha Kudithipudi). 

• Title: Target Detection/Tracking and Activity Recognition from Multimodal Data. Funding agency: National Geospatial-Intelligence Agency. Period: September 2019 - September 2024. Total obliged amount: $858,534. Role: Equal effort co-PI (PI: Dr. E. Saber, RIT).

• AFOSR Young Investigator Program Award. Title: Theory and Efficient Algorithms for Dynamic and Robust L1-Norm Analysis of Tensor Data. Funding agency: U.S. Air Force Office of Scientific Research (AFOSR). Period: January 2020 - January 2023. Amount: $348,460. Role: Sole PI.

• Title: Collaborative Research: CDS&E: Theoretical Foundations and Algorithms for L1-Norm-Based Reliable Multi-Modal Data Analysis. Funding agency: U.S. National Science Foundation (NSF). Period: September 2018 - August 2021. Amount: $323,973. Role: PI (Co-PI: Dr. A. Savakis, RIT).

• Title: Efficient Radar Imaging and Machine Learning for Concealed Object Detection. Funding Agency: NYSTAR / UR CoE in Data Science. Period: October 2021 - June 2022. Amount: $58,079. Role: Sole PI.

• Title: Continual and Incremental Learning with Tensor-Factorized Neural Networks. Funding Agency: U.S. Air Force Research Laboratory (AFRL). Period: September-December 2021. Amount: $30,286. Role: Sole PI.