I am currently a Senior Research Scientist on the Google Brain team. Previously I worked at the Information Sciences Institute with professors Kevin Knight and Daniel Marcu on topics related to neural network machine translation.
Publications
“AutoAugment: Learning Augmentation Policies from Data”
(Ekin D. Cubuk*, Barret Zoph*, Dandelion Mane, Vijay Vasudevan, Quoc V. Le), ArXiv, 2018.
(Ekin D. Cubuk*, Barret Zoph*, Dandelion Mane, Vijay Vasudevan, Quoc V. Le), ArXiv, 2018.
“Efficient Neural Architecture Search via Parameter Sharing”
(Hieu Pham, Melody Y. Guan, Barret Zoph, Quoc V. Le, Jeff Dean), ArXiv, 2018.
(Hieu Pham, Melody Y. Guan, Barret Zoph, Quoc V. Le, Jeff Dean), ArXiv, 2018.
“Progressive Neural Architecture Search”
(C. Liu, B. Zoph, J. Shlens, W. Hua, Li-Jia Li, Li Fei-Fei, A. Yuille, J. Huang, K. Murphy), ArXiv, 2017.
(C. Liu, B. Zoph, J. Shlens, W. Hua, Li-Jia Li, Li Fei-Fei, A. Yuille, J. Huang, K. Murphy), ArXiv, 2017.
“Searching for activation functions”
(Prajit Ramachandran, Barret Zoph, Quoc V. Le), ArXiv, 2017.
(Prajit Ramachandran, Barret Zoph, Quoc V. Le), ArXiv, 2017.
“Intriguing Properties of Adversarial Examples”
(Ekin D. Cubuk, Barret Zoph, Samuel S. Schoenholz, Quoc V. Le), ArXiv, 2017.
(Ekin D. Cubuk, Barret Zoph, Samuel S. Schoenholz, Quoc V. Le), ArXiv, 2017.
“Learning Transferable Architectures for Scalable Image Recognition”
(Barret Zoph , Vijay Vasudevan, Jonathan Shlens, Quoc V. Le), CVPR, 2018. (Spotlight)
(Barret Zoph , Vijay Vasudevan, Jonathan Shlens, Quoc V. Le), CVPR, 2018. (Spotlight)
“Neural Optimizer Search with Reinforcement Learning”
(Irwan Bello*, Barret Zoph*, Vijay Vasudevan, Quoc V. Le), ICML, 2017.
(Irwan Bello*, Barret Zoph*, Vijay Vasudevan, Quoc V. Le), ICML, 2017.
“Neural Architecture Search with Reinforcement Learning”
(Barret Zoph , Quoc V. Le), ICLR, 2017. (Oral)
(Barret Zoph , Quoc V. Le), ICLR, 2017. (Oral)
“Transfer Learning for Low-Resource Neural Machine Translation”
(Barret Zoph , Deniz Yuret, Jonathan May, Kevin Knight), EMNLP, 2016.
(Barret Zoph , Deniz Yuret, Jonathan May, Kevin Knight), EMNLP, 2016.
“Simple, Fast Noise-Contrastive Estimation for Large RNN Vocabularies”
(Barret Zoph , Ashish Vaswani, Jonathan May, Kevin Knight), Proc. NAACL, 2016.
(Barret Zoph , Ashish Vaswani, Jonathan May, Kevin Knight), Proc. NAACL, 2016.
“Multi-Source Neural Translation”
(Barret Zoph , Kevin Knight), Proc. NAACL, 2016. (Oral)
(Barret Zoph , Kevin Knight), Proc. NAACL, 2016. (Oral)
“How Much Information Does a Human Translator Add to the Original?”
(Barret Zoph , Marjan Ghazvininejad, Kevin Knight), Proc. EMNLP, 2015. (Oral)
(Barret Zoph , Marjan Ghazvininejad, Kevin Knight), Proc. EMNLP, 2015. (Oral)
Talks/Media
- New York Times: Building A.I. That Can Build A.I.
- Technology Review Article on AutoML/Neural Architecture Search
- Google Research Blog Post on AutoAugment
- Google Research Blog Post on Neural Architecture Search
- Second Google Research Blog Post on AutoML/Neural Architecture Search
- Guest Lecture for UC Berkeley's class CS 294: Deep Reinforcement Learning
- Talk on AutoML for Decentralized AI conference
Toolkits
A GPU Recurrent Neural Network Toolkit Github
- Supports multi-layered LSTM RNNs
- Allows for model parallelization across multiple GPUs
- Handles different loss functions such as MLE and NCE