Главная
Study mode:
on
1
Intro
2
Context
3
Formal Methods
4
Context Matters
5
Example
6
Properties
7
Robustness
8
Local Robustness
9
Semantic adversarial analysis
10
Differentiable rendering
11
Verification
12
CPSML
13
CPSML Example
14
Retraining
15
Scenic
16
Deep Neural Networks
17
Verified
18
Conclusion
19
Questions Directions
Description:
Explore the intersection of formal methods and deep learning in this 55-minute lecture by Sanjit Seshia from UC Berkeley. Delve into emerging challenges in deep learning, focusing on verification and robustness. Examine local robustness, semantic adversarial analysis, and differentiable rendering. Investigate the application of formal methods to cyber-physical systems with machine learning components. Learn about retraining techniques and the Scenic probabilistic programming language for scenario description. Gain insights into verified deep neural networks and future research directions in this field.

Towards Verified Deep Learning

Simons Institute
Add to list
0:00 / 0:00