Eldan Cohen

Eldan Cohen is an Assistant Professor of Industrial Engineering in the Department of Mechanical & Industrial Engineering at the University of Toronto. His research interests include machine and deep learning, heuristic search and optimization, and scalable data mining, with emphasis on interpretable and human-compatible approaches. His work focuses on applications in healthcare, automated planning, natural language processing, and software engineering. Prior to joining MIE, he was a postdoctoral fellow in the Department of Computer Science at the University of Toronto and the Vector Institute for Artificial Intelligence. He obtained his Ph.D. in the Department of Mechanical & Industrial Engineering at the University of Toronto, working on heuristic search algorithms for automated planning and neural sequence decoding, and has worked as a research intern at the Fujitsu Laboratories of America, developing unsupervised machine learning algorithms for specialized optimization hardware.

Eldan Cohen is a researcher at the University of Toronto with expertise in Artificial Intelligence, Machine Learning, Heuristic Search, Optimization, and Explainability. His work explores the performance of beam search in neural sequence models, the development of machine learning approaches for patient safety event classification, and the use of SAT-based methods for optimal decision trees. Cohen also investigates explainable clustering techniques, Ising frameworks for constrained clustering, and the application of transformer models for intent mining in emails. His research emphasizes the interplay between algorithmic efficiency, interpretability, and hardware optimization for complex problems.