1.8k citations
- Google DeepMind (United Kingdom)GB73 papers
- Google (United States)US34 papers
- University College LondonGB13 papers
- Massachusetts Institute of TechnologyUS12 papers
- Institut national de recherche en sciences et technologies du numériqueFR9 papers
- Imperial College LondonGB8 papers
- ETH ZurichCH7 papers
- Stanford UniversityUS7 papers
- University of WashingtonUS7 papers
- Carnegie Mellon UniversityUS6 papers
- University of OxfordGB6 papers
- École Normale Supérieure - PSLFR5 papers
6 papers · 1 filter
Deep learning for predicting refractive error from retinal fundus images
Avinash V. Varadarajan, Ryan Poplin, Katy Blumer +7
Refractive error, one of the leading cause of visual impairment, can be corrected by simple interventions like prescribing eyeglasses. We trained a deep learning algorithm to predi…
The Devil is in the Decoder: Classification, Regression and GANs
Zbigniew Wojna, Vittorio Ferrari, Sergio Guadarrama +4
Many machine vision applications, such as semantic segmentation and depth prediction, require predictions for every pixel of the input image. Models for such problems usually consi…
Automated Curriculum Learning for Neural Networks
Alex Graves, Marc G. Bellemare, Jacob Menick +2
We introduce a method for automatically selecting the path, or syllabus, that a neural network follows through a curriculum so as to maximise learning efficiency. A measure of the…
Multitask Learning with CTC and Segmental CRF for Speech Recognition
Liang Lu, Lingpeng Kong, Chris Dyer +1
Segmental conditional random fields (SCRFs) and connectionist temporal classification (CTC) are two sequence labeling methods used for end-to-end training of speech recognition mod…
Machine learning prediction errors better than DFT accuracy
Felix A. Faber, Luke Hutchison, Bing Huang +7
We investigate the impact of choosing regressors and molecular representations for the construction of fast machine learning (ML) models of thirteen electronic ground-state propert…
Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models
Louis Shao, Stephan Gouws, Denny Britz +3
Sequence-to-sequence models have been applied to the conversation response generation problem where the source sequence is the conversation history and the target sequence is the r…