Daniel Reichman

Daniel Reichman is an Assistant Professor in the Department of Computer Science at Worcester Polytechnic Institute (WPI). He holds a PhD from the Weizmann Institute of Science under the supervision of Uri Feige. Prior to WPI, he completed postdoctoral research at Cornell University, UC Berkeley, and Princeton University. His research focuses on intersections of machine learning, neural networks, cognitive science, and theoretical computer science. Key interests include neural network architecture design, computational complexity, and algorithmic graph theory. His work bridges theory and application, addressing challenges in network contagion, optimization, and human decision-making modeling.

Education: PhD, Weizmann Institute of Science (2010s), Postdoctoral Fellowships: Cornell, Berkeley, and Princeton (early 2020s).

Research Interests: Machine Learning, Neural Networks (depth/expressivity), Cognitive Science (goal systems), Theoretical Computer Science (complexity, spectral methods), and Combinatorics (graph algorithms).

Recent work includes studies on neural network depth separations, computational complexity of counting linear regions, and inoculation strategies in graphs. His publications often explore the theoretical underpinnings of modern AI systems and algorithmic solutions to combinatorial problems.