Yaser S. Abu-Mostafa
Professor of Electrical Engineering and Computer Science
machine learning, artificial intelligence, neural networks, computational finance, probability and statistics
Overview
The Learning Systems Group at Caltech studies the theory and applications of Machine Learning (ML). The theory of ML uses mathematical and statistical tools to estimate the information (data and hints) needed to learn a given task. The applications are very diverse and continue to expand to every corner of science and technology. The group works on medical applications of ML, on e-commerce and profiling applications, and on computational finance, among other domains. These applications use the latest techniques of neural networks and other models, and often give rise to novel ML theory and algorithms. Our latest projects are data-driven approach to predicting the spread of COVID-19 in every U.S. county, and ML approach to medical diagnostics using low-resolution ultrasound.
Related News
Read more newsPublications
- Cramer, Estee Y.;Huang, Yuxin et al. (2022) The United States COVID-19 Forecast Hub datasetScientific Data
- Yurk, Dominic;Abu-Mostafa, Yaser (2021) County-Specific, Real-Time Projection of the Effect of Business Closures on the COVID-19 Pandemic
- González, Carlos R.;Abu-Mostafa, Yaser S. (2015) Mismatched Training and Test Distributions Can Outperform Matched OnesNeural Computation
- Abu-Mostafa, Yaser S. (2012) Machines that Think for ThemselvesScientific American
- Li, Ling;Abu-Mostafa, Yaser S. (2006) Data complexity in machine learning
- Angelova, Anelia;Abu-Mostafa, Yaser S. et al. (2005) Pruning training sets for learning of object categories
- Li, Ling;Pratap, Amrit et al. (2005) Improving Generalization by Data Categorization
- Li, Ling;Martinoli, Alcherio et al. (2004) Learning and Measuring Specialization in Collaborative Swarm SystemsAdaptive Behavior
- Abu-Mostafa, Yaser;Song, Xubo et al. (2004) The Bin Model
- Magdon-Ismail, Malik;Atiya, Amir F. et al. (2004) On the Maximum Drawdown of a Brownian MotionJournal of Applied Probability