Fine-tuning Mysteries
Kyunghyun Cho discusses the mysteries surrounding fine-tuning and pretraining in deep learning. He explores the question of how a completely different loss function on a different dataset can inform the initial point for optimization on another dataset. Discover the insights behind this intriguing topic.In this clip
From this podcast
The Gradient
Kyunghyun Cho: Neural Machine Translation, Language, and Doing Good Science
Related Questions