Curriculum Learning
A training strategy for recurrent neural networks, often called 'sort grad', where models are first trained on shorter, easier utterances and gradually exposed to longer, more difficult ones to improve optimization and prevent numerical issues.
Save the 2 videos on Curriculum Learning to your own pod.
Sign up free to keep building your knowledge base on Curriculum Learning as more episodes are added.
Videos Mentioning Curriculum Learning
Deep Learning for Speech Recognition (Adam Coates, Baidu)
Lex Fridman
A training strategy for recurrent neural networks, often called 'sort grad', where models are first trained on shorter, easier utterances and gradually exposed to longer, more difficult ones to improve optimization and prevent numerical issues.
Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 6 - Model Training
Stanford Online
A concept in machine learning that involves teaching a model in a progressive manner, starting with easier tasks (e.g., low-resolution images) before moving to harder ones.