Machine Learning
Using advances in machine learning, modern computers are now able to learn and make decisions. Rather than acting according to an explicit set of instructions, researchers are building intelligent systems designed to deal with uncertainty, adapt to the surrounding environment, and learn from experience. The goal of research in machine learning is to build intelligent systems that learn and assist humans efficiently.
At Princeton, research in machine learning includes: the development of new deep learning architectures for computer vision, natural language, and materials science; sophisticated new methods for control and reinforcement learning; theoretical investigation of deep learning; new methods for understanding and correcting bias in machine learning algorithms and data sets; new approaches to automatic differentiation; and exploration of connections to human cognition and neuroscience.
Associated Faculty
- Ryan Adams
- Sanjeev Arora
- Danqi Chen
- Jia Deng
- Adji Bousso Dieng
- Benjamin Eysenbach
- Tom Griffiths
- Elad Hazan
- Peter Henderson
- Aleksandra Korolova
- Lydia Liu
- Olga Russakovsky
- Sebastian Seung
- Ellen Zhong
Associated Graduate Students
- Gianluca Bencomo
- Nataly Brukhim
- Berlin Chen
- Yun Cheng
- Arushi Gupta
- Seth Karten
- Zhou Lu
- Elizabeth Mieczkowski
- Edgar Minasyan
- Geoffrey Roeder
- Zheng Shi
- Ahmed Shuaibi
- Tianhan Xu
- Runzhe Yang
- Dingli Yu
