Awesome interview by Yoshua Bengio on lessons learned from starting academic labs

https://goo.gl/psCMRE

What’s New in Deep Learning Research: Microsoft’s TextWorld is the OpenAI Gym of Language Learning

https://flipboard.com/@flipboard/-whats-new-in-deep-learning-research-mic/f-2209f1e74e%2Ftowardsdata

Academic Torrents is a distributed system for sharing enormous datasets. So far they have made 27.23TB of research data available. https://academictorrents.com @ArtificialIntelligenceArticles

❄️💦10 مقاله برتر یادگیری ماشین به انتخاب Mybridge در ماه گذشته
Machine Learning Top 10 Articles for the Past Month (v.Aug 2018)
https://goo.gl/DUhd6W @ArtificialIntelligenceArticles

NVIDIA #Turing

Fusing Real-Time Ray Tracing, AI, Simulation and Rasterization https://goo.gl/fznEeq @ArtificialIntelligenceArticles

https://www.youtube.com/watch?v=FhRW77rZUS8 @ArtificialIntelligenceArticles

Deep learning in The Brain : https://goo.gl/oqUXqV @ArtificialIntelligenceArticles

108-page survey paper/book on Deep Learning Techniques for Music Generation. https://arxiv.org/abs/1709.01620

Video-to-Video Synthesis

Using Conditional GAN to generate HD resolution videos.

paper: https://arxiv.org/abs/1808.06601

Code: https://github.com/NVIDIA/vid2vid
Video: https://goo.gl/c6Em4R

Set of illustrated Machine Learning cheatsheets covering the content of Stanford's CS 229 class:

Deep Learning: https://goo.gl/nzETEb

Supervised Learning: https://goo.gl/U7UVpj

Unsupervised Learning: https://goo.gl/XgAxk6

Tips and tricks: https://goo.gl/FwwQLP

@ArtificialIntelligenceArticles

Pieter Abbeel's slides from his last lecture kicking off the IRIM seminar series yesterday at Georgia Tech

https://www.dropbox.com/s/0cs3s55hsuba0ra/2018_08_13__Deep-Learning-to-Learn__GaTech__Abbeel--final.pdf

@ArtificialIntelligenceArticles

Which GPU(s) to Get for Deep Learning
RTX 2080 most cost-efficient choice. GTX 1080/1070 (+Ti) cards remain very good choices, especially as prices drop
https://goo.gl/97aKSZ

Everybody Dance Now

Exciting new work on conditional video synthesis from Berkeley.

"Method for motion transfer: given a video of a person dancing we can transfer that performance to a novel target after only a few min of the target performing standard moves"

https://www.youtube.com/watch?v=PCBTZh41Ris&feature=youtu.be&t=2m14s

paper : https://arxiv.org/abs/1808.07371

@ArtificialIntelligenceArticles

Deep Learning based object detector #YOLOv3 with OpenCV

With code in both #Python and #C++

https://www.learnopencv.com/deep-learning-based-object-detection-using-yolov3-with-opencv-python-c/

@ArtificialIntelligenceArticles

A very good article for Reinforcement Learning https://goo.gl/twLP7Y @ArtificialIntelligenceArticles

The Matrix Calculus You Need For Deep Learning

https://explained.ai/matrix-calculus/index.html

@ArtificialIntelligenceArticles

What You Need to Know Before Considering a PhD

If you're considering a PhD, go read this excellent post by Rachel Thomas /

https://goo.gl/eqRRDy @ArtificialIntelligenceArticles

Evaluating Theory of Mind in Question Answering

https://arxiv.org/abs/1808.09352 @ArtificialIntelligenceArticles

In this Viewpoint, Geoffrey Hinton of Google’s Brain Team discusses the basics of neural networks. Learn more https://goo.gl/mmAiX8 @ArtificialIntelligenceArticles

François Chollet interesting talk at #RAAIS2018
https://goo.gl/RyYsqh

Deep learning for predicting aftershocks of large earthquakes.

Besides offering better predictions, interpretations of the model suggest promising directions for new physical theories

https://www.nature.com/articles/s41586-018-0438-y

The success of artificial intelligence in this domain is thanks to one of the technology’s core strengths: its ability to uncover previously overlooked patterns in complex datasets. This is especially relevant in seismology, where it can be incredibly difficult to see connections in the data. Seismic events involve too many variables, from the makeup of the ground in different areas to the types of interactions between seismic plates to the ways energy propagates in waves through the Earth. Making sense of it all is incredibly hard.

The researchers say their deep learning model was able to make its predictions by considering a factor known as the “von Mises yield criterion,” a complex calculation used to predict when materials will begin to break under stress.

https://t.iss.one/ArtificialIntelligenceArticles