At the Vermont Artificial Intelligence Laboratory (VaiL) we work at the intersection of machine learning theory and application. Our mission is to improve the adaptability and generalization of machine learning methods, in order to allow higher-quality applications to broader classes of real-life problems. We research deep learning, deep reinforcement learning, and memory-augmented models. Our main application domain is the energy field, though we also collaborate with groups from the medical and transportation fields.
We are looking for bright, hardworking students interested in research and scholarship opportunities. Email a copy of your CV/Resume to firstname.lastname@example.org. Ideal applicants should have knowledge of machine learning fundamentals, experience programming with Python, experience working with common deep learning frameworks (Tensorflow, PyTorch, etc.), and/or experience in energy systems.
2021-06-12 - Congrats to Colin for successfully defending his Ph.D. thesis.
2020-03-31 - Congrats to Wyatt Wu for successfully defending his MS thesis.
2019-11-01 - Congrats to Kristin McClure for successfully defending his MS Project.
2019-11-01 - I have been awarded an extension to our VTrans project one more year with $92K, our team will have accurate road signs localization on real-world maps.
2019-03-01 - In collaboration with university of Rochester I have been awarded a grant from NYSERDA, to research advanced machine learning algorithms for parameter verification and calibration.
2018-02-01 - In collaboration with UVMMC I have been awarded a grant to research techniques to predict the presence of an Endoleak in computerized tomography angiography (CTA) volumes.
2018-01-11 - I have been awarded a grant from University of Vermont Medical Center, Department of Surgery, to design deep learning algorithms for medical imaging applications.
2018-01-23 - I have been awarded, as a PI, a grant from the Vermont Agency of Transportation (VTrans) to localize road signs on both image coordinates and geographic coordinates on real-world maps.