Using AI to generate recipes from food images

Facebook developed image 2 recipe architecture.

Paper: https://research.fb.com/publications/inverse-cooking-recipe-generation-from-food-images/
Code: https://github.com/facebookresearch/inversecooking


Link: https://ai.facebook.com/blog/inverse-cooking/

#CV #DL

AlphaStar: Mastering the Game of StarCraft II
Talk by David Silver: https://slideslive.com/38916905/alphastar-mastering-the-game-of-starcraft-ii
#ArtificialIntelligence #DeepLearning #ReinforcementLearning

Deeplearning. Ai ===>> Deep learners: how do you best learn besides taking courses?

The Challenge of Open Source MT
https://www.cms-connected.com/News-Archive/June-2019/The-Challenge-of-Open-Source-Machine-Translation#.XQjjqDevkh4.twitter

Stand-Alone Self-Attention in Vision Models

Ramachandran et al.: https://arxiv.org/abs/1906.05909

#ArtificialIntelligence #DeepLearning #MachineLearning

From CVPR 2019: Turning Doodles into Stunning, Photorealistic Landscapes.

NVIDIA research harnesses generative adversarial networks to create highly realistic scenes.

Artists can use paintbrush and paint bucket tools to design their own landscapes with labels like river, rock and cloud

https://www.profillic.com/paper/arxiv:1903.07291

STEAL, a new algorithm developed by NVIDIA Research and being presented this week at #CVPR2019, automatically refines the boundaries of objects in training datasets, making them more exact.

Link to the blog: https://news.developer.nvidia.com/nvidia-research-released-at-cvpr-helps-developers-create-better-visual-datasets/

#CVPR 2019 Online Videos

https://www.youtube.com/channel/UC0n76gicaarsN_Y9YShWwhw/videos

Best Paper Award at the AI for social good Workshop at #ICML2019 https://medium.com/@jasonphang/deep-neural-networks-improve-radiologists-performance-in-breast-cancer-screening-565eb2bd3c9f

[code] https://github.com/nyukat/breast_cancer_classifier
[preprint] https://arxiv.org/pdf/1903.08297.pdf
[data specs] https://cs.nyu.edu/~kgeras/reports/datav1.0.pdf
[ICML '19] https://aiforsocialgood.github.io/icml2019/acceptedpapers.htm

New Paper:
Stand-Alone Self-Attention in Vision Models
https://arxiv.org/abs/1906.05909

Can attention work as a stand-alone primitive for vision models?
We develop a pure self-attention model by replacing the spatial convolutions in a ResNet by a simple, local self-attention layer.

MIT neuroscientists have performed the most rigorous testing yet of computational models that mimic the brain’s visual cortex.

Using their current best model of the brain’s visual neural network, the researchers designed a new way to precisely control individual neurons and populations of neurons in the middle of that network. In an animal study, the team then showed that the information gained from the computational model enabled them to create images that strongly activated specific brain neurons of their choosing.

The findings suggest that the current versions of these models are similar enough to the brain that they could be used to control brain states in animals. The study also helps to establish the usefulness of these vision models, which have generated vigorous debate over whether they accurately mimic how the visual cortex works, says James DiCarlo, the head of MIT’s Department of Brain and Cognitive Sciences, an investigator in the McGovern Institute for Brain Research and the Center for Brains, Minds, and Machines, and the senior author of the study.



Full article: https://news.mit.edu/2019/computer-model-brain-visual-cortex-0502

Science paper: https://science.sciencemag.org/content/364/6439/eaav9436

Biorxiv (open access): https://www.biorxiv.org/content/10.1101/461525v1

https://t.iss.one/ArtificialIntelligenceArticles

Can deep neural networks help cognitive scientists understand the brain?

Radoslaw M. Cichy & Daniel Kaiser discuss the value of DNNs as scientific models in a new TICS Opinion piece.

https://www.cell.com/trends/cognitive-sciences/fulltext/S1364-6613(19)30034-8 https://t.iss.one/ArtificialIntelligenceArticles

The future depends on some graduate student who is deeply suspicious of everything I have said. - Geoffrey Hinton https://t.iss.one/ArtificialIntelligenceArticles

Long Short-Term Memory: From Zero to Hero with PyTorch
https://blog.floydhub.com/long-short-term-memory-from-zero-to-hero-with-pytorch/

Efficient Exploration via State Marginal Matching

Lee et al.

Blog: https://sites.google.com/view/state-marginal-matching
Paper: https://arxiv.org/abs/1906.05274
Code: https://github.com/RLAgent/state-marginal-matching

#ArtificialIntelligence #MachineLearning #ReinforcementLearning

Learning the Depths of Moving People by Watching Frozen People

Li et al.: https://openaccess.thecvf.com/content_CVPR_2019/papers/Li_Learning_the_Depths_of_Moving_People_by_Watching_Frozen_People_CVPR_2019_paper.pdf

#ArtificialIntelligence #DeepLearning #MachineLearning

Theoretical Physics for Deep Learning workshop at #ICML2019

Slides and videos: https://sites.google.com/view/icml2019phys4dl/schedule?authuser=0

#Physics #DeepLearning