ArtificialIntelligenceArticles
3.03K subscribers
1.64K photos
9 videos
5 files
3.86K links
for who have a passion for -
1. #ArtificialIntelligence
2. Machine Learning
3. Deep Learning
4. #DataScience
5. #Neuroscience

6. #ResearchPapers

7. Related Courses and Ebooks
Download Telegram
Understanding & Generalizing AlphaGo Zero #ICLR2019

Anonymous: https://openreview.net/forum?id=rkxtl3C5YX
Search ICLR 2019

Having trouble finding the papers that use technique X, dataset D, or cite author ME in the #ICLR2019 submissions?

Search ICLR 2019: http://search.iclr2019.smerity.com/
#RP Mariya Toneva, Excited to present our work on understanding catastrophic example forgetting at ICLR on Wednesday from 11-1pm! Poster #44. Joint work with Alessandro Sordoni, Remi Tachet, Adam Trischler, Yoshua Bengio, and Geoff Gordon
Paper: http://bit.ly/2H8yQUg
Code: http://bit.ly/2vMH6mw

#ICLR #ICLR2019 #MachineLearning
An Empirical Study of Example Forgetting During Deep Neural Network Learning
Joint work with Alessandro Sordoni, Remi Tachet, Adam Trischler, Yoshua Bengio, and Geoff Gordon

Paper: http://bit.ly/2H8yQUg
Code: http://bit.ly/2vMH6mw

#ICLR #ICLR2019 #MachineLearning
ICLR 2019 posters
By Jonathan Binas and Avital Oliver: https://postersession.ai
#deeplearning #ICLR2019 #technology
Deep Convolutional Networks as Shallow Gaussian Processes #iclr2019
By @AdriGarriga

The kernel equivalent to a 32-layer ResNet obtains 0.84% classification error on
MNIST, SoTA for GPs with comparable params size

Github
https://github.com/convnets-as-gps/convnets-as-gps
ArXiv
https://arxiv.org/abs/1808.05587
Best research paper award at our Debugging ML workshop -- "Similarity of Neural Network Representations Revisited" by Geoffrey Hinton , Mohammad Norouzi, Honglak Lee, and Simon Kornblith
https://arxiv.org/abs/1905.00414
#ICLR2019 https://t.me/ArtificialIntelligenceArticles
Top 8 trends from ICLR 2019

Overview of trends on #ICLR2019:
1. Inclusivity
2. Unsupervised representation learning & transfer learning
3. Retro ML
4. RNN is losing its luster with researchers
5. GANs are still going on strong
6. The lack of biologically inspired deep learning
7. Reinforcement learning is still the most popular topic by submissions
8. Most accepted papers will be quickly forgotten

Link: https://huyenchip.com/2019/05/12/top-8-trends-from-iclr-2019.html