Deep Learning

Getting started with a TensorFlow surgery classifier with TensorBoard data viz

The most challenging part of deep learning is labeling, as you'll see in part one of this two-part series, <i>Learn how to classify images with …

Open Source Movement

Deep Learning for Disaster Recovery – Insight Data

<b>Flooded roads are a huge risk</b><p>With global climate change, devastating hurricanes are occurring with higher frequency.<p>After a hurricane, roads are …

Data Science

Race for the Galaxy AI

<b>From TD-Gammon to Race for the Galaxy</b>Temporal Difference Learning for Boardgame AI<p>What makes a game replayable over time? It offers new challenges …

Board Games

Leveraging Low Precision and Quantization for Deep Learning Using the Amazon EC2 C5 Instance and BigDL | Amazon Web Services

Recently AWS released the new compute-intensive Amazon EC2 C5 instances, based on the latest generation Intel Xeon Scalable Platinum processors. …

Data Science

3 NIPS Papers We Loved – tech-at

<i>Know your model’s limits, interpret it’s behavior and learn from variable length sets.</i><p>At NIPS 2017 what surprised me the most was not the size of the …

Data Science

How many images do you need to train a neural network?

Today I got an email with a question I’ve heard many times – “<i>How many images do I need to train my classifier?</i>“. In the early days I would reply …

Data Science

Create a Character-based Seq2Seq model using Python and Tensorflow

In this article, I will share my findings on creating a character-based Sequence-to-Sequence model (Seq2Seq) and I will share some of the results I …

Data Science

AI’s impact on network engineering now and in the future

2017 was the year we saw artificial intelligence take off. Or was it?<p>If nothing else, AI continues to climb the technology hype curve. It was impossible to read the news, browse the web, attend a conference, or even watch television without seeing a reference to how AI is making our lives …

Machine Learning

Who are my customers? What the machine can learn on its own

<i>By Melinda Han Williams, VP of data science and analytics, Dstillery</i><p>In digital marketing, every brand wants to identify the best new customers at the …

Machine Learning

Google boffins tease custom AI math-chip TPU2 stats: 45 TFLOPS, 16GB HBM, benchmarks

Missing key info, take with a pinch of salt, YMMVIf you've been curious about the potential performance of Google's TPU2 – its second-generation …

Machine Learning

Image Classification on Small Datasets with Keras

Using a pretrained convnet<p>A common and highly effective approach to deep learning on small image datasets is to use a pretrained network. A <i>pretrained</i> …

Neural Networks

Graph Representation Learning

Graph models are pervasive for describing information across any scientific and industrial field where complex information is used.<p>The classical …

Machine Learning

How to break a CAPTCHA system in 15 minutes with Machine Learning

Let’s hack the world’s most popular Wordpress CAPTCHA Plug-in<p>Everyone hates CAPTCHAs — those annoying images that contain text you have to type in …

Machine Learning

A Gentle Introduction to Neural Networks (with Python) Tariq EuroPython Bilbao July ppt download

Presentation on theme: "A Gentle Introduction to Neural Networks (with Python) Tariq EuroPython Bilbao July 2016."— Presentation transcript:<p>1 A …

Python Programming

TensorFlow for R

Simple Example<p>Let’s create a simple linear regression model with the mtcars dataset to demonstrate the use of estimators. We’ll illustrate how ‘input …

Data Science

Stock Performance Prediction Prototype Shows 62% Accuracy Using NLP, Deep Learning

Stock performance prediction prototype shows 62% accuracy using NLP, Deep Learning<p>Accurately predicting stock performance involves acquiring highly …

Machine Learning

TFGAN: A Lightweight Library for Generative Adversarial Networks

Posted by Joel Shor, Senior Software Engineer (Crossposted on the Google Open Source Blog ) Training a neural network usually involves d...

Cognitive Computing

Deep Learning for NLP, advancements and trends in 2017

Sentiment analysis in Twitter has drawn a lot of attention from researchers in NLP, but also in political and social sciences. That is why since …

Machine Learning

Save 91% On The Deep Learning and Artificial Intelligence Introductory Bundle

We have an awesome deal on the Deep Learning and Artificial Intelligence Introductory Bundle in the Geeky Gadgets Deals store today, you can save 91% …

Machine Learning

AlphaZero Is the New Chess Champion, and Harbinger of a Brave New World in AI - ExtremeTech

By on December 12, 2017 at 7:30 am<p>This site may earn affiliate commissions from the links on this page. Terms of use.<p>The world has quietly crowned a …

Artificial Intelligence

Efficiency is not associative for matrix multiplication

Here’s a fact that has been rediscovered many times in many different contexts: The way you parenthesize matrix products can greatly change the time …

Machine Learning

Embodied Learning is Essential to Artificial Intelligence

Jeff Hawkins has a principle that intuitively makes a lot of sense, yet is something that Deep Learning research has not emphasized enough. This is …

Machine Learning

21 Curated Blogs About Deep Learning and Data Science

Machine Learning

Essentials of Deep Learning : Introduction to Long Short Term Memory

Log in or Register to save this content for later.<p>Introduction<p>Sequence prediction problems have been around for a long time. They are considered as …

Data Science

Updated AWS Deep Learning AMIs: New Versions of TensorFlow, Apache MXNet, Keras, and PyTorch | Amazon Web Services

We’re excited to update the AWS Deep Learning AMIs with significantly faster training on NVIDIA Tesla V100 “Volta” GPUs across many frameworks, …

Data Science

Top Data Science and Machine Learning Methods Used in 2017

The most used methods are Regression, Clustering, Visualization, Decision Trees/Rules, and Random Forests; Deep Learning is used by only 20% of …

Data Science

NIPS 2017 Summary

tl;dr<p>Deep learning is influencing bayesian methods and vice versa: deep bayesian learning and bayesian deep learning are two slightly different …

Data Science

Connecting R to Keras and TensorFlow

by Joseph Rickert<p>It has always been the mission of R developers to connect R to the “good stuff”. As John Chambers puts it in his book <i>Extending R</i>:<p><i>One</i> …

Machine Learning

An Addendum to Alchemy

Ali Rahimi and Ben Recht • Dec 11, 2017<p><i>This post is an addendum to our “test of time” talk at NIPS 2017.</i><p>We’d like to expand on a few points about the …

Machine Learning

Deep Learning Chipset Market: Outlook, Opportunity & Future Trends Till Forecast Period

Deep learning chipset is a part of machine learning methods. It is grounded in the multilayer neural network and is the foundation of real time …

Machine Learning