Iterated Models: Expressive Power, Learning, and Chain of Thought
Offered By: Simons Institute via YouTube
Course Description
Overview
Explore the computational power and learning dynamics of iterated sequence-to-sequence models in this 54-minute lecture by Nati Srerbo from Toyota Technological Institute at Chicago. Delve into the concept of transformers as a computational model, focusing on systems that apply the same function at each step to generate the next token. Examine the expressive capabilities of these models, even with simple base classes, and investigate the sample and computational complexity of learning processes. Gain insights into both end-to-end learning and approaches that leverage the entire "chain of thought" in model training and inference.
Syllabus
Iterated Models: Expressive Power, Learning, and Chain of Thought
Taught by
Simons Institute
Related Courses
Simple Recurrent Neural Network with KerasCoursera Project Network via Coursera Deep Learning: Advanced Natural Language Processing and RNNs
Udemy Machine Translation
Great Learning via YouTube Tensorflow 2.0 | Recurrent Neural Networks, LSTMs, GRUs
Udemy Pytorch Transformers for Machine Translation
Aladdin Persson via YouTube