Admissions
Positions Available for Fall 2026
Research position: Machine Learning for Sensing and Autonomy
Machine learning for remote sensing, computer vision, semantic communication, and autonomy. Requirements: Strong foundation in mathematics and statistics with programming experience for machine learning. Prior experience with computer vision, signal processing, reinforcement learning, robotics, computer graphics or game engines is a plus. Students should have a clear interest in advancing machine learning to address challenging real-world problems that arise from limited data scenarios in a variety of domains.
Research position: Machine Learning for Health: Neuroimaging and Bioinformatics
Machine learning for extracting biomarkers and risk factors from multimodal data related to neurodegeneration, cognitive decline, dementia and Alzheimer’s disease. Requirements: Strong foundation in mathematics and statistics with programming experience for machine learning. Prior experience with biomedical imaging, electronic health records, or neuroscientific data is preferred.
Research position: Machine Learning for Neural Signal Processing
Learning waveform patterns of epilepsy embedded in background EEG using advanced machine learning techniques.
Requirements: Strong foundation in mathematics and statistics with programming experience for machine learning. Prior experience with signal processing, especially neural signals is preferred.
Graduate research assistant positions are available starting Fall 2026 (or later) in the Computational Neural Information Engineering Laboratory led by Dr. Brockmeier.
Graduate research assistant positions are available starting Fall 2026 in the Computational Neural Information Engineering Laboratory led by Dr. Brockmeier.
The lab develops innovative machine learning approaches designed to extract information from complex data, motivated by the vastness of undersea environments and the intricacies of brain structure and function. Projects range from foundational research (involving mathematical, information theoretic, statistical, and computational principles) to impactful applications related to remote sensing (underwater sonar), computer vision, neural signals, neuroimaging, and other biomedical data.
Two ongoing projects focus on the extraction of biomarkers that are indicative of disease onset, health outcomes, or genotypes from multimodal data (retinal images, neuroimages, functional imaging, EEG, cognitive assessments, health records) to be used for early diagnosis, tracking health trajectory, guiding interventions, or understanding the underlying mechanisms of disease. The first project develops machine learning to extract profiles of modifiable risk factors for predicting cognitive impairment related to neurodegeneration. In the second project, we seek to systematically identify and validate waveform patterns of epilepsy embedded in background EEG using advanced machine learning techniques. By uncovering these hidden markers, we aim to improve diagnostic accuracy, reduce time to diagnosis, and ultimately enable earlier and more targeted interventions for individuals with epilepsy.
Foundationally, the lab focuses on statistical divergences that can be used to guide alignment of distributions or datasets and interpret distributional shifts between them. We utilize divergence measures to advance generative modeling, covariate shift correction, and transfer learning. These foundational contributions have been translated to applied real-world cases in sonar imaging and neuroimaging. In particular, an ongoing project to simulate sonar imagery via (procedural generation, graphic simulators) to augment training.
Other ongoing research that uses information theoretic perspectives seeks to disentangle the learned representations of neural network models (large language models and vision encodings) for information retrieval, latent space editing, and compression. This has applications to task-relevant compression of sonar images.
Graduate student applicants are expected to have a strong foundation in mathematics and statistics with programming experience for machine learning. Prior experience with signal processing, reinforcement learning, robotics, biomedical data, neuroscientific data, computer graphics, game engines, or computer vision is preferred. Students should have a clear interest in advancing machine learning to address challenging real-world problems that arise from limited data scenarios in a variety of domains.
The ECE Department fosters a collaborative culture for graduate students. The lab has close ties to the Data Science Institute (DSI), Center for Bioinformatics and Computational Biology, the First State AI Institute, the Delaware Center for Cognitive Aging Research, and the Interdisciplinary Neuroscience Graduate program.
The University of Delaware is a Carnegie R1 institution (Very High Research Activity) located in Newark, Delaware. Newark is an affordable, high-quality college town within commuting distance from Philadelphia and Baltimore. We are centrally located within the mid-Atlantic bio-pharma and life sciences corridor with strategic proximity to major government and defense research hubs, including Aberdeen Proving Ground and Naval research centers in the D.C./Maryland corridor. There is easy access to New York City, Washington D.C., the Appalachian Trail, and Atlantic beaches.
Please apply to the Department of Electrical and Computer Engineering (ECE) and/or the Department of Computer and Information Sciences (CIS) and designate me as a potential advisor. Both departments are in the College of Engineering at the University of Delaware. For those more interested in applications of data science to health, I am also an Affiliated Faculty in the Ph.D. in Bioinformatics and Data Science Program. Please apply for graduate admissions online with your CV, transcripts, and statements of purpose and research interests. Priority will be given to applications received by January 2nd. It is unlikely that I can respond to email requests regarding positions in my group.