On the Fairness of Disentangled Representations
Locatello et al.: https://arxiv.org/abs/1905.13662
#ArtificialIntelligence #DeepLearning #MachineLearning

Luck Matters: Understanding Training Dynamics of Deep ReLU Networks
Tian et al.: https://arxiv.org/abs/1905.13405
#ArtificialIntelligence #DeepLearning #MachineLearning

Geoffrey Hinton Leads Google Brain Representation Similarity Index Research Aiming to Understand…

https://medium.com/syncedreview/geoffrey-hinton-leads-google-brain-representation-similarity-index-research-aiming-to-understand-b5d14bf77f49

New algorithm may help people store more pictures, share videos faster
https://news.psu.edu/story/576002/2019/05/29/research/new-algorithm-may-help-people-store-more-pictures-share-videos

How to create your first Sequential model in Python (w/ Py code) using Colab (link: https://github.com/gcosma/DeepLearningTutorials/blob/master/SimpleSequentialModelColab.ipynb) #DataScience #DeepLearning #MachineLearning #AI
@GoogleColab

Very proud to announce new work from the
@DeepMindAI
cognition team, bridging the gap between #DeepLearning and symbolic #AI, with Marta Garnelo, Kyriacos Nikiforou,
@ToniCreswell
, Christos Kaplanis, and
@dgbarrett
arxiv.org/abs/1905.10307

An outstanding Nature Medicine
guide to deep learning in healthcare, including computer vision, natural language processing, reinforcement learning, and generalized methods in genomic medicine and beyond. https://www.nature.com/articles/s41591-018-0316-z

He spent 30 years hammering away at an idea most people dismissed as nonsense. Now he's the most important figure in artificial intelligence https://torontolife.com/tech/ai-superstars-google-facebook-apple-studied-guy/

Wasserstein Style Transfer. arxiv.org/abs/1905.12828

The Fashion IQ Dataset: Retrieving Images by Combining Side Information and Relative Natu... arxiv.org/abs/1905.12794

The Theory Behind Overfitting, Cross Validation, Regularization, Bagging, and Boosting: Tutorial
arxiv.org/abs/1905.12787

Path-Augmented Graph Transformer Network. arxiv.org/abs/1905.12712

Defending Against Neural Fake News.

Recent progress in natural language generation has raised dual-use concerns. While applications like summarization and translation are positive, the underlying technology also might enable adversaries to generate neural fake news: targeted propaganda that closely mimics the style of real news.

read more: https://www.profillic.com/paper/arxiv:1905.12616

Papers with Code !

https://paperswithcode.com

#artificialintelligence #codes #deeplearning #machinelearning

MetroTwitter - What Twitter reveals about the differences between cities and the monoculture of the Bay Area

Researcher collected 96K bios + 180M tweets from Twitters users in 13 major cities and visualized the differences between these cities:

- How people describe themselves
- What they talk about
- Popular emojis
- Most unique city

Code and data are open-sourced.

Website: https://huyenchip.com/2019/05/28/metrotwitter.html
GitHub: https://github.com/chiphuyen/MetroTwitter

#openresearch

​​Neural network that turns sketches into realistic photo.

Paper is called «Semantic Image Synthesis with Spatially-Adaptive Normalization».

#CVPR19 oral paper on a new conditional normalization layer for semantic image synthesis #SPADE and its demo app #GauGAN

ArXiV: https://arxiv.org/abs/1903.07291
Website: https://nvlabs.github.io/SPADE/

#GAN #CV #DL

​​Website using Deep Learning to colorize pictures.

Link: https://colourise.sg/#colorize

#DL #CV #demo

Attentive Generative Adversarial Network for Raindrop Removal from A Single Image

Abstract : "Raindrops adhered to a glass window or camera lens can severely hamper the visibility of a background scene and degrade an image considerably. In this paper, we address the problem by visually removing raindrops, and thus transforming a raindrop degraded image into a clean one. The problem is intractable, since first the regions occluded by raindrops are not given. Second, the information about the background scene of the occluded regions is completely lost for most part. To resolve the problem, we apply an attentive generative network using adversarial training (...)."

Qian et al.: https://arxiv.org/pdf/1711.10098.pdf

#artificialintelligence #deeplearning #generativeadversarialnetwork

Artificial intelligence won’t revolutionize anything if hackers can mess with it.

https://www.technologyreview.com/s/613170/emtech-digital-dawn-song-adversarial-machine-learning/?utm_source=facebook&utm_medium=tr_social&utm_campaign=site_visitor.unpaid.engagement