AutoML Towards Deep Learning: Optimizing Neural Architectures and Hyperparameters
Offered By: Toronto Machine Learning Series (TMLS) via YouTube
Course Description
Overview
Explore the future of deep learning and automated machine learning in this 57-minute conference talk by Professor Frank Hutter at the Toronto Machine Learning Series. Delve into the potential of AutoML to revolutionize deep learning systems by automating the optimization of neural architectures and hyperparameters. Learn about advances in joint optimization of meta-choices in deep learning pipelines, efficiency improvements in meta-optimization, and techniques for optimizing uncertainty estimates and robustness to data shift. Gain insights into how next-generation deep learning systems may provide a streamlined interface between domain experts and machine learning algorithms, potentially transforming the field of artificial intelligence.
Syllabus
AutoML Towards Deep Learning
Taught by
Toronto Machine Learning Series (TMLS)
Related Courses
Machine Learning Modeling Pipelines in ProductionDeepLearning.AI via Coursera MLOps for Scaling TinyML
Harvard University via edX Parameter Prediction for Unseen Deep Architectures - With First Author Boris Knyazev
Yannic Kilcher via YouTube SpineNet - Learning Scale-Permuted Backbone for Recognition and Localization
Yannic Kilcher via YouTube Synthetic Petri Dish - A Novel Surrogate Model for Rapid Architecture Search
Yannic Kilcher via YouTube