Главная
Study mode:
on
1
Introduction
2
Overview
3
Recent examples
4
The bottom line
5
Verifying deep learning
6
The problem of deep networks
7
Linear networks
8
Offtheshelf solvers
9
Questions
10
Validation
11
Linear Programming
12
Branch Inbound
13
In practice
14
Does robustness matter
15
Security flaws
16
Why doesnt anyone care
17
Conclusion
Description:
Explore recent advancements in verifying neural networks in this Stanford seminar featuring Zico Kolter, Associate Professor at Carnegie Mellon University. Delve into the challenges of guaranteeing network output properties for specific input classes, a crucial aspect of validating robustness and safety in neural networks. Learn about the significant progress made in this complex field, with recent methods achieving verification speeds thousands of times faster than generic solvers. Discover the team's award-winning approach at the Verification of Neural Networks Competition (VNNCOMP) 2021. Gain insights into the verification problem, linear networks, off-the-shelf solvers, and practical applications. Examine the importance of robustness, potential security flaws, and the broader implications for deep learning validation.

Stanford Seminar - Recent Progress in Verifying Neural Networks, Zico Kolter

Stanford University
Add to list
0:00 / 0:00