Multi-task Neural Networks for QSAR Predictions
Jun 04, 2014
George E. Dahl, Navdeep Jaitly, Ruslan Salakhutdinov
Jun 04, 2014
George E. Dahl, Navdeep Jaitly, Ruslan Salakhutdinov




Click to Read Paper
Incorporating Side Information in Probabilistic Matrix Factorization with Gaussian Processes
Aug 09, 2014
Ryan Prescott Adams, George E. Dahl, Iain Murray
Aug 09, 2014
Ryan Prescott Adams, George E. Dahl, Iain Murray




* Appears in Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI2010)
Click to Read Paper
Training Restricted Boltzmann Machines on Word Observations
Jul 05, 2012
George E. Dahl, Ryan P. Adams, Hugo Larochelle
Jul 05, 2012
George E. Dahl, Ryan P. Adams, Hugo Larochelle




Click to Read Paper
The Importance of Generation Order in Language Modeling
Aug 23, 2018
Nicolas Ford, Daniel Duckworth, Mohammad Norouzi, George E. Dahl
Aug 23, 2018
Nicolas Ford, Daniel Duckworth, Mohammad Norouzi, George E. Dahl


Click to Read Paper
Parallel Architecture and Hyperparameter Search via Successive Halving and Classification
May 25, 2018
Manoj Kumar, George E. Dahl, Vijay Vasudevan, Mohammad Norouzi
May 25, 2018
Manoj Kumar, George E. Dahl, Vijay Vasudevan, Mohammad Norouzi




Click to Read Paper
Motivating the Rules of the Game for Adversarial Example Research
Jul 20, 2018
Justin Gilmer, Ryan P. Adams, Ian Goodfellow, David Andersen, George E. Dahl
Jul 20, 2018
Justin Gilmer, Ryan P. Adams, Ian Goodfellow, David Andersen, George E. Dahl




Click to Read Paper
Characterizing Diabetes, Diet, Exercise, and Obesity Comments on Twitter
Sep 22, 2017
Amir Karami, Alicia A. Dahl, Gabrielle Turner-McGrievy, Hadi Kharrazi, Jr. George Shaw
Sep 22, 2017
Amir Karami, Alicia A. Dahl, Gabrielle Turner-McGrievy, Hadi Kharrazi, Jr. George Shaw




* International Journal of Information Management (2017)
Click to Read Paper
Embedding Text in Hyperbolic Spaces
Jun 12, 2018
Bhuwan Dhingra, Christopher J. Shallue, Mohammad Norouzi, Andrew M. Dai, George E. Dahl
Jun 12, 2018
Bhuwan Dhingra, Christopher J. Shallue, Mohammad Norouzi, Andrew M. Dai, George E. Dahl




* TextGraphs 2018
Click to Read Paper
Large scale distributed neural network training through online distillation
Apr 09, 2018
Rohan Anil, Gabriel Pereyra, Alexandre Passos, Robert Ormandi, George E. Dahl, Geoffrey E. Hinton
Apr 09, 2018
Rohan Anil, Gabriel Pereyra, Alexandre Passos, Robert Ormandi, George E. Dahl, Geoffrey E. Hinton


Click to Read Paper
Neural Message Passing for Quantum Chemistry
Jun 12, 2017
Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, George E. Dahl
Jun 12, 2017
Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, George E. Dahl




* 14 pages
Click to Read Paper
Measuring the Effects of Data Parallelism on Neural Network Training
Nov 21, 2018
Christopher J. Shallue, Jaehoon Lee, Joseph Antognini, Jascha Sohl-Dickstein, Roy Frostig, George E. Dahl
Nov 21, 2018
Christopher J. Shallue, Jaehoon Lee, Joseph Antognini, Jascha Sohl-Dickstein, Roy Frostig, George E. Dahl




* Submitted to JMLR
Click to Read Paper
Improvements to deep convolutional neural networks for LVCSR
Dec 10, 2013
Tara N. Sainath, Brian Kingsbury, Abdel-rahman Mohamed, George E. Dahl, George Saon, Hagen Soltau, Tomas Beran, Aleksandr Y. Aravkin, Bhuvana Ramabhadran
Dec 10, 2013
Tara N. Sainath, Brian Kingsbury, Abdel-rahman Mohamed, George E. Dahl, George Saon, Hagen Soltau, Tomas Beran, Aleksandr Y. Aravkin, Bhuvana Ramabhadran




* 6 pages, 1 figure
Click to Read Paper
Peptide-Spectra Matching from Weak Supervision
Aug 22, 2018
Samuel S. Schoenholz, Sean Hackett, Laura Deming, Eugene Melamud, Navdeep Jaitly, Fiona McAllister, Jonathon O'Brien, George Dahl, Bryson Bennett, Andrew M. Dai, Daphne Koller
Aug 22, 2018
Samuel S. Schoenholz, Sean Hackett, Laura Deming, Eugene Melamud, Navdeep Jaitly, Fiona McAllister, Jonathon O'Brien, George Dahl, Bryson Bennett, Andrew M. Dai, Daphne Koller




Click to Read Paper
Detecting Cancer Metastases on Gigapixel Pathology Images
Mar 08, 2017
Yun Liu, Krishna Gadepalli, Mohammad Norouzi, George E. Dahl, Timo Kohlberger, Aleksey Boyko, Subhashini Venugopalan, Aleksei Timofeev, Philip Q. Nelson, Greg S. Corrado, Jason D. Hipp, Lily Peng, Martin C. Stumpe
Each year, the treatment decisions for more than 230,000 breast cancer patients in the U.S. hinge on whether the cancer has metastasized away from the breast. Metastasis detection is currently performed by pathologists reviewing large expanses of biological tissues. This process is labor intensive and error-prone. We present a framework to automatically detect and localize tumors as small as 100 x 100 pixels in gigapixel microscopy images sized 100,000 x 100,000 pixels. Our method leverages a convolutional neural network (CNN) architecture and obtains state-of-the-art results on the Camelyon16 dataset in the challenging lesion-level tumor detection task. At 8 false positives per image, we detect 92.4% of the tumors, relative to 82.7% by the previous best automated approach. For comparison, a human pathologist attempting exhaustive search achieved 73.2% sensitivity. We achieve image-level AUC scores above 97% on both the Camelyon16 test set and an independent set of 110 slides. In addition, we discover that two slides in the Camelyon16 training set were erroneously labeled normal. Our approach could considerably reduce false negative rates in metastasis detection.
Mar 08, 2017
Yun Liu, Krishna Gadepalli, Mohammad Norouzi, George E. Dahl, Timo Kohlberger, Aleksey Boyko, Subhashini Venugopalan, Aleksei Timofeev, Philip Q. Nelson, Greg S. Corrado, Jason D. Hipp, Lily Peng, Martin C. Stumpe
* Fig 1: normal and tumor patches were accidentally reversed - now fixed. Minor grammatical corrections in appendix, section "Image Color Normalization"
Click to Read Paper
Relational inductive biases, deep learning, and graph networks
Oct 17, 2018
Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Vinicius Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Ryan Faulkner, Caglar Gulcehre, Francis Song, Andrew Ballard, Justin Gilmer, George Dahl, Ashish Vaswani, Kelsey Allen, Charles Nash, Victoria Langston, Chris Dyer, Nicolas Heess, Daan Wierstra, Pushmeet Kohli, Matt Botvinick, Oriol Vinyals, Yujia Li, Razvan Pascanu
Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, in part, to cheap data and cheap compute resources, which have fit the natural strengths of deep learning. However, many defining characteristics of human intelligence, which developed under much different pressures, remain out of reach for current approaches. In particular, generalizing beyond one's experiences--a hallmark of human intelligence from infancy--remains a formidable challenge for modern AI. The following is part position paper, part review, and part unification. We argue that combinatorial generalization must be a top priority for AI to achieve human-like abilities, and that structured representations and computations are key to realizing this objective. Just as biology uses nature and nurture cooperatively, we reject the false choice between "hand-engineering" and "end-to-end" learning, and instead advocate for an approach which benefits from their complementary strengths. We explore how using relational inductive biases within deep learning architectures can facilitate learning about entities, relations, and rules for composing them. We present a new building block for the AI toolkit with a strong relational inductive bias--the graph network--which generalizes and extends various approaches for neural networks that operate on graphs, and provides a straightforward interface for manipulating structured knowledge and producing structured behaviors. We discuss how graph networks can support relational reasoning and combinatorial generalization, laying the foundation for more sophisticated, interpretable, and flexible patterns of reasoning. As a companion to this paper, we have released an open-source software library for building graph networks, with demonstrations of how to use them in practice.
Oct 17, 2018
Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Vinicius Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Ryan Faulkner, Caglar Gulcehre, Francis Song, Andrew Ballard, Justin Gilmer, George Dahl, Ashish Vaswani, Kelsey Allen, Charles Nash, Victoria Langston, Chris Dyer, Nicolas Heess, Daan Wierstra, Pushmeet Kohli, Matt Botvinick, Oriol Vinyals, Yujia Li, Razvan Pascanu
Click to Read Paper