Transfer learning
The most practical idea in modern deep learning: do not start from scratch. Inherit the features somebody else already learned.
2 steps
115 XP
A free account is needed
Start the lesson →
Sources
- Yosinski, J. et al. 2014 · How Transferable Are Features in Deep Neural Networks? · NeurIPS 2014
- Donahue, J. et al. 2014 · DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition · ICML 2014
- Howard, J. & Ruder, S. 2018 · Universal Language Model Fine-tuning (ULMFiT) · ACL 2018
- Devlin, J. et al. 2019 · BERT: Pre-training of Deep Bidirectional Transformers · NAACL 2019
ML Academy · an interactive machine learning course that runs in your browser ·
All lessons