Large Scale Machine Learning for Drug Discovery

Posted by Patrick Riley and Dale Webster, Google Research and Bharath Ramsundar, Google Research Intern and Stanford Ph.D. candidate

Discovering new treatments for human diseases is an immensely complicated challenge; Even after extensive research to develop a biological understanding of a disease, an effective therapeutic that can improve the quality of life must still be found. This process often takes years of research, requiring the creation and testing of millions of drug-like compounds in an effort to find a just a few viable drug treatment candidates. These high-throughput screens are often automated in sophisticated labs and are expensive to perform.

Recently, deep learning with neural networks has been applied in virtual drug screening^1,2,3, which attempts to replace or augment the high-throughput screening process with the use of computational methods in order to improve its speed and success rate.⁴ Traditionally, virtual drug screening has used only the experimental data from the particular disease being studied. However, as the volume of experimental drug screening data across many diseases continues to grow, several research groups have demonstrated that data from multiple diseases can be leveraged with multitask neural networks to improve the virtual screening effectiveness.

In collaboration with the Pande Lab at Stanford University, we’ve released a paper titled "Massively Multitask Networks for Drug Discovery", investigating how data from a variety of sources can be used to improve the accuracy of determining which chemical compounds would be effective drug treatments for a variety of diseases. In particular, we carefully quantified how the amount and diversity of screening data from a variety of diseases with very different biological processes can be used to improve the virtual drug screening predictions.

Using our large-scale neural network training system, we trained at a scale 18x larger than previous work with a total of 37.8M data points across more than 200 distinct biological processes. Because of our large scale, we were able to carefully probe the sensitivity of these models to a variety of changes in model structure and input data. In the paper, we examine not just the performance of the model but why it performs well and what we can expect for similar models in the future. The data in the paper represents more than 50M total CPU hours.

This graph shows a measure of prediction accuracy (ROC AUC is the area under the receiver operating characteristic curve) for virtual screening on a fixed set of 10 biological processes as more datasets are added.

One encouraging conclusion from this work is that our models are able to utilize data from many different experiments to increase prediction accuracy across many diseases. To our knowledge, this is the first time the effect of adding additional data has been quantified in this domain, and our results suggest that even more data could improve performance even further.

Machine learning at scale has significant potential to accelerate drug discovery and improve human health. We look forward to continued improvement in virtual drug screening and its increasing impact in the discovery process for future drugs.

Thank you to our other collaborators David Konerding (Google), Steven Kearnes (Stanford), and Vijay Pande (Stanford).

References:

1. Thomas Unterthiner, Andreas Mayr, Günter Klambauer, Marvin Steijaert, Jörg Kurt Wegner, Hugo Ceulemans, Sepp Hochreiter. Deep Learning as an Opportunity in Virtual Screening. Deep Learning and Representation Learning Workshop: NIPS 2014

2. Dahl, George E, Jaitly, Navdeep, and Salakhutdinov, Ruslan. Multi-task neural networks for QSAR predictions. arXiv preprint arXiv:1406.1231, 2014.

3. Ma, Junshui, Sheridan, Robert P, Liaw, Andy, Dahl, George, and Svetnik, Vladimir. Deep neural nets as a method for quantitative structure-activity relationships. Journal of Chemical Information and Modeling, 2015.

4. Peter Ripphausen, Britta Nisius, Lisa Peltason, and Jürgen Bajorath. Quo Vadis, Virtual Screening? A Comprehensive Survey of Prospective Applications. Journal of Medicinal Chemistry 2010 53 (24), 8461-8467

Read More..

Classifying everything using your RPi Camera Deep Learning with the Pi

For those who dont want to read, the code can be found on my github with a readme:
https://github.com/StevenHickson/RPi_CaffeQuery
You can also read about it on my Hackaday io page here.

What is object classification?

Object classification has been a very popular topic the past couple years. Given an image, we want a computer to be able to tell us what that image is showing. The newest trend has been using convolutional neural networks in order to classify networks trained with a large amount of data.

One of the bigger frameworks for this is the Caffe framework. For more on this see the Caffe home page.
You can test out there web demo here. It isnt great at people but it is very good at cats, dogs, objects, and activities.

Why is this useful?

There are all kinds of autonomous tasks you can do with the RPi camera. Perhaps you want to know if your dog is in your living room, so the Pi can take his/her picture or tell him/her they are a good dog. Perhaps you want your RPi to recognize whether there is fruit in your fruit drawer so it can order you more when it is empty. The possibilities are endless.

How do convolutional neural networks work (a VERY simple overview)?

Convolutional neural networks are based loosely off how the human brain works. They are built of layers of many neurons that are "activated" by certain inputs. The input layer is connected in a network through a series of interconnected neurons in hidden layers like so:

[1]

Each neuron sends its signal to any other neuron it is connected to which is then multiplied by the connection weight and run through a sigmoid function. The training of the network is done by changing the weights in order to minimize the error function based on a set of inputs with a known set of outputs using back propagation.

How do we get this on the Pi?

Well I went ahead and compiled Caffe on the RPi. Unfortunately since it doesnt have code to optimize the network with its GPU, the classification takes ~20-25s per image, which is far too much.

Note: I did find a different optimized CNN network for the RPi by Pete Warden here. It looks great but it still takes about 3 seconds per image, which still doesnt seem fast  enough. 

You will also need the Raspberry Pi camera which you can get from here:
Raspberry PI 5MP Camera Board Module

A better option: Using the web demo with python

So we can take advantage of the Caffe web demo and use that to reduce the processing time even further. With this method, the image classification takes ~1.5s, which is usable for a system.

How does the code work?

We make a symbolic link from /dev/shm/images/ to our /var/www for apache and forward our router port 5050 to the Pi port 80. 

Then we use raspistill to take an image and save it to memory as /dev/shm/images/test.jpg. Since this is symlinked in /var/www, we should be able to see it at http://YOUR-EXTERNAL-IP:5005/images/test.jpg.

Then we use grab to qull up the Caffe demo framework with our image and get the classification results. This is done in queryCNN.py which gets the results.

What does the output look like?

Given a picture of some of my Pi components, I get this, which is pretty accurate:

Where can I get the code?

https://github.com/StevenHickson/RPi_CaffeQuery

[1] http://white.stanford.edu/teach/index.php/An_Introduction_to_Convolutional_Neural_Networks

Consider donating to further my tinkering since I do all this and help people out for free.

Places you can find me

• Facebook
• Google+
• Linkedin
• Blogspot
• Google-Code
• Github
• YouTube
• Twitter

Read More..

How Google Translate squeezes deep learning onto a phone

Posted by Otavio Good, Software Engineer, Google Translate

Today we announced that the Google Translate app now does real-time visual translation of 20 more languages. So the next time you’re in Prague and can’t read a menu, we’ve got your back. But how are we able to recognize these new languages?

In short: deep neural nets. When the Word Lens team joined Google, we were excited for the opportunity to work with some of the leading researchers in deep learning. Neural nets have gotten a lot of attention in the last few years because they’ve set all kinds of records in image recognition. Five years ago, if you gave a computer an image of a cat or a dog, it had trouble telling which was which. Thanks to convolutional neural networks, not only can computers tell the difference between cats and dogs, they can even recognize different breeds of dogs. Yes, they’re good for more than just trippy art—if youre translating a foreign menu or sign with the latest version of Googles Translate app, youre now using a deep neural net. And the amazing part is it can all work on your phone, without an Internet connection. Here’s how.

Step by step

First, when a camera image comes in, the Google Translate app has to find the letters in the picture. It needs to weed out background objects like trees or cars, and pick up on the words we want translated. It looks at blobs of pixels that have similar color to each other that are also near other similar blobs of pixels. Those are possibly letters, and if they’re near each other, that makes a continuous line we should read.

Second, Translate has to recognize what each letter actually is. This is where deep learning comes in. We use a convolutional neural network, training it on letters and non-letters so it can learn what different letters look like.

But interestingly, if we train just on very “clean”-looking letters, we risk not understanding what real-life letters look like. Letters out in the real world are marred by reflections, dirt, smudges, and all kinds of weirdness. So we built our letter generator to create all kinds of fake “dirt” to convincingly mimic the noisiness of the real world—fake reflections, fake smudges, fake weirdness all around.

Why not just train on real-life photos of letters? Well, it’s tough to find enough examples in all the languages we need, and it’s harder to maintain the fine control over what examples we use when we’re aiming to train a really efficient, compact neural network. So it’s more effective to simulate the dirt.

Some of the “dirty” letters we use for training. Dirt, highlights, and rotation, but not too much because we don’t want to confuse our neural net.

The third step is to take those recognized letters, and look them up in a dictionary to get translations. Since every previous step could have failed in some way, the dictionary lookup needs to be approximate. That way, if we read an ‘S’ as a ‘5’, we’ll still be able to find the word ‘5uper’.

Finally, we render the translation on top of the original words in the same style as the original. We can do this because we’ve already found and read the letters in the image, so we know exactly where they are. We can look at the colors surrounding the letters and use that to erase the original letters. And then we can draw the translation on top using the original foreground color.

Crunching it down for mobile

Now, if we could do this visual translation in our data centers, it wouldn’t be too hard. But a lot of our users, especially those getting online for the very first time, have slow or intermittent network connections and smartphones starved for computing power. These low-end phones can be about 50 times slower than a good laptop—and a good laptop is already much slower than the data centers that typically run our image recognition systems. So how do we get visual translation on these phones, with no connection to the cloud, translating in real-time as the camera moves around?

We needed to develop a very small neural net, and put severe limits on how much we tried to teach it—in essence, put an upper bound on the density of information it handles. The challenge here was in creating the most effective training data. Since we’re generating our own training data, we put a lot of effort into including just the right data and nothing more. For instance, we want to be able to recognize a letter with a small amount of rotation, but not too much. If we overdo the rotation, the neural network will use too much of its information density on unimportant things. So we put effort into making tools that would give us a fast iteration time and good visualizations. Inside of a few minutes, we can change the algorithms for generating training data, generate it, retrain, and visualize. From there we can look at what kind of letters are failing and why. At one point, we were warping our training data too much, and ‘$’ started to be recognized as ‘S’. We were able to quickly identify that and adjust the warping parameters to fix the problem. It was like trying to paint a picture of letters that you’d see in real life with all their imperfections painted just perfectly.

To achieve real-time, we also heavily optimized and hand-tuned the math operations. That meant using the mobile processor’s SIMD instructions and tuning things like matrix multiplies to fit processing into all levels of cache memory.

In the end, we were able to get our networks to give us significantly better results while running about as fast as our old system—great for translating what you see around you on the fly. Sometimes new technology can seem very abstract, and its not always obvious what the applications for things like convolutional neural nets could be. We think breaking down language barriers is one great use.

Read More..

From Pixels to Actions Human level control through Deep Reinforcement Learning

Posted by Dharshan Kumaran and Demis Hassabis, Google DeepMind, London

Remember the classic videogame Breakout on the Atari 2600? When you first sat down to try it, you probably learned to play well pretty quickly, because you already knew how to bounce a ball off a wall in real life. You may have even worked up a strategy to maximise your overall score at the expense of more immediate rewards. But what if you didnt possess that real-world knowledge — and only had the pixels on the screen, the control paddle in your hand, and the score to go on? How would you, or equally any intelligent agent faced with this situation, learn this task totally from scratch?

This is exactly the question that we set out to answer in our paper “Human-level control through deep reinforcement learning”, published in Nature this week. We demonstrate that a novel algorithm called a deep Q-network (DQN) is up to this challenge, excelling not only at Breakout but also a wide variety of classic videogames: everything from side-scrolling shooters (River Raid) to boxing (Boxing) and 3D car racing (Enduro). Strikingly, DQN was able to work straight “out of the box” across all these games – using the same network architecture and tuning parameters throughout and provided only with the raw screen pixels, set of available actions and game score as input.

The results: DQN outperformed previous machine learning methods in 43 of the 49 games. In fact, in more than half the games, it performed at more than 75% of the level of a professional human player. In certain games, DQN even came up with surprisingly far-sighted strategies that allowed it to achieve the maximum attainable score—for example, in Breakout, it learned to first dig a tunnel at one end of the brick wall so the ball could bounce around the back and knock out bricks from behind.

Video courtesy of Atari Inc. and Mnih et al. “Human-level control through deep reinforcement learning"

So how does it work? DQN incorporated several key features that for the first time enabled the power of Deep Neural Networks (DNN) to be combined in a scalable fashion with Reinforcement Learning (RL)—a machine learning framework that prescribes how agents should act in an environment in order to maximize future cumulative reward (e.g., a game score). Foremost among these was a neurobiologically inspired mechanism, termed “experience replay,” whereby during the learning phase DQN was trained on samples drawn from a pool of stored episodes—a process physically realized in a brain structure called the hippocampus through the ultra-fast reactivation of recent experiences during rest periods (e.g., sleep). Indeed, the incorporation of experience replay was critical to the success of DQN: disabling this function caused a severe deterioration in performance.

Comparison of the DQN agent with the best reinforcement learning methods in the literature. The performance of DQN is normalized with respect to a professional human games tester (100% level) and random play (0% level). Note that the normalized performance of DQN, expressed as a percentage, is calculated as: 100 X (DQN score - random play score)/(human score - random play score). Error bars indicate s.d. across the 30 evaluation episodes, starting with different initial conditions. Figure courtesy of Mnih et al. “Human-level control through deep reinforcement learning”, Nature 26 Feb. 2015.

This work offers the first demonstration of a general purpose learning agent that can be trained end-to-end to handle a wide variety of challenging tasks, taking in only raw pixels as inputs and transforming these into actions that can be executed in real-time. This kind of technology should help us build more useful products—imagine if you could ask the Google app to complete any kind of complex task (“Okay Google, plan me a great backpacking trip through Europe!”).

We also hope this kind of domain general learning algorithm will give researchers new ways to make sense of complex large-scale data creating the potential for exciting discoveries in fields such as climate science, physics, medicine and genomics. And it may even help scientists better understand the process by which humans learn. After all, as the great physicist Richard Feynman famously said: “What I cannot create, I do not understand.”

Read More..

Smart Autofill Harnessing the Predictive Power of Machine Learning in Google Sheets

Posted by Konstantin Davydov, Software Engineer and Afshin Rostamizadeh, Research Scientist

Much of Google’s work on language, speech, translation, and visual processing relies on machine learning, where we construct and apply learning algorithms that make use of labeled data in order to make predictions for new data. What if you could leverage machine learning algorithms to learn patterns in your spreadsheet data, automatically build a model, and infer unknown values?

You can now use machine learning to make predictions in Google Sheets with the newly launched Smart Autofill Add-on. With a single click, Smart Autofill predicts the missing values of a partially filled column in your spreadsheet by using the data of other related columns. Smart Autofill uses the non-missing data to learn patterns and differs from the standard "Auto-fill" feature of Sheets, which attempts to fill in only simple patterns that it already knows (e.g. calendar dates, days of the week, ordered numbers).

As an example, in the screenshots below, we give four very simple characteristics of used vehicles (year, number of miles, number of doors, and type: car or truck) as well as the price for some of the vehicles. Since the prices are probably correlated with the characteristics of the vehicle, we can use Smart Autofill to estimate what the missing prices should be. The rows that do contain a price will be used as examples to learn from in order to fill in the rows with a missing price.

Smart Autofill uses Googles cloud-based machine learning service Prediction API, which trains several linear as well as non-linear classification and regression models. The best model is automatically chosen for your problem by finding the one with the smallest misclassification error (for categorical data) or root-mean-squared error (for numeric data) calculated by using cross-validation on the labeled (non-empty) set of examples.

To use Smart Autofill, after following the installation procedure, simply select "Add-ons > Smart Autofill > Start" which will open a sidebar. Select a block of data that includes the column to Autofill and click "Next". Finally, from the selected data, choose a target column to Autofill and click "Start" (Figure 1). Now just sit back as Smart Autofill does its work and fills in the missing values (Figure 2).

Figure 1: Highlighting the dataset and selecting the target column.

Figure 2: After clicking "Start" a model is trained and applied to automatically fill in the missing values of the target column. Note, the estimated error of the model is reported in the sidebar.

An estimate of the error-rate of the model (based on the non-missing data) is shown in the sidebar after the missing values are filled. The accuracy of Smart Autofill (as well as the accuracy of the estimated error) depends on many factors, including the amount and quality of the data provided. While not all datasets will be ideally suited for machine learning, we hope our more in-depth tutorial will provide an idea of the range of problems where Smart Autofill can be effective.

While the vehicle pricing example is relatively simple (in reality used vehicle prices are a function of more than just four variables), more complex datasets could have many more non-target columns as well as data rows. Also, the target column does not need to be numeric, since Smart Autofill can also predict categorical values (i.e. in the car example the target column value could have contained the categories "expensive", "moderate", "affordable" instead of price). Other illustrative scenarios include:

• You have a spreadsheet that holds the results of a customer survey, but one of the columns (e.g. "overall satisfaction 1-5") has some missing values. If the other columns of the survey can help indicate overall satisfaction then you can try using Smart Autofill to estimate the missing values.
• You keep a spreadsheet of restaurants that youve visited and their characteristics (type: Italian, ambiance: quiet, cost: $$$, etc.) and whether you enjoyed the restaurant or not. Now you can add the characteristics of new restaurants to your spreadsheet and use Smart Autofill to guess at which ones you might enjoy.

The example dataset and more detailed tutorial for the add-on can be found here. We hope you discover new and useful ways to incorporate the predictive power of machine learning with your data.

Read More..

ICML 2015 and Machine Learning Research at Google

Posted by Corinna Cortes, Head, Google Research NY

This week, Lille, France hosts the 2015 International Conference on Machine Learning (ICML 2015), a premier annual Machine Learning event supported by the International Machine Learning Society (IMLS). As a leader in Machine Learning research, Google will have a strong presence at ICML 2015, with many Googlers publishing work and hosting workshops. If you’re attending, we hope you’ll visit the Google booth and talk with the Googlers to learn more about the hard work, creativity and fun that goes into solving interesting ML problems that impacts millions of people. You can also learn more about our research being presented at ICML 2015 in the list below (Googlers highlighted in blue).

Google is a Platinum Sponsor of ICML 2015.

ICML Program Committee
Area Chair - Corinna Cortes & Samy Bengio
IMLS Board Member - Corinna Cortes

Papers:
Learning Program Embeddings to Propagate Feedback on Student Code
Chris Piech, Jonathan Huang, Andy Nguyen, Mike Phulsuksombati, Mehran Sahami, Leonidas Guibas

BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
Stephan Gouws, Yoshua Bengio, Greg Corrado

An Empirical Exploration of Recurrent Network Architectures
Rafal Jozefowicz, Wojciech Zaremba, Ilya Sutskever

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe, Christian Szegedy

DRAW: A Recurrent Neural Network For Image Generation
Karol Gregor, Ivo Danihelka, Alex Graves, Danilo Rezende, Daan Wierstra

Variational Inference with Normalizing Flows
Danilo Rezende, Shakir Mohamed

Structural Maxent Models
Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Umar Syed

Weight Uncertainty in Neural Network
Charles Blundell, Julien Cornebise, Koray Kavukcuoglu, Daan Wierstra

MADE: Masked Autoencoder for Distribution Estimation
Mathieu Germain, Karol Gregor, Iain Murray, Hugo Larochelle

Fictitious Self-Play in Extensive-Form Games
Johannes Heinrich, Marc Lanctot, David Silver

Universal Value Function Approximators
Tom Schaul, Daniel Horgan, Karol Gregor, David Silver

Workshops:
Extreme Classification: Learning with a Very Large Number of Labels
Samy Bengio - Organizing Committee

Machine Learning for Education
Jonathan Huang - Organizing Committee

Workshop on Machine Learning Open Source Software 2015: Open Ecosystems
Ian Goodfellow - Program Committee

Machine Learning for Music Recommendation
Philippe Hamel - Invited Speaker

Large-Scale Kernel Learning: Challenges and New Opportunities
Poster - Just-In-Time Kernel Regression for Expectation Propagation
Wittawat Jitkrittum, Arthur Gretton, Nicolas Heess, S.M. Ali Eslami, Balaji Lakshminarayanan, Dino Sejdinovic, Zoltan Szabo

European Workshop on Reinforcement Learning (EWRL)
Rémi Munos - Organizing Committee
David Silver - Keynote

Workshop on Deep Learning
Geoff Hinton - Organizer
Tara Sainath, Oriol Vinyals, Ian Goodfellow, Karol Gregor - Invited Speakers
Poster - A Neural Conversational Model
Oriol Vinyals, Quoc Le
Oral Presentation - Massively Parallel Methods for Deep Reinforcement Learning
Arun Nair, Praveen Srinivasan, Sam Blackwell, Cagdas Alcicek, Rory Fearon, Alessandro De Maria, Vedavyas Panneershelvam, Mustafa Suleyman, Charles Beattie, Stig Petersen, Shane Legg, Volodymyr Mnih, Koray Kavukcuoglu, David Silver

Read More..

Learning Statistics with Privacy aided by the Flip of a Coin

Posted by Úlfar Erlingsson, Tech Lead Manager, Security Research

(Cross-posted on the Chromium Blog and the Google Online Security Blog)

At Google, we are constantly trying to improve the techniques we use to protect our users security and privacy. One such project, RAPPOR (Randomized Aggregatable Privacy-Preserving Ordinal Response), provides a new state-of-the-art, privacy-preserving way to learn software statistics that we can use to better safeguard our users’ security, find bugs, and improve the overall user experience.

Building on the concept of randomized response, RAPPOR enables learning statistics about the behavior of users’ software while guaranteeing client privacy. The guarantees of differential privacy, which are widely accepted as being the strongest form of privacy, have almost never been used in practice despite intense research in academia. RAPPOR introduces a practical method to achieve those guarantees.

To understand RAPPOR, consider the following example. Let’s say you wanted to count how many of your online friends were dogs, while respecting the maxim that, on the Internet, nobody should know you’re a dog. To do this, you could ask each friend to answer the question “Are you a dog?” in the following way. Each friend should flip a coin in secret, and answer the question truthfully if the coin came up heads; but, if the coin came up tails, that friend should always say “Yes” regardless. Then you could get a good estimate of the true count from the greater-than-half fraction of your friends that answered “Yes”. However, you still wouldn’t know which of your friends was a dog: each answer “Yes” would most likely be due to that friend’s coin flip coming up tails.

RAPPOR builds on the above concept, allowing software to send reports that are effectively indistinguishable from the results of random coin flips and are free of any unique identifiers. However, by aggregating the reports we can learn the common statistics that are shared by many users. We’re currently testing the use of RAPPOR in Chrome, to learn statistics about how unwanted software is hijacking users’ settings.

We believe that RAPPOR has the potential to be applied for a number of different purposes, so were making it freely available for all to use. Well continue development of RAPPOR as a standalone open-source project so that anybody can inspect and test its reporting and analysis mechanisms, and help develop the technology. We’ve written up the technical details of RAPPOR in a report that will be published next week at the ACM Conference on Computer and Communications Security.

We’re encouraged by the feedback we’ve received so far from academics and other stakeholders, and we’re looking forward to additional comments from the community. We hope that everybody interested in preserving user privacy will review the technology and share their feedback at rappor-discuss@googlegroups.com

Read More..

TensorFlow Google’s latest machine learning system open sourced for everyone

Posted by Jeff Dean, Senior Google Fellow, and Rajat Monga, Technical Lead

Deep Learning has had a huge impact on computer science, making it possible to explore new frontiers of research and to develop amazingly useful products that millions of people use every day. Our internal deep learning infrastructure DistBelief, developed in 2011, has allowed Googlers to build ever larger neural networks and scale training to thousands of cores in our datacenters. We’ve used it to demonstrate that concepts like “cat” can be learned from unlabeled YouTube images, to improve speech recognition in the Google app by 25%, and to build image search in Google Photos. DistBelief also trained the Inception model that won Imagenet’s Large Scale Visual Recognition Challenge in 2014, and drove our experiments in automated image captioning as well as DeepDream.

While DistBelief was very successful, it had some limitations. It was narrowly targeted to neural networks, it was difficult to configure, and it was tightly coupled to Google’s internal infrastructure - making it nearly impossible to share research code externally.

Today we’re proud to announce the open source release of TensorFlow -- our second-generation machine learning system, specifically designed to correct these shortcomings. TensorFlow is general, flexible, portable, easy-to-use, and completely open source. We added all this while improving upon DistBelief’s speed, scalability, and production readiness -- in fact, on some benchmarks, TensorFlow is twice as fast as DistBelief (see the whitepaper for details of TensorFlow’s programming model and implementation).

TensorFlow has extensive built-in support for deep learning, but is far more general than that -- any computation that you can express as a computational flow graph, you can compute with TensorFlow (see some examples). Any gradient-based machine learning algorithm will benefit from TensorFlow’s auto-differentiation and suite of first-rate optimizers. And it’s easy to express your new ideas in TensorFlow via the flexible Python interface.

Inspecting a model with TensorBoard, the visualization tool

TensorFlow is great for research, but it’s ready for use in real products too. TensorFlow was built from the ground up to be fast, portable, and ready for production service. You can move your idea seamlessly from training on your desktop GPU to running on your mobile phone. And you can get started quickly with powerful machine learning tech by using our state-of-the-art example model architectures. For example, we plan to release our complete, top shelf ImageNet computer vision model on TensorFlow soon.

But the most important thing about TensorFlow is that it’s yours. We’ve open-sourced TensorFlow as a standalone library and associated tools, tutorials, and examples with the Apache 2.0 license so you’re free to use TensorFlow at your institution (no matter where you work).

Our deep learning researchers all use TensorFlow in their experiments. Our engineers use it to infuse Google Search with signals derived from deep neural networks, and to power the magic features of tomorrow. We’ll continue to use TensorFlow to serve machine learning in products, and our research team is committed to sharing TensorFlow implementations of our published ideas. We hope you’ll join us at www.tensorflow.org.

Read More..

Course Builder now supports the Learning Tools Interoperability LTI Specification

Posted by John Cox, Software Engineer

Since the release of Course Builder two years ago, it has been used by individuals, companies, and universities worldwide to create and deliver online courses on a variety of subjects, helping to show the potential for making education more accessible through open source technology.

Today, we’re excited to announce that Course Builder now supports the Learning Tools Interoperability (LTI) specification. Course Builder can now interoperate with other LTI-compliant systems and online learning platforms, allowing users to interact with high-quality educational content no matter where it lives. This is an important step toward our goal of making educational content available to everyone.

If you have LTI-compliant software and would like to serve its content inside Course Builder, you can do so by using Course Builder as an LTI consumer. If you want to serve Course Builder content inside another LTI-compliant system, you can use Course Builder as an LTI provider. You can use either of these features, both, or none—the choice is entirely up to you.

The Course Builder LTI extension module, now available on Github, supports LTI version 1.0, and its LTI provider is certified by IMS Global, the nonprofit member organization that created the LTI specification. Like Course Builder itself, this module is open source and available under the Apache 2.0 license.

As part of our continued commitment to online education, we are also happy to announce we have become an affiliate member of IMS Global. IMS Global shares our desire to provide education online at scale, and we look forward to working with the IMS community on LTI and other online education technologies.

Read More..

Teach Yourself Deep Learning with TensorFlow and Udacity

Posted by Vincent Vanhoucke, Principal Research Scientist

Deep learning has become one of the hottest topics in machine learning in recent years. With TensorFlow, the deep learning platform that we recently released as an open-source project, our goal was to bring the capabilities of deep learning to everyone. So far, we are extremely excited by the uptake: more than 4000 users have forked it on GitHub in just a few weeks, and the project has been starred more than 16000 times by enthusiasts around the globe.

To help make deep learning even more accessible to engineers and data scientists at large, we are launching a new Deep Learning Course developed in collaboration with Udacity. This short, intensive course provides you with all the basic tools and vocabulary to get started with deep learning, and walks you through how to use it to address some of the most common machine learning problems. It is also accompanied by interactive TensorFlow notebooks that directly mirror and implement the concepts introduced in the lectures.

The course consists of four lectures which provide a tour of the main building blocks that are used to solve problems ranging from image recognition to text analysis. The first lecture focuses on the basics that will be familiar to those already versed in machine learning: setting up your data and experimental protocol, and training simple classification models. The second lecture builds on these fundamentals to explore how these simple models can be made deeper, and more powerful, and explores all the scalability problems that come with that, in particular regularization and hyperparameter tuning. The third lecture is all about convolutional networks and image recognition. The fourth and final lecture explore models for text and sequences in general, with embeddings and recurrent neural networks. By the end of the course, you will have implemented and trained this variety of models on your own machine and will be ready to transfer that knowledge to solve your own problems!

Our overall goal in designing this course was to provide the machine learning enthusiast a rapid and direct path to solving real and interesting problems with deep learning techniques, and were now very excited to share what weve built! It has been a lot of fun putting together with the fantastic team of experts in online course design and production at Udacity. For more details, see the Udacity blog post, and register for the course. We hope you enjoy it!

Read More..

Released Data Set Features Extracted From YouTube Videos for Multiview Learning

Posted by Omid Madani, Senior Software Engineer

“If it looks like a duck, swims like a duck, and quacks like a duck, then it probably is a duck.”

The “duck test”.

Performance of machine learning algorithms, supervised or unsupervised, is often significantly enhanced when a variety of feature families, or multiple views of the data, are available. For example, in the case of web pages, one feature family can be based on the words appearing on the page, and another can be based on the URLs and related connectivity properties. Similarly, videos contain both audio and visual signals where in turn each modality is analyzed in a variety of ways. For instance, the visual stream can be analyzed based on the color and edge distribution, texture, motion, object types, and so on. YouTube videos are also associated with textual information (title, tags, comments, etc.). Each feature family complements others in providing predictive signals to accomplish a prediction or classification task, for example, in automatically classifying videos into subject areas such as sports, music, comedy, games, and so on.

We have released a dataset of over 100k feature vectors extracted from public YouTube videos. These videos are labeled by one of 30 classes, each class corresponding to a video game (with some amount of class noise): each video shows a gameplay of a video game, for teaching purposes for example. Each instance (video) is described by three feature families (textual, visual, and auditory), and each family is broken into subfamilies yielding up to 13 feature types per instance. Neither video identities nor class identities are released.

We hope that this dataset will be valuable for research on a variety of multiview related machine learning topics, including multiview clustering, co-training, active learning, classifier fusion and ensembles.

The data and more information can be obtained from the UCI machine learning repository (multiview video dataset), or from here.

Read More..