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
A very good article for Reinforcement Learning https://goo.gl/twLP7Y @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
The p5.js Web Editor is a friendly online platform for learning to code in a visual way. Designed for all ages and abilities, anyone can get started quickly creating, editing, https://goo.gl/3TLZrU
Kaggle winner explains how to combine categorical, numerical, image and text features into a single NN that gets you into top 10 without stacking.


Online ad demand prediction kaggle competition 1st place summary:


https://www.kaggle.com/c/avito-demand-prediction/discussion/59880

@ArtificialIntelligenceArticles
250 awesome short lectures on robotics

The Queensland University of Technology robot academy : https://robotacademy.net.au/ @ArtificialIntelligenceArticles
The First World-Class Overview of AI for the General Public

Curated Open-Source Codes, Implementations and Science : https://goo.gl/AZ3DJy @ArtificialIntelligenceArticles
Princeton Team using Deep Learning to develop Fusion Energy
https://goo.gl/KGefMB @ArtificialIntelligenceArticles
Page Proportions as Musical Intervals

New Codepen by Tero Parviainen : https://codepen.io/teropa/full/xaqzLj/
Graph Attention Networks

"We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. (...)"

Paper by Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio : https://arxiv.org/abs/1710.10903

Source Code : https://github.com/PetarV-/GAT

Website : https://mila.quebec/en/publication/graph-attention-networks/