Modules and Architectures
Offered By: Alfredo Canziani via YouTube
Course Description
Overview
Explore key concepts in deep learning through this comprehensive lecture covering non-linear functions, softargmax and softargmin, logsoftargmax, cost functions, and various architectures. Delve into multiplicative interaction, mixture of experts, and parameter transformations. Gain valuable insights from renowned speaker Yann LeCun as he guides you through essential topics in neural network design and optimization. Perfect for those seeking to deepen their understanding of advanced deep learning concepts and architectures.
Syllabus
– Welcome to class
– Non-linear functions
– Q&A
– Softargmax and softargmin
– Logsoftargmax
– Cost functions
– Architectures: multiplicative interaction
– Mixture of experts
– Parameter transformations
Taught by
Alfredo Canziani
Tags
Related Courses
GShard- Scaling Giant Models with Conditional Computation and Automatic ShardingYannic Kilcher via YouTube Learning Mixtures of Linear Regressions in Subexponential Time via Fourier Moments
Association for Computing Machinery (ACM) via YouTube Stanford Seminar - Mixture of Experts Paradigm and the Switch Transformer
Stanford University via YouTube Decoding Mistral AI's Large Language Models - Building Blocks and Training Strategies
Databricks via YouTube Pioneering a Hybrid SSM Transformer Architecture - Jamba Foundation Model
Databricks via YouTube