Stanford Seminar 2022 - Self Attention and Non-Parametric Transformers
Offered By: Stanford University via YouTube
Course Description
Overview
Explore the origins and intuitions of Transformers, followed by an in-depth discussion on Non-Parametric Transformers (NPTs) in this Stanford seminar. Begin with a 15-minute overview of Transformer fundamentals by Aidan, a PhD student at Oxford and Cohere co-founder. Then, delve into the recently NeurIPs-accepted NPTs with Neil and Jannik, both PhD students at the University of Oxford. Gain insights into massive neural networks, Bayesian Deep Learning, Active Learning, and the application of non-parametric models with Transformers. Learn from these emerging researchers as they share their expertise in building and implementing advanced AI models.
Syllabus
CS25 I Stanford Seminar 2022 - Self Attention and Non-parametric transformers (NPTs)
Taught by
Stanford Online
Tags
Related Courses
Axial-DeepLab - Stand-Alone Axial-Attention for Panoptic SegmentationYannic Kilcher via YouTube Linformer - Self-Attention with Linear Complexity
Yannic Kilcher via YouTube Synthesizer - Rethinking Self-Attention in Transformer Models
Yannic Kilcher via YouTube The Narrated Transformer Language Model
Jay Alammar via YouTube Learning the Structure of EHR with Graph Convolutional Transformer - Edward Choi
Stanford University via YouTube