Big Data Technologies
1.7K views | +0 today
Follow
Big Data Technologies
New technologies in big data - deep learning, image processing, machine learning, and more.
Curated by Dahl Winters
Your new post is loading...
Scooped by Dahl Winters
Scoop.it!

A Must-See List of TensorFlow Examples

A Must-See List of TensorFlow Examples | Big Data Technologies | Scoop.it
In this article, I made a collection of the best TensorFlow examples.
more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Traffic light recognition - Deep Learning

Traffic light recognition using deep learning- trained CNN. Detection of stop line is being done using hough transform.
more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Microsoft's artificial intelligence CNTK framework is now open-source

Microsoft's artificial intelligence CNTK framework is now open-source | Big Data Technologies | Scoop.it
Microsoft brings a new meaning to the phrase "collective intelligence" by open-sourcing its artificial brain. This is the technology behind both Cortana and Skype Translator's speech recognition.
more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Google's DeepMind Masters Atari Games

Google's DeepMind Masters Atari Games | Big Data Technologies | Scoop.it
A computer that taught itself to play almost 50 video games including Space Invaders and Pong is being hailed as the pinnacle of artificial intelligence. But it is unlikely to spark the Terminator-like Armageddon predicted in recent months by technology entrepreneur Elon Musk (who provided early funding for the project) [...]
more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Facebook AI Director Yann LeCun on His Quest to Unleash Deep Learning and Make Machines Smarter - IEEE Spectrum

Facebook AI Director Yann LeCun on His Quest to Unleash Deep Learning and Make Machines Smarter - IEEE Spectrum | Big Data Technologies | Scoop.it
The Deep Learning expert explains how convolutional nets work, why Facebook needs AI, what he dislikes about the Singularity, and more
more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Understanding Deep Neural Networks - Research at Google

Understanding Deep Neural Networks - Research at Google | Big Data Technologies | Scoop.it

Former Google intern +Christopher Olah has written a blog post that uses dimensionality reduction and interactive visualizations to help understand what exactly is happening “under the hood”, giving one an intuition on the internal operations of DNNs.

more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Practical Advice on Training Large Deep Neural Networks

Practical Advice on Training Large Deep Neural Networks | Big Data Technologies | Scoop.it
RT @sedielem: Some great practical advice from Ilya Sutskever for training large deep neural networks http://t.co/m0GBzeEJBf

 

Ok. So you’re sold. You’re convinced that LDNNs are the present and the future and you want to train it. But rumor has it that it’s so hard, so difficult… or is it? The reality is that it used to be hard, but now the community has consolidated its knowledge and realized that training neural networks is easy as long as you keep the following in mind. 

Here is a summary of the community’s knowledge of what’s important and what to look after.

more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Video: Deep Learning on GPU Clusters

Video: Deep Learning on GPU Clusters | Big Data Technologies | Scoop.it
In this video from the Nvidia Theater at SC14, Bryan Catanzaro from Baidu presents: Deep Learning on GPU Clusters.

 

Deep neural networks have recently emerged as an important tool for difficult AI problems, and have found success in many fields ranging from computer vision to speech recognition. Training deep neural networks is computationally intensive, and so practical application of these networks requires careful attention to parallelism. GPUs have been instrumental in the success of deep neural networks, because they significantly reduce the cost of network training, which then has allowed many researchers to train better networks. In this talk, I will discuss how we were able to duplicate results from a 1000 node cluster using only 3 nodes, each with 4 GPUs.

more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Facebook open-sources its deep-learning AI tools

Facebook open-sources its deep-learning AI tools | Big Data Technologies | Scoop.it
Facebook is sharing some of its technology. The company’s artificial intelligence research team today announced that it is open sourcing its deep-learning AI tools. The software will be available on…
more...
No comment yet.
Rescooped by Dahl Winters from Data is big
Scoop.it!

A Deep Learning Tutorial: From Perceptrons to Deep Networks

A Deep Learning Tutorial: From Perceptrons to Deep Networks | Big Data Technologies | Scoop.it
Are you joining the growing group of developers who want to know more about Deep Learning? This introductory tutorial covers it all.

Via ukituki
more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Deep learning reveals unexpected genetic roots of cancers, autism and other disorders

Deep learning reveals unexpected genetic roots of cancers, autism and other disorders | Big Data Technologies | Scoop.it
In the decade since the genome was sequenced in 2003, scientists and doctors have struggled to answer an all-consuming question: Which DNA mutations cause disease?
more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

In one aspect of vision, computers catch up to primate brain

In one aspect of vision, computers catch up to primate brain | Big Data Technologies | Scoop.it
Newest computer neural networks can identify visual objects as well as the primate brain.
more...
No comment yet.
Rescooped by Dahl Winters from Jobcrumb Research
Scoop.it!

Convolutional Neural Networks for Visual Recognition - Open Sourced on Github

Convolutional Neural Networks for Visual Recognition - Open Sourced on Github | Big Data Technologies | Scoop.it

We present a model that generates free-form natural language descriptions of image regions. Our model leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between text and visual data.

 

Our approach is based on a novel combination of Convolutional Neural Networks over image regions, bidirectional Recurrent Neural Networks over sentences, and a structured objective that aligns the two modalities through a multimodal embedding. We then describe a Recurrent Neural Network architecture that uses the inferred alignments to learn to generate novel descriptions of image regions. 


Via Denny Wong
Dahl Winters's insight:

In short, the method to be described generates very accurate sentence descriptions from images.  Images can be translated into sentences.

more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Pedestrian Detection by Deep Convolutional Neural Network - YouTube

Real-time pedestrian detection by Deep Convolutional Neural Network is demonstrated. It runs on NVIDIA's Jetson Pro platform with Tegra K1. DENSO IT LABORATO...
more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Recursive neural networks by deep-learning startup MetaMind

Recursive neural networks by deep-learning startup MetaMind | Big Data Technologies | Scoop.it

The convolutional neural networks have pulled out features after scanning many, many images. And the recursive neural networks extract meaning from all the words. They work together jointly. Google and Microsoft have each announced recently that they have made inroads in processing text and images in one shot, but Socher himself was doing that last year, with a paper about it coming out in February.

 
Dahl Winters's insight:

This is pretty new (although it's been almost a year since it was first developed).  Type in "bird" and you get an image of one bird.  Type in "birds" and you get images of multiple birds.  But type in "birds on water," and the algorithm is able to parse this sentence to give you images of birds flying over bodies of water.

more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Real-Time Video Processing Algorithm for Instant License Plate Recognition in iOS Apps (using OpenCV & GPGPU)

Real-Time Video Processing Algorithm for Instant License Plate Recognition in iOS Apps (using OpenCV & GPGPU) | Big Data Technologies | Scoop.it
The GPGPU opens new horizons for mobile apps. Shifting license plate recognition from OpenCV to GPGPU has made real-time number recognition possible.
Dahl Winters's insight:

Doing more with less - step-by-step details on just how character recognition is done on a cell phone.  If this can be done on a cell phone, imagine the possibilities for more capable machines.

more...
No comment yet.
Rescooped by Dahl Winters from leapmind
Scoop.it!

AI For Everyone: Startups Democratize Deep Learning So Google And Facebook Don't Own It All

AI For Everyone: Startups Democratize Deep Learning So Google And Facebook Don't Own It All | Big Data Technologies | Scoop.it
Startups aim to democratize deep learning so big companies such as Google and Facebook don't end up owning all the most promising tools to improve computing over the coming decades, according to a panel this week at Stanford University.

Via LeapMind
more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Using convolutional neural nets to detect facial keypoints tutorial — Daniel Nouri's Blog

Using convolutional neural nets to detect facial keypoints tutorial — Daniel Nouri's Blog | Big Data Technologies | Scoop.it
Dahl Winters's insight:

Two things: 1) Lasagne, a new library for building neural networks with Python/Theano, and 2) utilizing GPU capability to accelerate the process. 

more...
No comment yet.
Rescooped by Dahl Winters from Metaglossia: The Translation World
Scoop.it!

Finding an image with an image and other feats of computer vision

Finding an image with an image and other feats of computer vision | Big Data Technologies | Scoop.it
Ars talks to Yahoo about making photos easier to find, share, and communicate with.

Via Charles Tiayon
more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

AI Recognizes Cats the Same Way Physicists Calculate the Cosmos - Wired

AI Recognizes Cats the Same Way Physicists Calculate the Cosmos - Wired | Big Data Technologies | Scoop.it
New research suggests physicists, computers and brains employ the same procedure to tease out important features from among other irrelevant bits of data.
more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Watson wannabes: 4 open source projects for machine intelligence

Watson wannabes: 4 open source projects for machine intelligence | Big Data Technologies | Scoop.it
These projects aren't as established as Watson, but they're open source and ready for work
more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

How Google "Translates" Pictures into Words Using Vector Space Mathematics | MIT Technology Review

How Google "Translates" Pictures into Words Using Vector Space Mathematics | MIT Technology Review | Big Data Technologies | Scoop.it
Google engineers have trained a machine-learning algorithm to write picture captions using the same techniques it developed for language translation.
more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

What we read about deep learning is just the tip of the iceberg

What we read about deep learning is just the tip of the iceberg | Big Data Technologies | Scoop.it
The artificial intelligence technique known as deep learning is white hot right now, as we have noted numerous times before.
more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Speeding up isotonic regression in scikit-learn by 5,000x

Speeding up isotonic regression in scikit-learn by 5,000x | Big Data Technologies | Scoop.it
RT @DataSciNews: #MachineLearning => Speeding up isotonic regression in scikit-learn by 5,000x >> http://t.co/b2TAYy73t8 by @ajtulloch
more...
No comment yet.
Scooped by Dahl Winters
Scoop.it!

Geospatial (distance) faceting using Lucene's dynamic range facets | Java Code Geeks

Geospatial (distance) faceting using Lucene's dynamic range facets | Java Code Geeks | Big Data Technologies | Scoop.it
There have been several recent, quiet improvements to Lucene that, taken together, have made it surprisingly simple to add geospatial distance faceting to any Lucene search application, for example:                 < 1 km (147) < 2 km (579) < 5 km...
more...
No comment yet.
Curated by Dahl Winters
I curate three topics on big data analytics/science, geospatial big data, and deep learning/new technologies that will hopefully make the world of big data more accessible and all the more awesome.