Toronto Machine Learning Series (TMLS)
Unraveling Long Context: Existing Methods, Challenges, and Future Directions
Explore the complexities of scaling transformer models for longer context, examining current methodologies, implementation hurdles, and emerging solutions in AI development.
YouTube32 minutesSelf-pacedFree video
Google TechTalks
Accelerating Transformers via Kernel Density Estimation - Google TechTalk
Explore efficient Transformer acceleration using kernel density estimation. Learn innovative techniques for handling long sequences and improving performance in deep learning models.
YouTube53 minutesSelf-pacedFree video
Alexander Amini
MIT 6.S191 - Recurrent Neural Networks
Comprehensive lecture on Recurrent Neural Networks, covering theory, implementation, and applications. Explores sequence modeling, LSTM, attention mechanisms, and practical examples in deep learning.
YouTube1 hour 1 minuteSelf-pacedFree video
Center for Language & Speech Processing(CLSP), JHU
Toward Length Extrapolatable Transformers
Explore innovative techniques for enhancing transformer models' ability to handle longer sequences, improving their performance and scalability in natural language processing tasks.
YouTube1 hour 5 minutesSelf-pacedFree video