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 Akram Erraqabi

Akram Erraqabi
Alert button

Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints


Aug 08, 2022
Jose Gallego-Posada, Juan Ramirez, Akram Erraqabi, Yoshua Bengio, Simon Lacoste-Julien

Add code
Alert button

Figure 1 for Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints
Figure 2 for Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints
Figure 3 for Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints
Figure 4 for Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints
* Code available at https://github.com/gallego-posada/constrained_sparsity 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL


Mar 21, 2022
Akram Erraqabi, Marlos C. Machado, Mingde Zhao, Sainbayar Sukhbaatar, Alessandro Lazaric, Ludovic Denoyer, Yoshua Bengio

Add code
Alert button

Figure 1 for Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL
Figure 2 for Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL
Figure 3 for Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL
Figure 4 for Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A3T: Adversarially Augmented Adversarial Training


Jan 12, 2018
Akram Erraqabi, Aristide Baratin, Yoshua Bengio, Simon Lacoste-Julien

Add code
Alert button

Figure 1 for A3T: Adversarially Augmented Adversarial Training
Figure 2 for A3T: Adversarially Augmented Adversarial Training
Figure 3 for A3T: Adversarially Augmented Adversarial Training
* accepted for an oral presentation in Machine Deception Workshop, NIPS 2017 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Image Segmentation by Iterative Inference from Conditional Score Estimation


Aug 18, 2017
Adriana Romero, Michal Drozdzal, Akram Erraqabi, Simon Jégou, Yoshua Bengio

Add code
Alert button

Figure 1 for Image Segmentation by Iterative Inference from Conditional Score Estimation
Figure 2 for Image Segmentation by Iterative Inference from Conditional Score Estimation
Figure 3 for Image Segmentation by Iterative Inference from Conditional Score Estimation
Figure 4 for Image Segmentation by Iterative Inference from Conditional Score Estimation

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Diet Networks: Thin Parameters for Fat Genomics


Mar 16, 2017
Adriana Romero, Pierre Luc Carrier, Akram Erraqabi, Tristan Sylvain, Alex Auvolat, Etienne Dejoie, Marc-André Legault, Marie-Pierre Dubé, Julie G. Hussin, Yoshua Bengio

Add code
Alert button

Figure 1 for Diet Networks: Thin Parameters for Fat Genomics
Figure 2 for Diet Networks: Thin Parameters for Fat Genomics
Figure 3 for Diet Networks: Thin Parameters for Fat Genomics
Figure 4 for Diet Networks: Thin Parameters for Fat Genomics
* ICLR 2017 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

On Random Weights for Texture Generation in One Layer Neural Networks


Dec 19, 2016
Mihir Mongia, Kundan Kumar, Akram Erraqabi, Yoshua Bengio

Add code
Alert button

Figure 1 for On Random Weights for Texture Generation in One Layer Neural Networks
* ICASSP 2017 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email