Sort by
Refine Your Search
-
Listed
-
Country
-
Field
-
, speaker diarization, speech separation and enhancement Research advanced neural network architectures for speech and audio Assist in supervising graduate and undergraduate students Research evaluation
-
, speaker diarization, speech separation and enhancement Research advanced neural network architectures for speech and audio Assist in supervising graduate and undergraduate students Research evaluation
-
simulations of PDEs, deep learning, neural networks. Our research interest: Our focus is on theoretical and computational biological physics, ranging from the study of molecules to cells. We strive to leverage
-
models, programming, and quantitative methods. Preferred qualifications include experience in reinforcement learning, neural networks, and/or statistics. Questions can be addressed to Professor Nathaniel
-
research focuses on a geometric understanding of training in deep neural networks. The position offers excellent training opportunities at the intersection of machine learning and applied mathematics
-
challenges and real-world impact. Project overview In recent years, generative neural network models for creation of photo-realistic images have become increasingly popular. Their training results in a low
-
of neuronal loss to better understand why neurons die or axons are damaged to ultimately establish new strategies for the preservation or restoration of neural tissue. We use multiple approaches, but focus
-
learning methods. Develop deep learning architectures (e.g., variational autoencoders, graph neural networks, transformers) for cross-omics data representation and feature extraction. Apply multi-view
-
platforms, as well as extensive networking opportunities within the University of Miami’s robust AI and digital health ecosystem. Program Objectives: Provide fundamental training by interdisciplinary faculty
-
interpretable deep neural networks is required. Candidate must have published in top journal and conference at least one scientific paper in interpretable machine learning (not explanations of black boxes) among