Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for David Rolnick

David Rolnick

MIT

Techniques for Symbol Grounding with SATNet


Jun 16, 2021
Sever Topan, David Rolnick, Xujie Si

Figure 1 for Techniques for Symbol Grounding with SATNet
Figure 2 for Techniques for Symbol Grounding with SATNet
Figure 3 for Techniques for Symbol Grounding with SATNet
Figure 4 for Techniques for Symbol Grounding with SATNet
* Code available at https://github.com/SeverTopan/SATNet 
  Access Paper or Ask Questions

DC3: A learning method for optimization with hard constraints


Apr 25, 2021
Priya L. Donti, David Rolnick, J. Zico Kolter

Figure 1 for DC3: A learning method for optimization with hard constraints
Figure 2 for DC3: A learning method for optimization with hard constraints
Figure 3 for DC3: A learning method for optimization with hard constraints
Figure 4 for DC3: A learning method for optimization with hard constraints
* International Conference on Learning Representations 2021 
 * In ICLR 2021. Code available at https://github.com/locuslab/DC3 
  Access Paper or Ask Questions

Geo-Spatiotemporal Features and Shape-Based Prior Knowledge for Fine-grained Imbalanced Data Classification


Mar 21, 2021
Charles A. Kantor, Marta Skreta, Brice Rauby, Léonard Boussioux, Emmanuel Jehanno, Alexandra Luccioni, David Rolnick, Hugues Talbot

Figure 1 for Geo-Spatiotemporal Features and Shape-Based Prior Knowledge for Fine-grained Imbalanced Data Classification
Figure 2 for Geo-Spatiotemporal Features and Shape-Based Prior Knowledge for Fine-grained Imbalanced Data Classification
Figure 3 for Geo-Spatiotemporal Features and Shape-Based Prior Knowledge for Fine-grained Imbalanced Data Classification
* Proc. IJCAI 2021, Workshop on AI for Social Good, Harvard University (2021) 
 * Copyright by the authors. All rights reserved to authors only. Correspondence to: ckantor (at) stanford [dot] edu 
  Access Paper or Ask Questions

Deep ReLU Networks Preserve Expected Length


Feb 21, 2021
Boris Hanin, Ryan Jeong, David Rolnick

Figure 1 for Deep ReLU Networks Preserve Expected Length
Figure 2 for Deep ReLU Networks Preserve Expected Length
Figure 3 for Deep ReLU Networks Preserve Expected Length
Figure 4 for Deep ReLU Networks Preserve Expected Length
* 25 pages, 5 figures 
  Access Paper or Ask Questions

Identifying Weights and Architectures of Unknown ReLU Networks


Oct 02, 2019
David Rolnick, Konrad P. Kording

Figure 1 for Identifying Weights and Architectures of Unknown ReLU Networks
Figure 2 for Identifying Weights and Architectures of Unknown ReLU Networks
Figure 3 for Identifying Weights and Architectures of Unknown ReLU Networks
Figure 4 for Identifying Weights and Architectures of Unknown ReLU Networks
* 15 pages, 4 figures 
  Access Paper or Ask Questions

Tackling Climate Change with Machine Learning


Jun 10, 2019
David Rolnick, Priya L. Donti, Lynn H. Kaack, Kelly Kochanski, Alexandre Lacoste, Kris Sankaran, Andrew Slavin Ross, Nikola Milojevic-Dupont, Natasha Jaques, Anna Waldman-Brown, Alexandra Luccioni, Tegan Maharaj, Evan D. Sherwin, S. Karthik Mukkavilli, Konrad P. Kording, Carla Gomes, Andrew Y. Ng, Demis Hassabis, John C. Platt, Felix Creutzig, Jennifer Chayes, Yoshua Bengio

Figure 1 for Tackling Climate Change with Machine Learning

  Access Paper or Ask Questions

Deep ReLU Networks Have Surprisingly Few Activation Patterns


Jun 03, 2019
Boris Hanin, David Rolnick

Figure 1 for Deep ReLU Networks Have Surprisingly Few Activation Patterns
Figure 2 for Deep ReLU Networks Have Surprisingly Few Activation Patterns
Figure 3 for Deep ReLU Networks Have Surprisingly Few Activation Patterns
Figure 4 for Deep ReLU Networks Have Surprisingly Few Activation Patterns
* 18 page, 7 figures 
  Access Paper or Ask Questions

Complexity of Linear Regions in Deep Networks


Jan 25, 2019
Boris Hanin, David Rolnick

Figure 1 for Complexity of Linear Regions in Deep Networks
Figure 2 for Complexity of Linear Regions in Deep Networks
Figure 3 for Complexity of Linear Regions in Deep Networks
Figure 4 for Complexity of Linear Regions in Deep Networks

  Access Paper or Ask Questions

Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics


Dec 04, 2018
Yaron Meirovitch, Lu Mi, Hayk Saribekyan, Alexander Matveev, David Rolnick, Casimir Wierzynski, Nir Shavit

Figure 1 for Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics
Figure 2 for Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics
Figure 3 for Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics
Figure 4 for Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics
* 10 pages, 10 figures 
  Access Paper or Ask Questions

Experience Replay for Continual Learning


Nov 28, 2018
David Rolnick, Arun Ahuja, Jonathan Schwarz, Timothy P. Lillicrap, Greg Wayne

Figure 1 for Experience Replay for Continual Learning
Figure 2 for Experience Replay for Continual Learning
Figure 3 for Experience Replay for Continual Learning
Figure 4 for Experience Replay for Continual Learning

  Access Paper or Ask Questions

How to Start Training: The Effect of Initialization and Architecture


Jun 19, 2018
Boris Hanin, David Rolnick

Figure 1 for How to Start Training: The Effect of Initialization and Architecture
Figure 2 for How to Start Training: The Effect of Initialization and Architecture
Figure 3 for How to Start Training: The Effect of Initialization and Architecture
Figure 4 for How to Start Training: The Effect of Initialization and Architecture
* v2. 15p. Comments welcome 
  Access Paper or Ask Questions

Measuring and regularizing networks in function space


May 21, 2018
Ari S. Benjamin, David Rolnick, Konrad Kording

Figure 1 for Measuring and regularizing networks in function space
Figure 2 for Measuring and regularizing networks in function space
Figure 3 for Measuring and regularizing networks in function space
Figure 4 for Measuring and regularizing networks in function space
* Submitted to to NIPS 2018 
  Access Paper or Ask Questions

The power of deeper networks for expressing natural functions


Apr 27, 2018
David Rolnick, Max Tegmark

Figure 1 for The power of deeper networks for expressing natural functions
Figure 2 for The power of deeper networks for expressing natural functions
* Replaced to match version published at ICLR 2018. 14 pages, 2 figs 
  Access Paper or Ask Questions

Deep Learning is Robust to Massive Label Noise


Feb 26, 2018
David Rolnick, Andreas Veit, Serge Belongie, Nir Shavit

Figure 1 for Deep Learning is Robust to Massive Label Noise
Figure 2 for Deep Learning is Robust to Massive Label Noise
Figure 3 for Deep Learning is Robust to Massive Label Noise
Figure 4 for Deep Learning is Robust to Massive Label Noise

  Access Paper or Ask Questions

Why does deep and cheap learning work so well?


Aug 03, 2017
Henry W. Lin, Max Tegmark, David Rolnick

Figure 1 for Why does deep and cheap learning work so well?
Figure 2 for Why does deep and cheap learning work so well?
Figure 3 for Why does deep and cheap learning work so well?
Figure 4 for Why does deep and cheap learning work so well?
* Replaced to match version published in Journal of Statistical Physics: https://link.springer.com/article/10.1007/s10955-017-1836-5 Improved refs & discussion, typos fixed. 16 pages, 3 figs 
  Access Paper or Ask Questions

Morphological Error Detection in 3D Segmentations


May 30, 2017
David Rolnick, Yaron Meirovitch, Toufiq Parag, Hanspeter Pfister, Viren Jain, Jeff W. Lichtman, Edward S. Boyden, Nir Shavit

Figure 1 for Morphological Error Detection in 3D Segmentations
Figure 2 for Morphological Error Detection in 3D Segmentations
Figure 3 for Morphological Error Detection in 3D Segmentations
Figure 4 for Morphological Error Detection in 3D Segmentations
* 13 pages, 6 figures 
  Access Paper or Ask Questions

A Multi-Pass Approach to Large-Scale Connectomics


Dec 07, 2016
Yaron Meirovitch, Alexander Matveev, Hayk Saribekyan, David Budden, David Rolnick, Gergely Odor, Seymour Knowles-Barley, Thouis Raymond Jones, Hanspeter Pfister, Jeff William Lichtman, Nir Shavit

Figure 1 for A Multi-Pass Approach to Large-Scale Connectomics
Figure 2 for A Multi-Pass Approach to Large-Scale Connectomics
Figure 3 for A Multi-Pass Approach to Large-Scale Connectomics
Figure 4 for A Multi-Pass Approach to Large-Scale Connectomics
* 18 pages, 10 figures 
  Access Paper or Ask Questions