Deep learning and neural networks coupled with high-performance computing and big data have led to remarkable advances in computer vision. For example, we now have a good capability to detect and localize people or objects. But we are still quite short of “visual understanding”. I’ll sketch some of our recent progress towards this grand goal. One is to explore the role of feedback or recurrence in visual processing. Another is to unify geometric and semantic reasoning for understanding the 3D structure of a scene. Most importantly, vision in a biological setting, and for many robotics applications, is not an end in itself but to guide manipulation and locomotion. I will show results on learning to perform manipulation tasks by experimentation, as well as on a cognitive mapping and planning architecture for mobile robotics.
Sep 16th, 2017, 4.00 pm to 5.00 pm
Himalaya # 105, IIIT Hyderabad, Gachibowli, Hyderabad.
Jitendra Malik is Arthur J. Chick Professor of Electrical Engineering and Computer Science at UC Berkeley. Over the past 30 years, Prof. Malik's research group has worked on many different topics in computer vision. Several well-known concepts and algorithms arose in this research, such as anisotropic diffusion, normalized cuts, high dynamic range imaging, shape contexts and R-CNN. Prof. Malik received the Distinguished Researcher in Computer Vision Award from IEEE PAMI-TC, the K.S. Fu Prize from the International Association of Pattern Recognition, and the Allen Newell award from ACM and AAAI. He has been elected to the National Academy of Sciences, the National Academy of Engineering and the American Academy of Arts and Sciences. He earned a B.Tech in Electrical Engineering from Indian Institute of Technology, Kanpur in 1980 and a PhD in Computer Science from Stanford University in 1985.
The advent of modern Artificial Intelligence, powered by Machine Learning and Big Data, is already having a large impact on the IT industry and is spreading to other sectors of the economy. However, not all data are equally useful; for instance data with both detailed observations (inputs) and known outcomes (desired and undesired outputs) is most useful for predictive tasks, but often data is noisy, incomplete and outcomes are at least partially unknown. New machine learning methods are needed to cope with such data, complementing the current wave of deep learning. The presentation will address proactive learning, multi-task learning, and their applications.
Sep 1st, 2017, 4.00 pm
Himalaya 105, IIIT Hyderabad, Gachibowli
University Professor and Allan Newell Professor of Computer Science Jaime G. Carbonell joined the Carnegie Mellon community as an assistant professor of computer science in 1979, and has gone on to become a widely recognized authority in machine translation, natural language processing and machine learning. Carbonell has invented a number of well-known algorithms and methods during his career, including proactive machine learning and maximal marginal relevance for information retrieval. His research has resulted in or contributed to a number of commercial enterprises, including Carnegie Speech, Carnegie Group and Dynamix Technologies.
In addition to his work on machine learning and translation, Carbonell also investigates computational proteomics and biolinguistics — fields that take computational tools used for analyzing language and adapt them to understanding biological information encoded in protein structures. This process leads to increased knowledge of protein-protein interactions and molecular signaling processes.
Carbonell's career has had an enormous impact on both Carnegie Mellon and the School of Computer Science. He created the university's Ph.D. program in language technologies, and is co-creator of the Universal Library and its Million Book Project. He founded CMU's Center for Machine Translation in 1986 and led its transformation in 1996 into the Language Technologies Institute, which he currently directs. He has advised more than 40 Ph.D. students and authored more than 300 research papers.
Before joining the Carnegie Mellon faculty, Carbonell earned bachelor's degrees in mathematics and physics at the Massachusetts Institute of Technology, and his master's degree and Ph.D. in computer science at Yale University.
During the last two decades, the experience of consumers has been undergoing a fundamental and dramatic transformation – giving a rich variety of informed choices, online shopping, consumption of news and entertainment on the go, and personalized shopping experiences. All of this has been powered by the massive amounts of data that is continuously being collected and the application of machine learning, data science and AI techniques to it.
Adobe is a leader in Digital Marketing and is the leading provider of solutions to enterprises that are serving customers both in the B2B and B2C space. In this talk, Dr. Anandan will outline the current state of the industry and the technology that is behind it, how Data Science and Machine Learning are gradually beginning to transform the experiences of the consumer as well as the marketer. He will also speculate on how recent developments in Artificial Intelligence will lead to deep personalization and richer experiences for the consumer as well as more powerful and tailored end-to-end capabilities for the marketer.
April 11th, 2017, 3:30 p.m.
Himalaya 105, IIIT Hyderabad, Gachibowli
Dr. P. Anandan is responsible for developing research strategy for Adobe, especially in the Artificial Intelligence and Machine Learning as applied to Digital Marketing and for leading the Adobe India Research lab.
Prior to Adobe, Dr. Anandan was a Distinguished Scientist and Managing Director of Microsoft Research Outreach. Previously, he was Distinguished Scientist and Managing Director at Microsoft Research India, which he founded in December 2004 in Bangaluru. He joined Microsoft Research in Redmond, Washington in 1997, where he founded and built the Interactive Visual Media group. Before joining Microsoft, Dr. Anandan was the Head of Video Information Processing research at Sarnoff Corporation from 1991-1997. He was an Assistant Professor of Computer Science at Yale University from 1987-1991.
Dr. Anandan holds an undergraduate degree in electrical engineering from the Indian Institute of Technology Madras, a Master of Science in Computer Science from the University of Nebraska, Lincoln, and a Ph.D. in Computer Science from the University of Massachusetts, Amherst. He is a Distinguished Alumnus of the University of Massachusetts as well as of IIT Madras, and has been inducted to the Nebraska Hall of Computing. During a research career spanning over three decades, Dr. Anandan has also done pioneering research in Computer Vision, specifically in the area of Visual Motion Analysis and Optical Flow Estimation.