Towards Verified Deep Learning
Offered By: Simons Institute via YouTube
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 LearningUniversity 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