Comet Calendar Event Details

Due to changes in campus operations, many events may be canceled, virtualized or postponed.
Please check with the sponsoring department to confirm event details.
Mathematical Sciences Colloquium by Bao Wang
Friday, Jan. 31
1 p.m. - 2 p.m. Location: JO 4.102

Bao Wang

University of California

PDE-Principled Trustworthy Deep Learning Meets Computational Biology

Deep learning achieves tremendous success in image and speech recognition and machine translation. However, deep learning is not trustworthy. 1. How to improve the robustness of deep neural networks? Deep neural networks are well known to be vulnerable to adversarial attacks. For instance, malicious attacks can fool the Tesla self-driving system by making a tiny change on the scene acquired by the intelligence system. 2. How to compress high-capacity deep neural networks eciently without loss of accuracy? It is notorious that the computational cost of inference by deep neural networks is one of the major bottlenecks for applying them to mobile devices. 3. How to protect the private information that is used to train a deep neural network? Deep learning-based arti cial intelligence systems may leak the private training data. Fredrikson et al. recently showed that a simple model-inversion attack can recover the portraits of the victims whose face images are used to train the face recognition system.

In this talk, I will present some recent work on developing PDE-principled robust neural architecture and optimization algorithms for robust, accurate, private, and ecient deep learning. I will also present some potential applications of the data-driven approach for bio-molecule simulation and computer-aided drug design.

Coffee to be served 30 minutes prior to the talk in the alcove outside of FO 2.406.

 

Persons with disabilities may submit a request for accommodations to participate in this event at UT Dallas' ADA website. You may also call (972) 883-5331 for assistance or send an email to [email protected]. All requests should be received no later than 2 business days prior to the event.
Contact Info:
Viswanath Ramakrishna, 972-883-6873
Questions? Email me.

Tagged as Lectures/Seminars, Professional Dev.
See more events from Natural Sciences & Mathematics
View other events on the Comet Calendar