Iddo Drori

🧠 Can a machine solve, grade, and generate university-level mathematics and stem courses? Our latest research on learning to learn courses demonstrates that a neural network trained on text and fine-tuned on code solves, grades, and generates university-level mathematics and stem courses by program synthesis.
🌎 Can we predict extreme climate change based on millennia of data and monitor climate? In the spirit of MIT's leading efforts to take action against climate change for a better world, we've published multidisciplinary work on machine learning for climate change, awarded best paper: pathway to impact.
💧 Can we efficiently optimize bubbles at micrometer and millimeter scales using only a few samples? Our recent journal paper describes multidisciplinary work to optimize generation of droplets at multiple scales.
📖 My new book The Science of Deep Learning is being published with Cambridge University Press.
📚 22 accepted journal (2), conference (8), and workshop (12) papers in the past 18 months, including multiple best paper awards and conference competition winners.

Recent Awards

🌎 CCAI NeurIPS 2021 Best Paper Award Winner
🏆 FG 2021 Competition Winner, Kinship Verification Challenge
🥇 ACML 2021 Best Student Paper Award Winner
🚘 ICCV 2019 Competition Winner, Learning to Drive Challenge

 Massachusetts Institute of Technology

Department of Electrical Engineering and Computer Science
77 Massachusetts Ave, Cambridge, MA 02139
www.mit.edu/~idrori
idrori@mit.edu

 Columbia University

School of Engineering and Applied Science
500 W 120th Street, New York, NY 10027
www.cs.columbia.edu/~idrori
idrori@cs.columbia.edu

The Science of Deep Learning

Cambridge University Press, 2021.

 Cornell University

idrori@cornell.edu

I was a visiting Associate Professor at Cornell University, working on automated machine learning and combinatorial optimization.

Academic Service

Profile on Google Scholar

Publications

Teaching

Education

Selected Invited Talks and Panels