NIPS 2015 and Machine Learning Research at Google

Posted by Sanjiv Kumar, Research Scientist

This week, Montreal hosts the 29^th Annual Conference on Neural Information Processing Systems (NIPS 2015), a machine learning and computational neuroscience conference that includes invited talks, demonstrations and oral and poster presentations of some of the latest in machine learning research. Google will have a strong presence at NIPS 2015, with over 140 Googlers attending in order to contribute to and learn from the broader academic research community by presenting technical talks and posters, in addition to hosting workshops and tutorials.

Research at Google is at the forefront of innovation in Machine Intelligence, actively exploring virtually all aspects of machine learning including classical algorithms as well as cutting-edge techniques such as deep learning. Focusing on both theory as well as application, much of our work on language understanding, speech, translation, visual processing, ranking, and prediction relies on Machine Intelligence. In all of those tasks and many others, we gather large volumes of direct or indirect evidence of relationships of interest, and develop learning approaches to understand and generalize.

If you are attending NIPS 2015, we hope you’ll stop by our booth and chat with our researchers about the projects and opportunities at Google that go into solving interesting problems for billions of people. You can also learn more about our research being presented at NIPS 2015 in the list below (Googlers highlighted in blue).

Google is a Platinum Sponsor of NIPS 2015.

PROGRAM ORGANIZERS
General Chairs
Corinna Cortes, Neil D. Lawrence
Program Committee includes:
Samy Bengio, Gal Chechik, Ian Goodfellow, Shakir Mohamed, Ilya Sutskever

ORAL SESSIONS
Learning Theory and Algorithms for Forecasting Non-stationary Time Series
Vitaly Kuznetsov, Mehryar Mohri

SPOTLIGHT SESSIONS
Distributed Submodular Cover: Succinctly Summarizing Massive Data
Baharan Mirzasoleiman, Amin Karbasi, Ashwinkumar Badanidiyuru, Andreas Krause

Spatial Transformer Networks
Max Jaderberg, Karen Simonyan, Andrew Zisserman, Koray Kavukcuoglu

Pointer Networks
Oriol Vinyals, Meire Fortunato, Navdeep Jaitly

Structured Transforms for Small-Footprint Deep Learning
Vikas Sindhwani, Tara Sainath, Sanjiv Kumar

Spherical Random Features for Polynomial Kernels
Jeffrey Pennington, Felix Yu, Sanjiv Kumar

POSTERS
Learning to Transduce with Unbounded Memory
Edward Grefenstette, Karl Moritz Hermann, Mustafa Suleyman, Phil Blunsom

Deep Knowledge Tracing
Chris Piech, Jonathan Bassen, Jonathan Huang, Surya Ganguli, Mehran Sahami, Leonidas Guibas, Jascha Sohl-Dickstein

Hidden Technical Debt in Machine Learning Systems
D Sculley, Gary Holt, Daniel Golovin, Eugene Davydov, Todd Phillips, Dietmar Ebner, Vinay Chaudhary, Michael Young, Jean-Francois Crespo, Dan Dennison

Grammar as a Foreign Language
Oriol Vinyals, Lukasz Kaiser, Terry Koo, Slav Petrov, Ilya Sutskever, Geoffrey Hinton

Stochastic Variational Information Maximisation
Shakir Mohamed, Danilo Rezende

Embedding Inference for Structured Multilabel Prediction
Farzaneh Mirzazadeh, Siamak Ravanbakhsh, Bing Xu, Nan Ding, Dale Schuurmans

On the Convergence of Stochastic Gradient MCMC Algorithms with High-Order Integrators
Changyou Chen, Nan Ding, Lawrence Carin

Spectral Norm Regularization of Orthonormal Representations for Graph Transduction
Rakesh Shivanna, Bibaswan Chatterjee, Raman Sankaran, Chiranjib Bhattacharyya, Francis Bach

Differentially Private Learning of Structured Discrete Distributions
Ilias Diakonikolas, Moritz Hardt, Ludwig Schmidt

Nearly Optimal Private LASSO
Kunal Talwar, Li Zhang, Abhradeep Thakurta

Learning Continuous Control Policies by Stochastic Value Gradients
Nicolas Heess, Greg Wayne, David Silver, Timothy Lillicrap, Tom Erez, Yuval Tassa

Gradient Estimation Using Stochastic Computation Graphs
John Schulman, Nicolas Heess, Theophane Weber, Pieter Abbeel

Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
Samy Bengio, Oriol Vinyals, Navdeep Jaitly, Noam Shazeer

Teaching Machines to Read and Comprehend
Karl Moritz Hermann, Tomas Kocisky, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, Phil Blunsom

Bayesian dark knowledge
Anoop Korattikara, Vivek Rathod, Kevin Murphy, Max Welling

Generalization in Adaptive Data Analysis and Holdout Reuse
Cynthia Dwork, Vitaly Feldman, Moritz Hardt, Toniann Pitassi, Omer Reingold, Aaron Roth

Semi-supervised Sequence Learning
Andrew Dai, Quoc Le

Natural Neural Networks
Guillaume Desjardins, Karen Simonyan, Razvan Pascanu, Koray Kavukcuoglu

Revenue Optimization against Strategic Buyers
Andres Munoz Medina, Mehryar Mohri


WORKSHOPS
Feature Extraction: Modern Questions and Challenges
Workshop Chairs include: Dmitry Storcheus, Afshin Rostamizadeh, Sanjiv Kumar
Program Committee includes: Jeffery Pennington, Vikas Sindhwani

NIPS Time Series Workshop
Invited Speakers include: Mehryar Mohri
Panelists include: Corinna Cortes

Nonparametric Methods for Large Scale Representation Learning
Invited Speakers include: Amr Ahmed

Machine Learning for Spoken Language Understanding and Interaction
Invited Speakers include: Larry Heck

Adaptive Data Analysis
Organizers include: Moritz Hardt

Deep Reinforcement Learning
Organizers include : David Silver
Invited Speakers include: Sergey Levine

Advances in Approximate Bayesian Inference
Organizers include : Shakir Mohamed
Panelists include: Danilo Rezende

Cognitive Computation: Integrating Neural and Symbolic Approaches
Invited Speakers include: Ramanathan V. Guha, Geoffrey Hinton, Greg Wayne

Transfer and Multi-Task Learning: Trends and New Perspectives
Invited Speakers include: Mehryar Mohri
Poster presentations include: Andres Munoz Medina

Learning and privacy with incomplete data and weak supervision
Organizers include : Felix Yu
Program Committee includes: Alexander Blocker, Krzysztof Choromanski, Sanjiv Kumar
Speakers include: Nando de Freitas

Black Box Learning and Inference
Organizers include : Ali Eslami
Keynotes include: Geoff Hinton

Quantum Machine Learning
Invited Speakers include: Hartmut Neven

Bayesian Nonparametrics: The Next Generation
Invited Speakers include: Amr Ahmed

Bayesian Optimization: Scalability and Flexibility
Organizers include: Nando de Freitas

Reasoning, Attention, Memory (RAM)
Invited speakers include: Alex Graves, Ilya Sutskever

Extreme Classification 2015: Multi-class and Multi-label Learning in Extremely Large Label Spaces
Panelists include: Mehryar Mohri, Samy Bengio
Invited speakers include: Samy Bengio

Machine Learning Systems
Invited speakers include: Jeff Dean


SYMPOSIA
Brains, Mind and Machines
Invited Speakers include: Geoffrey Hinton, Demis Hassabis

Deep Learning Symposium
Program Committee Members include: Samy Bengio, Phil Blunsom, Nando De Freitas, Ilya Sutskever, Andrew Zisserman
Invited Speakers include: Max Jaderberg, Sergey Ioffe, Alexander Graves

Algorithms Among Us: The Societal Impacts of Machine Learning
Panelists include: Shane Legg


TUTORIALS
NIPS 2015 Deep Learning Tutorial
Geoffrey E. Hinton, Yoshua Bengio, Yann LeCun

Large-Scale Distributed Systems for Training Neural Networks
Jeff Dean, Oriol Vinyals

Read More..

AlphaGo Mastering the ancient game of Go with Machine Learning

Posted by David Silver and Demis Hassabis, Google DeepMind

Games are a great testing ground for developing smarter, more flexible algorithms that have the ability to tackle problems in ways similar to humans. Creating programs that are able to play games better than the best humans has a long history - the first classic game mastered by a computer was noughts and crosses (also known as tic-tac-toe) in 1952 as a PhD candidate’s project. Then fell checkers in 1994. Chess was tackled by Deep Blue in 1997. The success isn’t limited to board games, either - IBMs Watson won first place on Jeopardy in 2011, and in 2014 our own algorithms learned to play dozens of Atari games just from the raw pixel inputs.

But one game has thwarted A.I. research thus far: the ancient game of Go. Invented in China over 2500 years ago, Go is played by more than 40 million people worldwide. The rules are simple: players take turns to place black or white stones on a board, trying to capture the opponents stones or surround empty space to make points of territory. Confucius wrote about the game, and its aesthetic beauty elevated it to one of the four essential arts required of any true Chinese scholar. The game is played primarily through intuition and feel, and because of its subtlety and intellectual depth it has captured the human imagination for centuries.

But as simple as the rules are, Go is a game of profound complexity. The search space in Go is vast -- more than a googol times larger than chess (a number greater than there are atoms in the universe!). As a result, traditional “brute force” AI methods -- which construct a search tree over all possible sequences of moves -- don’t have a chance in Go. To date, computers have played Go only as well as amateurs. Experts predicted it would be at least another 10 years until a computer could beat one of the world’s elite group of Go professionals.

We saw this as an irresistible challenge! We started building a system, AlphaGo, described in a paper in Nature this week, that would overcome these barriers. The key to AlphaGo is reducing the enormous search space to something more manageable. To do this, it combines a state-of-the-art tree search with two deep neural networks, each of which contains many layers with millions of neuron-like connections. One neural network, the “policy network”, predicts the next move, and is used to narrow the search to consider only the moves most likely to lead to a win. The other neural network, the “value network”, is then used to reduce the depth of the search tree -- estimating the winner in each position in place of searching all the way to the end of the game.

AlphaGo’s search algorithm is much more human-like than previous approaches. For example, when Deep Blue played chess, it searched by brute force over thousands of times more positions than AlphaGo. Instead, AlphaGo looks ahead by playing out the remainder of the game in its imagination, many times over - a technique known as Monte-Carlo tree search. But unlike previous Monte-Carlo programs, AlphaGo uses deep neural networks to guide its search. During each simulated game, the policy network suggests intelligent moves to play, while the value network astutely evaluates the position that is reached. Finally, AlphaGo chooses the move that is most successful in simulation.

We first trained the policy network on 30 million moves from games played by human experts, until it could predict the human move 57% of the time (the previous record before AlphaGo was 44%). But our goal is to beat the best human players, not just mimic them. To do this, AlphaGo learned to discover new strategies for itself, by playing thousands of games between its neural networks, and gradually improving them using a trial-and-error process known as reinforcement learning. This approach led to much better policy networks, so strong in fact that the raw neural network (immediately, without any tree search at all) can defeat state-of-the-art Go programs that build enormous search trees.

These policy networks were in turn used to train the value networks, again by reinforcement learning from games of self-play. These value networks can evaluate any Go position and estimate the eventual winner - a problem so hard it was believed to be impossible.

Of course, all of this requires a huge amount of compute power, so we made extensive use of Google Cloud Platform, which enables researchers working on AI and Machine Learning to access elastic compute, storage and networking capacity on demand. In addition, new open source libraries for numerical computation using data flow graphs, such as TensorFlow, allow researchers to efficiently deploy the computation needed for deep learning algorithms across multiple CPUs or GPUs.

So how strong is AlphaGo? To answer this question, we played a tournament between AlphaGo and the best of the rest - the top Go programs at the forefront of A.I. research. Using a single machine, AlphaGo won all but one of its 500 games against these programs. In fact, AlphaGo even beat those programs after giving them 4 free moves headstart at the beginning of each game. A high-performance version of AlphaGo, distributed across many machines, was even stronger.

This figure from the Nature article shows the Elo rating and approximate rank of AlphaGo (both single machine and distributed versions), the European champion Fan Hui (a professional 2-dan), and the strongest other Go programs, evaluated over thousands of games. Pale pink bars show the performance of other programs when given a four move headstart.

It seemed that AlphaGo was ready for a greater challenge. So we invited the reigning 3-time European Go champion Fan Hui — an elite professional player who has devoted his life to Go since the age of 12 — to our London office for a challenge match. The match was played behind closed doors between October 5-9 last year. AlphaGo won by 5 games to 0 -- the first time a computer program has ever beaten a professional Go player.

AlphaGo’s next challenge will be to play the top Go player in the world over the last decade, Lee Sedol. The match will take place this March in Seoul, South Korea. Lee Sedol is excited to take on the challenge saying, "I am privileged to be the one to play, but I am confident that I can win." It should prove to be a fascinating contest!

We are thrilled to have mastered Go and thus achieved one of the grand challenges of AI. However, the most significant aspect of all this for us is that AlphaGo isn’t just an ‘expert’ system built with hand-crafted rules, but instead uses general machine learning techniques to allow it to improve itself, just by watching and playing games. While games are the perfect platform for developing and testing AI algorithms quickly and efficiently, ultimately we want to apply these techniques to important real-world problems. Because the methods we have used are general purpose, our hope is that one day they could be extended to help us address some of society’s toughest and most pressing problems, from climate modelling to complex disease analysis.

Read More..

Advances in Variational Inference Working Towards Large scale Probabilistic Machine Learning at NIPS 2014

Posted by Shakir Mohamed and Charles Blundell, Google DeepMind, London

At Google, we continually explore and develop large-scale machine learning systems to improve our user’s experience, such as providing better video recommendations, deciding on the best language translation in a given context, or improving the accuracy of image search results. The data used to train these systems often contains many inconsistencies and missing elements, making progress towards large-scale probabilistic models designed to address these problems an important and ongoing part of our research. One principled and efficient approach for developing such models relies on an approach known as Variational Inference.

A renewed interest and several recent advances in variational inference^1,2,3,4,5,6 has motivated us to support and co-organise this year’s workshop on Advances in Variational Inference as part of the Neural Information Processing Systems (NIPS) conference in Montreal. These advances include new methods for scalability using stochastic gradient methods, the ability to handle data that arrives continuously as a stream, inference in non-linear time-series models, principled regularisation in deep neural networks, and inference-based decision making in reinforcement learning, amongst others.

Whilst variational methods have clearly emerged as a leading approach for tractable, large-scale probabilistic inference, there remain important trade-offs in speed, accuracy, simplicity and applicability between variational and other approximative schemes. The goal of the workshop will be to contextualise these developments and address some of the many unanswered questions through:

• Contributed talks from 6 speakers who are leading the resurgence of variational inference, and shaping the debate on topics of stochastic optimisation, deep learning, Bayesian non-parametrics, and theory.
• 34 contributed papers covering significant advances in methodology, theory and applications including efficient optimisation, streaming data analysis, submodularity, non-parametric modelling and message passing.
• A panel discussion with leading researchers in the field that will further interrogate these ideas. Our panelists are David Blei, Neil Lawrence, Shinichi Nakajima and Matthias Seeger.

The workshop presents a fantastic opportunity to discuss the opportunities and obstacles facing the wider adoption of variational methods. The workshop will be held on the 13th December 2014 at the Montreal Convention and Exhibition Centre. For more details see: www.variationalinference.org.

References:

1. Rezende, Danilo J., Shakir Mohamed, and Daan Wierstra, Stochastic Backpropagation and Approximate Inference in Deep Generative Models, Proceedings of the 31st International Conference on Machine Learning (ICML-14), 2014.

2. Gregor, Karol, Ivo Danihelka, Andriy Mnih, Charles Blundell and Daan Wierstra, Deep AutoRegressive Networks, Proceedings of the 31st International Conference on Machine Learning (ICML-14), 2014.

3. Mnih, Andriy, and Karol Gregor, Neural Variational Inference and Learning in Belief Networks, Proceedings of the 31st International Conference on Machine Learning (ICML-14), 2014.

4. Kingma, D. P. and Welling, M., Auto-Encoding Variational Bayes, Proceedings of the International Conference on Learning Representations (ICLR), 2014.

5. Broderick, T., Boyd, N., Wibisono, A., Wilson, A. C., & Jordan, M., Streaming Variational Bayes, Advances in Neural Information Processing Systems (pp. 1727-1735), 2013.

6. Hoffman, M., Blei, D. M., Wang, C., and Paisley, J., Stochastic Variational Inference, Journal of Machine Learning Research, 14:1303–1347, 2013.

Read More..

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..

Claude Shannons Ultimate Machine

Claude Shannon is best know for inventing digital logic, proving that boolean logic and binary arithmetic can be implemented with just AND, OR and NOT (or indeed just NAND or NOR). Not content with that discovery he went on to found the science of information theory. But perhaps his crowning achievement is the invention of the "ultimate machine" a device of cunning digital simplicity.


from The Universal Machine http://universal-machine.blogspot.com/

Put the internet to work for you.

Turn off or edit this Recipe

Recommended for you

Read More..

Building A Visual Planetary Time Machine

Posted by Randy Sargent, Google/Carnegie Mellon University; Matt Hancher and Eric Nguyen, Google; and Illah Nourbakhsh, Carnegie Mellon University

When a societal or scientific issue is highly contested, visual evidence can cut to the core of the debate in a way that words alone cannot — communicating complicated ideas that can be understood by experts and non-experts alike. After all, it took the invention of the optical telescope to overturn the idea that the heavens revolved around the earth.

Last month, Google announced a zoomable and explorable time-lapse view of our planet. This time-lapse Earth enables you explore the last 29 years of our planet’s history — from the global scale to the local scale, all across the planet. We hope this new visual dataset will ground debates, encourage discovery, and shift perspectives about some of today’s pressing global issues.

This project is a collaboration between Google’s Earth Engine team, Carnegie Mellon University’s CREATE Lab, and TIME Magazine — using nearly a petabyte of historical record from USGS’s and NASA’s Landsat satellites. And in this post, we’d like to give a little insight into the process required to build this time-lapse view of our planet.

Previews of the phenomena visible in these time-lapses.

First well describe Google’s Earth Engine system for deriving the time-series imagery. Second, well tell you more about CMU’s open-source “Time Machine” software for creating and streaming large, explorable time-series imagery.

Annual Composites: Distilling a Massive Dataset

Google Earth Engine brings together the worlds scientific satellite imagery — over a petabyte of multispectral imagery recording over 40 years of history — and makes it available online with tools that scientists, independent researchers, and nations can use to mine this massive warehouse of data to detect changes, map trends and quantify differences on the Earths surface using Google’s computational infrastructure. Today, the platform is used to monitor the Amazon and estimate forest carbon in Tanzania, among hundreds of other partners developing new uses for the technology.

Using Earth Engine, we first built annual global mosaics at a resolution of 30 meters per pixel for each year from 1984 through 2012. We started with a total of 2,068,467 scenes from the Landsat 4, 5, and 7 satellites, comprising 909 terabytes of data. The Earth’s atmosphere is a constantly-shifting sea of clouds, so in order to assemble a seamless cloud-free view of each year we analyzed all the images available at each location and used a simple cloud model to separate out the clouds from the ground. To help correct for atmospheric and seasonal effects, we used an additional 20TB of data from the MODIS MCD43A4 product to build a cloud-free low-resolution model of the Earth over time. We combined all this to produce a statistical estimate of the color of each pixel for every year for which data was available. Producing the final 29 global mosaics took a bit less than a day and consumed approximately 260,000 core-hours of CPU.

Some areas of the planet are almost perpetually cloudy, obscuring satellite views. In addition, before the more capable Landsat 7 began operating in 1999, coverage in some areas of the world was sparse, particularly in Asia, for various operational and technological reasons. We wrestled with how best to visualize areas with missing or cloud-obscured images from each year. In the end, after much experimentation, we chose to simply interpolate between valid image years. Other techniques, such as greying out invalid data, created distractingly large artifacts, visually drowning out the valid information. However, the downside with the approach we have taken is that it can be difficult to tell which data is original and which is interpolated. We are exploring the possibility of including a view that allows drilling down into the non-interpolated, original mosaics.

"Time Machine": An HTML5 Time-Series Exploration Tool

Once we had produced the final global images, we adapted the Carnegie Mellon CREATE Lab’s open-source “Time Machine” software, which enables authoring, streaming, and exploring very-high-resolution videos. Time Machine videos take advantage of the power of HTML5 and modern web browsers: they are streamed as multiresolution, overlapping video tiles and displayed in a web page by manipulating the HTML5 <video> tag, in much the same way that Google Maps first demonstrated using the HTML <img> tag.

Examples of zoomable timelapses with hundreds of millions or billions of pixels per frame include documenting plant growth, bee colony collapse, and very-large-scale simulations of the universe. Time-lapse Earth, however, sets a new record for giant videos: each frame of the video is a global Mercator-projected map with a resolution of 30 meters per pixel at the equator, for a total of 1.78 trillion pixels per frame. That’s about a million times larger than a standard HD video stream. In order to scale to such large videos, we needed to integrate Time Machine’s data production pipeline into Earth Engine and the rest of Google’s infrastructure. Encoding the final video tiles consumed approximately 1.4 million core-hours of CPU in Google’s data centers over the course of about a day. For CMUs researchers, this would have been impossible without Googles resources.

Combining all three phases of product generation:

• Total processing time: 3 days
• Total CPU usage: 1.8 million core-hours
• Peak CPU usage: 66,000 simultaneous cores

Destination locations of top 1500 share links, weighted by number of visits.

Time-lapse Earth is powerful because it helps us to access and construct the story of our planet. That story will become richer with each release, as we continue to improve fidelity and add data. The story-teller is everyone — scientists and citizens alike provide the real value by interacting, exploring, layering their knowledge upon the globe, and sharing their insights so that we can all better understand our world.

We are especially proud of the collaboration that made time-lapse Earth possible, and believe it to be an exemplar of how industry, academia, government, and the press can benefit from working together deeply over a period of years. By drawing on the strengths of each member of the collaborative community, Google strives to integrate the worlds technical expertise and knowledge in order to tackle innovative and groundbreaking projects. In doing so, it is our goal to deliver an impactful service, one that can put a focus on the dramatic effect we are having on our planet.

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..

Fast Accurate Detection of 100 000 Object Classes on a Single Machine

Posted by Tom Dean, Google Research

Humans can distinguish among approximately 10,000 relatively high-level visual categories, but we can discriminate among a much larger set of visual stimuli referred to as features. These features might correspond to object parts, animal limbs, architectural details, landmarks, and other visual patterns we don’t have names for, and it is this larger collection of features we use as a basis with which to reconstruct and explain our day-to-day visual experience. Such features provide the components for more complicated visual stimuli and establish a context essential for us to resolve ambiguous scenes.

Contrary to current practice in computer vision, the explanatory context required to resolve a visual detail may not be entirely local. A flash of red bobbing along the ground might be a child’s toy in the context of a playground or a rooster in the context of a farmyard. It would be useful to have a large number of feature detectors capable of signaling the presence of such features, including detectors for sandboxes, swings, slides, cows, chickens, sheep and farm machinery necessary to establish the context for distinguishing between these two possibilities.

This year’s winner of the CVPR Best Paper Award, co-authored by Googlers Tom Dean, Mark Ruzon, Mark Segal, Jonathon Shlens, Sudheendra Vijayanarasimhan and Jay Yagnik, describes technology that will enable computer vision systems to extract the sort of semantically rich contextual information required to recognize visual categories even when a close examination of the pixels spanning the object in question might not be sufficient for identification in the absence of such contextual clues. Specifically, we consider a basic operation in computer vision that involves determining for each location in an image the degree to which a particular feature is likely to be present in the image at that particular location.

This so-called convolution operator is one of the key operations used in computer vision and, more broadly, all of signal processing. Unfortunately, it is computationally expensive and hence researchers use it sparingly or employ exotic SIMD hardware like GPUs and FPGAs to mitigate the computational cost. We turn things on their head by showing how one can use fast table lookup — a method called hashing — to trade time for space, replacing the computationally-expensive inner loop of the convolution operator — a sequence of multiplications and additions — required for performing millions of convolutions with a single table lookup.

We demonstrate the advantages of our approach by scaling object detection from the current state of the art involving several hundred or at most a few thousand of object categories to 100,000 categories requiring what would amount to more than a million convolutions. Moreover, our demonstration was carried out on a single commodity computer requiring only a few seconds for each image. The basic technology is used in several pieces of Google infrastructure and can be applied to problems outside of computer vision such as auditory signal processing.

On Wednesday, June 26, the Google engineers responsible for the research were awarded Best Paper at a ceremony at the IEEE Conference on Computer Vision and Pattern Recognition held in Portland Oregon. The full paper can be found here.

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..

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..