YoVDO

Towards Verified Deep Learning

Offered By: Simons Institute via YouTube

Tags

Formal Methods Courses Deep Learning Courses

Course Description

Overview

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.

Syllabus

Intro
Context
Formal Methods
Context Matters
Example
Properties
Robustness
Local Robustness
Semantic adversarial analysis
Differentiable rendering
Verification
CPSML
CPSML Example
Retraining
Scenic
Deep Neural Networks
Verified
Conclusion
Questions Directions


Taught by

Simons Institute

Related Courses

Neural Networks for Machine Learning
University of Toronto via Coursera
機器學習技法 (Machine Learning Techniques)
National Taiwan University via Coursera
Machine Learning Capstone: An Intelligent Application with Deep Learning
University of Washington via Coursera
Прикладные задачи анализа данных
Moscow Institute of Physics and Technology via Coursera
Leading Ambitious Teaching and Learning
Microsoft via edX