Mathematics Colloquium: Hongkai Zhao (Duke University)- Numerical understanding of neural networks:

Warning Icon This event is in the past.

When:
April 15, 2024
2:45 p.m. to 3:45 p.m.
Where:
Faculty/Administration
656 W. Kirby (Room #1146)
Detroit, MI 48202
Event category: Seminar
In-person

Date/Time: Monday April 15, 2:45pm

Room: FAB 1146

Speaker: Hongkai Zhao (Duke University)

 Title: Numerical understanding of neural networks: from representation to learning dynamics

Abstract:

In this talk I will present both numerical analysis and experiments to understand a few basic computational issues in using neural network to approximate functions: (1) the numerical error that can be achieved given a finite machine precision, (2) the learning dynamics and computation cost to achieve certain accuracy, and (3) structured and balanced approximation. These issues are studied for both approximation and optimization in asymptotic and non-asymptotic regimes.

Contact

Tao Huang
taohuang@wayne.edu

Cost

Free
April 2024
SU M TU W TH F SA
31123456
78910111213
14151617181920
21222324252627
2829301234