George D. Montañez, PhD, focuses his research at the intersection of machine learning, information theory and algorithmic search. He has worked on problems related to computational biology, spatio-temporal learning, cross-device search and the information properties of genetic algorithms. His current research explores why machine learning works from a search and dependence perspective, and identifies information constraints on general search processes.
Montañez’s research lab, the Artificial Machine Intelligence = Search Targets Awaiting Discovery (AMISTAD) lab, researches problems in theoretical machine learning, probability, statistics and search. Their current research projects include DFA learnability, information-theoretic models for biological molecular recognition tasks, a theory of overfitting and underfitting, and machine learning as search.
Montañez completed his PhD in machine learning at Carnegie Mellon University. He holds an M.S. in computer science from Baylor University, an M.S. in machine learning from Carnegie Mellon University, and a B.S. in computer science from the University of California Riverside. He previously worked in industry as a software engineer and web developer, and interned at Microsoft Research at Yahoo! Labs.
- Mind Matters, 10/3/2019 Can Machines Think?
- Mind Matters, 1/7/2019 AI: Think About Ethics Before Trouble Arises
- Baylor.edu, 2018 George Montañez, MS ’11
- Baylor.edu, 2018 Data Driven
- hmc.edu, 9/16/17 Montañez Receives IEEE SMC Best Paper Honors