Perceiving, Acting and Collaborating

Thursday, November 26, 2020

Abstract:
I will discuss the development and open problems in robot perception and interaction. The integral ability of any robot is to act in the environment, interact and collaborate with people and other robots. Interaction between the agents builds on the ability to engage in mutual prediction and signaling. The focus will be on physical interaction with objects and modelling of multisensory data.

Bio:
Danica Kragic is a Professor at the School of Computer Science and Communication at the Royal Institute of Technology, KTH. She received MSc in Mechanical Engineering from the Technical University of Rijeka, Croatia in 1995 and PhD in Computer Science from KTH in 2001. She has been a visiting researcher at Columbia University, Johns Hopkins University and INRIA Rennes. She is the Director of the Centre for Autonomous Systems. Danica received the 2007 IEEE Robotics and Automation Society Early Academic Career Award. She is a member of the Royal Swedish Academy of Sciences, Royal Swedish Academy of Engineering Sciences and Young Academy of Sweden. She holds a Honorary Doctorate from the Lappeenranta University of Technology. She chaired IEEE RAS Technical Committee on Computer and Robot Vision and served as an IEEE RAS AdCom member. Her research is in the area of robotics, computer vision and machine learning. In 2012, she received an ERC Starting Grant. Her research is supported by the EU, Knut and Alice Wallenberg Foundation, Swedish Foundation for Strategic Research and Swedish Research Council. She is an IEEE Fellow.

Surprises in the Quest for Robust Machine Learning

Thursday, January 21, 2021

Abstract:
Standard machine learning produces models that are accurate on average but degrade dramatically on when the test distribution of interest deviates from the training distribution.  We consider three settings where this happens: when test inputs are subject to adversarial attacks, when we are concerned with performance on minority subpopulations, and when the world simply changes (classic domain shift). Our aim is to produce methods that are provably robust to such deviations.  In this talk, I will provide an overview of the work my group has done on this topic over the last three years. We have found many surprises in our quest for robustness: for example, that the "more data" and "bigger models" strategy that works so well for average accuracy sometimes fails out-of-domain.  On the other hand, we have found that certain tools such as analysis of linear regression and use of unlabeled data (e.g., robust self-training) have reliably delivered promising results across a number of different settings.

Bio:
Percy Liang is an Associate Professor of Computer Science at Stanford University (B.S. from MIT, 2004; Ph.D. from UC Berkeley, 2011). His two research goals are (i) to make machine learning more robust, fair, and interpretable; and (ii) to make computers easier to communicate with through natural language. His awards include the Presidential Early Career Award for Scientists and Engineers (2019), IJCAI Computers and Thought Award (2016), an NSF CAREER Award (2016), a Sloan Research Fellowship (2015), and a Microsoft Research Faculty Fellowship (2014).

Modeling Chemistry for Drug Discovery: Current State and Unsolved Challenges

Thursday, January 28, 2021

Abstract:
Until today, all the available therapeutics are designed by human experts, with no help from AI tools. This reliance on human knowledge and dependence on large-scale experimentations result in prohibitive development cost and high failure rate. Recent developments in machine learning algorithms for molecular modeling aim to transform this field. In my talk, I will present state-of-the-art approaches for property prediction and de-novo molecular generation, describing their use in drug design. In addition, I will highlight unsolved algorithmic questions in this field, including confidence estimation, pretraining, and deficiencies in learned molecular representations.  

Bio:
Regina Barzilay is a professor in the Department of Electrical Engineering and Computer Science and a member of the Computer Science and Artificial Intelligence Laboratory at the Massachusetts Institute of Technology. Her research interests are in natural language processing. Currently, Prof. Barzilay is focused on bringing the power of machine learning to oncology. In collaboration with physicians and her students, she is devising deep learning models that utilize imaging, free text, and structured data to identify trends that affect early diagnosis, treatment, and disease prevention. Prof. Barzilay is poised to play a leading role in creating new models that advance the capacity of computers to harness the power of human language data.

Regina Barzilay is a recipient of various awards including the MacArthur Fellowship, NSF Career Award, the MIT Technology Review TR-35 Award, Microsoft Faculty Fellowship and several Best Paper Awards in top NLP conferences. In 2017, she received a MacArthur fellowship, an ACL fellowship and an AAAI fellowship. Most recently, in 2020, she is the first recipient of the AAAI Squirrel AI Award for Artificial Intelligence for the Benefit of Humanity.

Prof. Barzilay received her MS and BS from Ben-Gurion University of the Negev. She received her PhD in Computer Science from Columbia University, and spent a year as a postdoc at Cornell University