Tin

139 Flips | 8 Magazines | 2 Likes | 7 Followers | @tmavra5 | Keep up with Tin on Flipboard, a place to see the stories, photos, and updates that matter to you. Flipboard creates a personalized magazine full of everything, from world news to life’s great moments. Download Flipboard for free and search for “Tin”

Running fast.ai notebooks with Amazon SageMaker | Amazon Web Services

fast.ai is an organization dedicated to making the power of deep learning accessible to all. They have developed a popular open source deep learning …

Cloud Computing

Learn D3.js in 5 minutes

An introduction to creating visual representations of your data<p>D3.js is a JavaScript library used to manipulate documents based on data. It uses …

JavaScript

Lessons from My First Two Years of AI Research

<b>Tom Silver</b> | About Me | Favorite Papers | Blog<p>By Tom Silver<p>A friend of mine who is about to start a career in artificial intelligence research …

MIT

A Comprehensive Guide to Understand and Implement Text Classification in Python

Table of Contents<p>In this article, I will explain about the text classification and the step by step process to implement it in python.<p>Text …

Generative Models for Reinforcement Learning

Room: Teatro del Mar<p>In the last few years there has been an enormous amount of progress in Reinforcement Learning, with breakthroughs in our ability …

Rethinking–or Remembering–Generalization in Neural Networks

Rethinking Generalization: the Google paper<p>Last year, ICLR 2017, a very interesting paper came out of Google claiming that<p>Which basically asks, why …

How a yeast cell helps crack open the 'black box' behind artificial intelligence

UC San Diego School of Medicine researchers developed a visible neural network and used it to build DCell, a virtual model of a functioning brewer's …

Artificial Intelligence

#77: Amazon tests inventory improvement by generating fake customers with GANs, the ImageNet of video arrives, and robots get prettier with Unity-MuJoCo tie-up.

<b>Urban flaneurs generate fake cities with GANs:</b> <i><br>…Researchers discover same problems that AI researchers have been grappling with, like those relating</i> …

Machine Learning Trick of the Day (7): Density Ratio Trick

· Read in · 1481 words · All posts in series · A probability on its own is often an uninteresting thing. But when we can compare probabilities, that …

Machine Learning

How to create a deep learning dataset using Google Images

PyImageSearch reader José asks:Hey Adrian, thanks for putting together Deep Learning for Computer Vision with Python. This is by far the best …

Deep Learning

The Best of AI: New Articles Published This Month (November 2017)

10 data articles handpicked by the Sicara team, just for youWelcome to the November edition of <b>our best and favorite articles in AI that were</b> …

Scientists Have Developed a Baldness Treatment That Helps Grow New Follicles

But there's a catch, of course.<p>There's a plethora of treatments for balding on the market. But what if you could regrow your own hair out of your own …

hair loss

“Ok, Google — How do you run Deep Learning Inference on Android Using TensorFlow?”

There are many situations when running deep learning inferences on local devices is preferable for both individuals and companies: imagine traveling …

Deep Learning

CUDA Tutorial: Implicit Matrix Factorization on the GPU

I recently bought a system that actually has a decent GPU on it, and I thought it would be cool to learn a little bit about CUDA programming to …

Deep Learning

Revisiting Deep Learning as a Non-Equilibrium Process

Last year, the best paper award for ICLR 2017 went to “Re-thinking Generalization” by Chiyuan Zhang et al. For a good review, here is a video of his …

Tangent: Source-to-Source Debuggable Derivatives

Posted by Alex Wiltschko, Research Scientist, Google Brain Team<br>Tangent is a new, free, and open-source Python library for automatic differentiation. …

Deep Learning

AlphaGo Zero – How and Why it Works

DeepMind's AlphaGo made waves when it became the first AI to beat a top human Go player in March of 2016. This version of AlphaGo - AlphaGo Lee - …

Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks

Recurrent Neural Networks (RNNs) continue to show outstanding performance in sequence modeling tasks. However, training RNNs on long sequences often face challenges like slow inference, vanishing gradients and difficulty in capturing long term dependencies. In backpropagation through time settings, …

Learning Diverse Skills via Maximum Entropy Deep Reinforcement Learning

Haoran Tang and Tuomas Haarnoja Oct 6, 2017<p>Deep reinforcement learning (deep RL) has achieved success in many tasks, such as playing video games from …

A Nitty-Gritty Explanation of How Neural Networks Really Work

See the first in a three part series that explains machine learning through math.<p>Over the last few years, we've heard a lot about neural networks, whether its Google's Deep Dream software creating horrifying digital dreamscapes or composites of pop songs written by a machine. But how do these …

GAN Deep Learning Architectures - review

Introduction<p>How do you teach a machine to draw a human face if it has never seen one? A computer can store petabytes of photos, but it has no idea …

Generative Adversarial Networks (GANs): Engine and Applications

<i>Generative adversarial networks (GANs) are a class of neural networks that are used in unsupervised machine learning. They help to solve such tasks</i> …

Deep Learning

Data-driven Advice for Applying Machine Learning to Bioinformatics Problems. (arXiv:1708.05070v2 [q-bio.QM] UPDATED)

As the bioinformatics field grows, it must keep pace not only with new data but with new algorithms. Here we contribute a thorough analysis of 13 …

Machine Learning

How To Become A Machine Learning Engineer: Learning Path

We will walk you through all the aspects of machine learning from simple linear regressions to the latest neural networks, and you will learn not …

Learning Math with LSTMs and Keras

• Most, but not all errors are in the space of smaller numbers, i.e. where at least one number is less than 100.<br>• All errors seem to be in one single …

Machine Learning

The mostly complete chart of Neural Networks, explained

The zoo of neural network types grows exponentially. One needs a map to navigate between many emerging architectures and approaches.<p>Fortunately, …

Real-Time User-Guided Image Colorization with Learned Deep Priors. In SIGGRAPH, 2017.

Related and Concurrent Work<p><b>Automatic Colorization with Deep Networks</b><p>R. Zhang, P. Isola, A. A. Efros. <b>Colorful Image Colorization.</b> In ECCV, 2016. [PDF] …

The data that transformed AI research—and possibly the world

In 2006, Fei-Fei Li started ruminating on an idea.<p>Li, a newly-minted computer science professor at University of Illinois Urbana-Champaign, saw her colleagues across academia and the AI industry hammering away at the same concept: a better algorithm would make better decisions, regardless of the …

Deep Learning

A.I.-Generated Map Predicts Who Will Die Next in 'Game of Thrones'

According to sophisticated machine-learning calculations, the Queen of Dragons will soon meet her demise.<p>In early July, a computer scientist at …