YDS

By Krishnan Srinivasan | What we're reading

Everything that Works Works Because it's Bayesian: Why Deep Nets Generalize?

The Bayesian community should really start going to ICLR. They really should have started going years ago. Some people actually have.For too long we …

Deep Learning

Using Deep Learning at Scale in Twitter’s Timelines

(This post was co-authored by Anton Andryeyev from our timelines quality team)For more than a year now since we enhanced our timeline to show the …

Machine Learning

Creating a Modern OCR Pipeline Using Computer Vision and Deep Learning

In this post we will take you behind the scenes on how we built a state-of-the-art Optical Character Recognition (OCR) pipeline for our mobile …

The algorithm that could help end partisan gerrymandering

Constructing a gerrymandering measuring stick.<p>We are living in the era of the computer algorithm. Data science drives the global economy — to the point where, for many people, an algorithm will play a role in everything from what news articles they read to whom they will date — or even marry. So …

Ada Lovelace

Deepcolor: automatic coloring and shading of manga-style lineart

In the past few months, I've been experimenting with digital art. The process involves creating a rough sketch, cleaning it up into lineart, and then …

Deep Deterministic Policy Gradients in TensorFlow

Introduction<p>Deep Reinforcement Learning has recently gained a lot of traction in the machine learning community due to the significant amount of …

Deep Learning

Clustering Similar Stories Using LDA

There is more to a story than meets the eye, and some stories deserve to be presented from more than just one perspective. With Flipboard 4.0, we have released story roundups, a new feature that adds coverage from multiple sources to a story and provides you with a fuller picture of an event.<p>Here’s …

Redirecting…

Where New Slang Comes From

Ty Dolla $ign’s “Wavy” was never that popular (it didn’t even chart), and searches for wavy’s definition continue to grow. So unlike “In Da Club,” I …

Making sense of word2vec

One year ago, Tomáš Mikolov (together with his colleagues at Google) made some ripples by releasing word2vec, an unsupervised algorithm for learning …

Data Science

Matrix Factorization with Tensorflow

Mar 11, 2016 · 9 minute read · Comments<p>I’ve been working on building a content recommender in TensorFlow using matrix factorization, following the …

Diehard Coders Just Rescued NASA's Earth Science Data

On Saturday morning, the white stone buildings on UC Berkeley’s campus radiated with unfiltered sunshine. The sky was blue, the campanile was …

Image-to-Image Translation with Conditional Adversarial Networks

Generative adversarial networks have been vigorously explored in the last two years, and many conditional variants have been proposed. Please see the …

Deep Learning

Google's AI just created its own universal 'language'

The technology used in Google Translate can identify hidden material between languages to create what's known as interlingua<p>Google has previously …

Tuning Recurrent Neural Networks with Reinforcement Learning

We are excited to announce our new RL Tuner algorithm, a method for enchancing the performance of an LSTM trained on data using Reinforcement …

Deep Learning

Brain 'reads' sentences the same in English and Portuguese

An international research team led by Carnegie Mellon University has found that when the brain "reads" or decodes a sentence in English or …

Pareto efficency

2016-10-25<p>Pareto efficiency is a useful concept I like to think about. It often comes up when you compare items on multiple dimensions. Say you want …

Asynchronous methods for deep reinforcement learning

Asynchronous methods for deep reinforcement learning Mnih et al. <i>ICML 2016</i>You know something interesting is going on when you see a scalability plot …

Machine Learning

Graph-powered Machine Learning at Google

Posted by Sujith Ravi, Staff Research Scientist, Google Research<br>Recently, there have been significant advances in Machine Learning that enable …

Machine Learning

Mining the Social Web

Google has really been on the up-and-up lately with a service called Google Takeout that allows you to export <i>your</i> data from its cloud. For the …

How Robots Can Acquire New Skills from Their Shared Experience

Posted by Sergey Levine (Google Brain Team), Timothy Lillicrap (DeepMind), Mrinal Kalakrishnan (X)<br>The ability to learn from experience will likely be …

Machine Learning

Learning Reinforcement Learning (with Code, Exercises and Solutions)

Skip all the talk and go directly to the Github Repo with code and exercises. Why Study Reinforcement Learning Reinforcement Learning is one of the …

Machine Learning

Hyper Networks | 大トロ

In this post, I will talk about our recent paper called [1609.09106] HyperNetworks. I worked on this paper as a Google Brain Resident - a great …

Deep Learning

The 280-Year-Old Algorithm Inside Google Trips

Posted by Bogdan Arsintescu, Software Engineer & Sreenivas Gollapudi, Kostas Kollias, Tamas Sarlos and Andrew Tomkins, Research Scientists<br>Algorithms …

Asia Travel

Mastering the game of Go with deep neural networks and tree search

Mastering the Game of Go with Deep Neural Networks and Tree Search Silver, Huang et al., <i>Nature vol 529, 2016</i>Pretty much everyone has heard about …

Machine Learning

Deep Learning | Jeremy D. Jackson, PhD

Videos<p>Deep Learning and Neural Networks with Kevin Duh: course page<br>• NY Course by Yann LeCun: 2014 version, 2015 version<br>• NIPS 2015 Deep Learning …

Large Scale Decision Forests: Lessons Learned

Post category: Articles<p>•<p>Background of modeling at Sift:<p>We at Sift Science provide fraud detection for hundreds of customers spanning many industries …

A path to unsupervised learning through adversarial networks

Humans learn by observing and experiencing the physical world. We can imagine a not-too-distant future where a complete artificial intelligence …