Organized by India, a large number of scientists from India and the Indian diaspora provided ideas for Atmanirbhar Bharat related initiatives. Dr. Ravela was a panelist on Machine Learning and Inversion. He presented the framework for Informative Learning and Optimization, which is a key...
News
Trautner, Margolis, and Ravela won the "Top 5" recognition for the paper presented at the DDDAS 2020 conference. This paper contains three fundamentally transformative components: 1) Informative Ensemble Learning provides an efficacious parallel...
Our paper, found here, wins the best student paper award at the KDD 2020 Fragile Earth workshop....
Our own Gabriel will stay at the institute for an MENG in Robotics!
Our own Margaret, who worked on Neural Dynamical Systems, will head to Caltech for graduate school
We presented a video and paper at the Winter Applications of Computer Vision Conference (WACV 2020) in the Deep Learning for Animal Re-Identification Workshop.
...
We presented our work on long-range prediction and climate risk to a mixed academic-industrial audience, much fun it was!
Under a collaboration, we are developing adaptive autopilots to handle rapid unmodeled aircraft configuration changes, Dr. Ankit Goel visits us
...
Ziwei Li and Sai Ravela discuss how
- The predictability of neural networks is near identical to the chaotic dynamics they learn from
- This they argue is because neural Networks follow a path to chaos through alternate stretching and compression
- Very few training...
Sai Ravela presents at Shell, arguing for theory-data symbiosis, which includes:
- Models from theory suffer from nonlinearity, dimensionality and uncertainty
- Models from data suffer from the above plus issues of generalization, extrapolation, and the representation of theory...
- ‹ previous
- 2 of 5
- next ›