MLT Talk: Infusing Structure into ML Algorithms with Anima Anandkumar, NVIDIA

Machine Learning Tokyo
Machine Learning Tokyo

International Academic Research Building

7 Chome-3 Hongo, Bunkyo City · 東京都


Lecture room No. 5, basement floor of International Academic Research Building, University of Tokyo



We are honored to welcome Anima Anandkumar, Director of ML Research at NVIDIA and Bren Professor at Caltech, for a MLT talk at the University of Tokyo.

7:00 PM Doors open
7:30 PM "Infusing Structure into Machine Learning Algorithms", Anima Anandkumar
8:20 PM Q&A
8:45 PM Closing

-- TALK --
Standard deep-learning algorithms are based on a function-fitting approach that do not exploit any domain knowledge or constraints. This makes them unsuitable in applications that have limited data or require safety or stability guarantees, such as robotics. By infusing structure and physics into deep-learning algorithms, we can overcome these limitations. There are several ways to do this. For instance, we use tensorized neural networks to encode multidimensional data and higher-order correlations. We combine symbolic expressions with numerical data to learn a domain of functions and obtain strong generalization. We combine baseline controllers with learnt residual dynamics to improve landing of quadrotor drones. These instances demonstrate that building structure into ML algorithms can lead to significant gains.

Anima Anandkumar is the Director of ML Research at NVIDIA and Bren Professor at Caltech. She was previously a Principal Scientist at Amazon Web Services. She has received several honors such as the Alfred. P. Sloan Fellowship, Young investigator awards from DoD, and Faculty Fellowships from Microsoft, Google and Adobe. She is part of the World Economic Forum's Expert Network consisting of leading experts from academia, business, government, and the media. She has been featured in documentaries by PBS, KPCC, wired magazine, and in articles by MIT Technology review, Forbes, Yourstory, O’Reilly media, and so on. Anima received her B.Tech in Electrical Engineering from IIT Madras in 2004 and her PhD from Cornell University in 2009. She was a postdoctoral researcher at MIT from 2009 to 2010, a visiting researcher at Microsoft Research New England in 2012 and 2014, an assistant professor at U.C. Irvine between 2010 and 2016, an associate professor at U.C. Irvine between 2016 and 2017 and a principal scientist at Amazon Web Services between 2016 and 2018.

Thank you to the University of Tokyo and the Center for Research and Education in Program Evaluation (CREPE) for co-hosting this event. CREPE was established in October 2017 to pursue "Evidence Based Policy Making" (EBPM). Great importance is placed on the activities such as
1. Organizing seminars/lecture series for graduate students by distinguished visitors
2. Conducting joint research projects with policymakers and industries
3. Human resource development programs both for graduate students and officials of central/local government offices

English website:
Japanese website:

Become a MLT Patron and help us to keep MLT meetups like this inclusive and for free.


MLT events are for community building and knowledge sharing. We politely ask that company representatives, recruiters and consultants looking to hire or sell their services do not come to this event.