Machine learning has proved a powerful tool for artificial intelligence and data mining problems. However, its success has usually relied on having a good feature representation of the data, and having a poor representation can severely limit the performance of learning algorithms. These feature representations are often hand-designed and require significant amounts of domain knowledge and human labor. To address these issues, there has been much interest in algorithms that learn feature hierarchies from unlabeled and labeled data. In this talk, I will discuss the fundamental challenges and present my research on developing algorithms that can learn invariant representations from unlabeled and labeled data. Further, I will talk about my recent work on learning state-of-the-art representations for visual recognition and speech recognition tasks.

Honglak Lee is an Assistant Professor of Computer Science and Engineering at the University of Michigan, Ann Arbor. He received his Ph.D. in Computer Science Department at Stanford University, advised by Andrew Ng. His research interests include deep learning and unsupervised feature learning with application to computer vision, audio recognition, and text processing. His work received ICML 2009 best application paper award and CEAS 2005 best student paper award.He received a Google Faculty Research Award in 2011.