Applied Deep Learning Lectures

Learn practical deep learning implementation through a comprehensive lecture series covering the complete machine learning project lifecycle from conception to deployment. Master essential skills including project selection, data management, model troubleshooting, and team building through expert presentations from industry leaders and researchers. Explore advanced topics such as programming training data with Snorkel, experiment management tools, and research methodologies while gaining insights into building effective machine learning teams. Discover debugging techniques for deep learning models, understand grading rubrics for AI applications, and examine potential research directions in the field. Benefit from real-world perspectives on ML tools, testing strategies, and deployment practices essential for successful applied deep learning projects.

Syllabus

Applied Deep Learning Fellowship Overview and Project Selection with Josh Tobin (2019)
Grading Rubric for AI Applications with Sergey Karayev (2019)
Applied Deep Learning - Data Management with Josh Tobin (2019)
Snorkel: Programming Training Data with Paroma Varma of Stanford University (2019)
Applied Deep Learning - Troubleshooting and Debugging with Josh Tobin (2019)
Troubleshooting and Iterating ML Models with Lee Redden (2019)
Pieter Abeel on Potential Deep Learning Research Directions (2019)
Applied Deep Learning - Rosanne Liu on AI Research (2019)
Designing a Machine Learning Project with Neal Khosla (2019)
Lukas Beiwald on ML Tools and Experiment Management (2019)
Building Machine Learning Teams with Josh Tobin (2019)
Testing and Deployment of Deep Learning Models with Josh Tobin (2019)
Five Lessons for Team-Oriented Research with Peter Welder (2019)