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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Every Model Learned by Gradient Descent Is Approximately a Kernel Machine


Nov 30, 2020
Pedro Domingos

* 12 pages, 2 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Amodal 3D Reconstruction for Robotic Manipulation via Stability and Connectivity


Sep 28, 2020
William Agnew, Christopher Xie, Aaron Walsman, Octavian Murad, Caelen Wang, Pedro Domingos, Siddhartha Srinivasa


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Self-Supervised Object-Level Deep Reinforcement Learning


Mar 03, 2020
William Agnew, Pedro Domingos


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Deep Learning as a Mixed Convex-Combinatorial Optimization Problem


Apr 16, 2018
Abram L. Friesen, Pedro Domingos

* In Proceedings of the International Conference on Learning Representations (ICLR) 2018 
* 14 pages (9 body, 5 pages of references and appendices) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Neural-Symbolic Learning and Reasoning: A Survey and Interpretation


Nov 10, 2017
Tarek R. Besold, Artur d'Avila Garcez, Sebastian Bader, Howard Bowman, Pedro Domingos, Pascal Hitzler, Kai-Uwe Kuehnberger, Luis C. Lamb, Daniel Lowd, Priscila Machado Vieira Lima, Leo de Penning, Gadi Pinkas, Hoifung Poon, Gerson Zaverucha

* 58 pages, work in progress 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

The Sum-Product Theorem: A Foundation for Learning Tractable Models


Nov 11, 2016
Abram L. Friesen, Pedro Domingos

* Proceedings of the 33rd International Conference on Machine Learning, pp. 1909-1918, 2016 
* 15 pages (10 body, 5 pages of appendices) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Recursive Decomposition for Nonconvex Optimization


Nov 08, 2016
Abram L. Friesen, Pedro Domingos

* Proceedings of the 24th International Joint Conference on Artificial Intelligence (2015), pp. 253-259 
* 11 pages, 7 figures, pdflatex 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

On the Latent Variable Interpretation in Sum-Product Networks


Oct 28, 2016
Robert Peharz, Robert Gens, Franz Pernkopf, Pedro Domingos

* Revised version, accepted for publication in IEEE Transactions on Machine Intelligence and Pattern Analysis (TPAMI). Shortened and revised Section 4: Thanks to our reviewers, pointing out that Theorem 2 holds for selective SPNs. Added paragraph in Section 2.1, relating sizes of original/augmented SPNs. Fixed typos, rephrased sentences, revised references 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Learning Tractable Probabilistic Models for Fault Localization


Jul 07, 2015
Aniruddh Nath, Pedro Domingos

* Fifth International Workshop on Statistical Relational AI (StaR-AI 2015) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Exchangeable Variable Models


May 02, 2014
Mathias Niepert, Pedro Domingos

* ICML 2014 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>