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..

An Unprecedented Look at Stuxnet the World’s First Digital Weapon

My recent book, The Universal Machine, opens its chapter on hacking with the deployment of the Stuxnet computer virus. Allegedly created by Israel and US intelligence services to target Irans nuclear bomb programme it was the worlds first state against state digital weapon. With North Korea now being accused of hacking Sony perhaps its time to revisit this story. Wired has recently published an excerpt from a new book on Stuxnet - recommended reading.



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..

These robots cheer for absent fans at South Korean baseball games

File this one under "weird." The South Korean baseball team, The Eagles, havent won the championship in 15 years; theyre commonly know as The Chickens! But still their loyal fans come to watch and cheer their side on. So of course, being South Korea, it was natural for them to create robots who could cheer for absent fans. An unusual use of the concept of telepresence. Watch the video below to see how its done. This story was brought to my attention by my colleague Mark.



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..

VLDB 2015 and Database Research at Google

Posted by Corinna Cortes, Head of Google Research NY and Cong Yu, Research Scientist

This week, Kohala, Hawaii hosts the 41st International Conference of Very Large Databases (VLDB 2015), a premier annual international forum for data management and database researchers, vendors, practitioners, application developers and users. As a leader in Database research, Google will have a strong presence at VLDB 2015 with many Googlers publishing work, organizing workshops and presenting demos.

The research Google is presenting at VLDB involves the work of Structured Data teams who are building intelligent and efficient systems to discover, annotate and explore structured data from the Web, surfacing them creatively through Google products (such as structured snippets and table search), as well as engineering efforts that create scalable, reliable, fast and general-purpose infrastructure for large-scale data processing (such as F1, Mesa, and Google Clouds BigQuery).

If you are attending VLDB 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 VLDB 2015 in the list below (Googlers highlighted in blue).

Google is a Gold Sponsor of VLDB 2015.

Papers:
Keys for Graphs
Wenfei Fan, Zhe Fan, Chao Tian, Xin Luna Dong

In-Memory Performance for Big Data
Goetz Graefe, Haris Volos, Hideaki Kimura, Harumi Kuno, Joseph Tucek, Mark Lillibridge, Alistair Veitch

The Dataflow Model: A Practical Approach to Balancing Correctness, Latency, and Cost in Massive-Scale, Unbounded, Out-of-Order Data Processing
Tyler Akidau, Robert Bradshaw, Craig Chambers, Slava Chernyak, Rafael Fernández-Moctezuma, Reuven Lax, Sam McVeety, Daniel Mills, Frances Perry, Eric Schmidt, Sam Whittle

Resource Bricolage for Parallel Database Systems
Jiexing Li, Jeffrey Naughton, Rimma Nehme

AsterixDB: A Scalable, Open Source BDMS
Sattam Alsubaiee, Yasser Altowim, Hotham Altwaijry, Alex Behm, Vinayak Borkar, Yingyi Bu, Michael Carey, Inci Cetindil, Madhusudan Cheelangi, Khurram Faraaz, Eugenia Gabrielova, Raman Grover, Zachary Heilbron, Young-Seok Kim, Chen Li, Guangqiang Li, Ji Mahn Ok, Nicola Onose, Pouria Pirzadeh, Vassilis Tsotras, Rares Vernica, Jian Wen, Till Westmann

Knowledge-Based Trust: A Method to Estimate the Trustworthiness of Web Sources
Xin Luna Dong, Evgeniy Gabrilovich, Kevin Murphy, Van Dang, Wilko Horn, Camillo Lugaresi, Shaohua Sun, Wei Zhang

Efficient Evaluation of Object-Centric Exploration Queries for Visualization
You Wu, Boulos Harb, Jun Yang, Cong Yu

Interpretable and Informative Explanations of Outcomes
Kareem El Gebaly, Parag Agrawal, Lukasz Golab, Flip Korn, Divesh Srivastava

Take me to your leader! Online Optimization of Distributed Storage Configurations
Artyom Sharov, Alexander Shraer, Arif Merchant, Murray Stokely

TreeScope: Finding Structural Anomalies In Semi-Structured Data
Shanshan Ying, Flip Korn, Barna Saha, Divesh Srivastava

Workshops:
Workshop on Big-Graphs Online Querying - Big-O(Q) 2015
Workshop co-chair: Cong Yu

3rd International Workshop on In-Memory Data Management and Analytics
Program committee includes: Sandeep Tata

High-Availability at Massive Scale: Building Googles Data Infrastructure for Ads
Invited talk at BIRTE by: Ashish Gupta, Jeff Shute

Demonstrations:
KATARA: Reliable Data Cleaning with Knowledge Bases and Crowdsourcing
Xu Chu, John Morcos, Ihab Ilyas, Mourad Ouzzani, Paolo Papotti, Nan Tang, Yin Ye

Error Diagnosis and Data Profiling with Data X-Ray
Xiaolan Wang, Mary Feng, Yue Wang, Xin Luna Dong, Alexandra Meliou

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..

Forget Turing the Lovelace Test Has a Better Shot at Spotting AI

I recently blogged about a chatbot, called Eugene Goostman, that was claimed to have passed Alan Turings famous measure of machine intelligence in June by posing as a Ukrainian teenager with questionable language skills. Motherboard notices that "the world went nuts for about an hour before realizing that the bot, far from having achieved human-level intelligence, was actually pretty dumb." This article proposes the Lovelace test for AI that demands an act of creativity from an AI rather than automated conversational skills - its an interesting idea and would be a good way of honouring Ada Lovelace.

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..

How To Bypass Megaupload Wait Time And Download At Maximum Speed !!!

Megaupload is one of the leading file sharing network ranking next to Rapidshare File hosting. Megaupload offers a better set of features for downloading for free users which inclues resume support. Recently,i came across a trick in one of orkut communities to skip the wait time in Megaupload. I exptected the bug would be fixed soon enough although it hasn’t been till date.So i just thought of sharing it here now. By the way, it needn’t always work and usually gets redirected to regular download page after 2-3 downloads. So if you’re lucky enough,it will work out for you.

This is a simple trick.

The megaupload download link usually looks like this:

http://www.megaupload.com/?d=abc123

All you need to do is insert mgr_dl.php before the “?’” mark.So the link will now look like this.

http://www.megaupload.com/mgr_dl.php?d=abc123

Just apply this to trick on your download links and you will be able to download at maximum speed and also eliminate the wait time :) :D

Read More..

Hardware Initiative at Quantum Artificial Intelligence Lab

Posted by Hartmut Neven, Director of Engineering

The Quantum Artificial Intelligence team at Google is launching a hardware initiative to design and build new quantum information processors based on superconducting electronics. We are pleased to announce that John Martinis and his team at UC Santa Barbara will join Google in this initiative. John and his group have made great strides in building superconducting quantum electronic components of very high fidelity. He recently was awarded the London Prize recognizing him for his pioneering advances in quantum control and quantum information processing. With an integrated hardware group the Quantum AI team will now be able to implement and test new designs for quantum optimization and inference processors based on recent theoretical insights as well as our learnings from the D-Wave quantum annealing architecture. We will continue to collaborate with D-Wave scientists and to experiment with the “Vesuvius” machine at NASA Ames which will be upgraded to a 1000 qubit “Washington” processor.

Read More..

Amazon at 20 what has the online giant ever done for retail

You may not have noticed but Amazon recently celebrated its 20th birthday. You may or not be a regular user (I certainly am). It was originally billed a the "Earths Biggest Bookstore" featuring over one million titles. Twenty years later it has over 270m active accounts and claims to have more than 2m third-party vendors selling millions of products through its marketplace platform. Amazon is comfortable with the term "disruptive." Its disrupted the bookshop and publishing industries and is disrupting other retail industries. The Guardian recently published an interesting article about the impact Amazon has had - recommended.




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..

Computer Hangs at Start up

Q. My Computer Hangs for about 2 to 3 minutes at Start-up. I cannot access the Start button. What can i do?

A. The problem may be due to a service "Background Intelligent Transfer" running at background.
In order to solve this problem, perform the following steps:

• Click on Start >> Run.
• Type "msconfig" without quotes then click on OK
• Now, Go to Services tab, Disable Background Intelligent Transfer Service, apply the changes
• Reboot your system.
  

Thats all...

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..

Get Smart exhibition at MOTAT

MOTAT in Auckland has a new exhibition called Get Smart - NZ Wired in the Digital World. The museum says "Get Smart will take visitors on an immersive journey of discovery and nostalgia as they explore the origins of the smart devices that surround us today. Learn about how networks and computing have come tog ether to provide instant connectivity and take a closer look at the Kiwi innovators and entrepreneurs who have contributed to this thrilling digital age. Get Smart investigates the growth of computing, gaming and communications to illustrate how the powerful machines now carried in pockets and purses have become faster, cheaper, and smarter." If youve never visited MOTAT perhaps now you should and if youve not been for years its obviously time to return. MOTAT is located at Western Springs, a short bus ride from downtown Auckland.

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

Put the internet to work for you.

Delete or edit this Recipe

Read More..

High Quality Object Detection at Scale

Google Engineers Christian Szegedy, Scott Reed^*, Dumitru Erhan, and Dragomir Anguelov

Update - 26/02/2015
We recently discovered a bug in the evaluation methodology of our object detector. Consequently, the large numbers we initially reported below are not realistic, due to the fact that our separately trained context extractor was contaminated with half of the validation set images. Therefore, our initial results were overly optimistic and were not attainable by the methodology described in the paper. Re-evaluating our initial results, we have restricted ourselves to reporting only the single-model results on the other half of the dedicated validation set without retraining the models. With the updated evaluation, we are still able to report the best single-model result on the ILSVRC 2014 detection challenge data set, with 0.43 mAP when combining both Selective Search and MultiBox proposals with our post-classification model. The original draft of our paper "Scalable, High Quality Object Detection" has been updated to reflect this information. We are deeply sorry if our initial reported results caused any confusion in the community. Original post follows below. 
-C. Szegedy, S. Reed, D. Erhan, and D. Anguelov

The ILSVRC detection challenge is an influential academic benchmark for measuring the quality of object detection. This summer, the GoogLeNet team reported top results in the 2014 edition of the challenge, with ~2X improvement over the previous year’s best results. However, the quality of our results came at a high computational cost: processing each image took about two minutes on a state-of-the-art workstation.

Naturally, we began to think of how we could both improve the accuracy and reduce the computation time needed. Given the already high quality of previous results like those of GoogLeNet^[6], we expected that further improvements to detection quality would be increasingly hard to achieve. In our recent paper Scalable, High Quality Object Detection^[7], we detail advances that instead have resulted in an accelerated rate of progress in object detection:

Evolution of detection quality over time. On the y axis is the mean average precision of the best published results at any given time. The blue line shows result using individual models, the red line is multi-model ensembles. Overfeat^[8] was the state-of-the-art at end of last year, followed by R-CNN^[1] published in May. The later measurement points are the results of our team.^[6,7]

As seen in the plot above, the mean average precision has been improved since August from 0.45 to 0.56: a 23% relative gain. The new approach can also match the quality of the former best solution with 140X reduced computational resources.

Most current approaches for object detection employ two phases^[1]: in the first phase, some hand-engineered algorithm proposes regions of interest in the image. In the second phase, each proposed region is run through a deep neural network, identifying which proposed patches correspond to an object (and what that object is).

For the first phase, the common wisdom^[1,2,3,4] was that it took skillfully crafted code to produce high quality region proposals. This has come with a drawback though: these methods don’t produce reliable scoring for the proposed regions. This forces the second phase to evaluate most of the proposed patches in order to achieve good results.

So we revisited our prior “MultiBox” work^[5], in which we let the computer learn to pick the proposals to see whether we could avoid relying on any of the hand-crafted methods above. Although the MultiBox method, using previous generation vision network architectures, could not compete with hand-engineered proposal approaches, there were several advantages of fully relying on machine learning only. First, the quality of proposals increases with each new improved network architecture or training methodology without additional programming effort. Second, the regions come with confidence scores which are used for trading off running time versus quality. Additionally, the implementation is simplified.

Once we used new variants of the network architecture introduced in [6], MultiBox also started to perform much better; Now, we could match the coverage of alternative methods with half as many proposal patches. Also, we changed our networks to take the context of objects into account, fueling additional quality gains for the second phase. Furthermore, we came up with a new way to train deep networks to learn more robustly even when some objects are not annotated in the training set, which improved both phases.

Besides the significant gains in mean average precision, we can now cut the number of evaluated patches dramatically at a modest loss of quality: the task that used to take 2 minutes of processing time for a single image on a workstation by the GoogLeNet ensemble (of 6 networks), is now performed under a second using a single network without using GPUs. If we constrain ourselves to a single category like “dog”, we can now process 50 images/second on the same machine by a more streamlined approach^[7] that skips the proposal generation step altogether.

As a core area of research in computer vision, object detection is used for providing strong signals for photo and video search, while high quality detection could prove useful for self-driving cars and automatically generated image captions. We look forward to the continuing research in this field.

References:

[1]  Rich feature hierarchies for accurate object detection and semantic segmentation
by Ross Girshick and Jeff Donahue and Trevor Darrell and Jitendra Malik (CVPR, 2014)

[2]  Prime Object Proposals with Randomized Prim’s Algorithm
by Santiago Manen, Matthieu Guillaumin and Luc Van Gool

[3]  Edge boxes: Locating object proposals from edges
by Lawrence C Zitnick, and Piotr Dollàr (ECCV 2014)

[4]  BING: Binarized normed gradients for objectness estimation at 300fps
by Ming-Ming Cheng, Ziming Zhang, Wen-Yan Lin and Philip Torr (CVPR 2014)

[5]  Scalable Object Detection using Deep Neural Networks
by Dumitru Erhan, Christian Szegedy, Alexander Toshev, and Dragomir Anguelov

[6]  Going deeper with convolutions
by Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke and Andrew Rabinovich

[7]  Scalable, high quality object detection
by Christian Szegedy, Scott Reed, Dumitru Erhan and Dragomir Anguelov

[8]  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Network by Pierre Sermanet, David Eigen, Xiang Zhang, Michael Mathieu, Rob Fergus and Yann LeCun


* A PhD student at University of Michigan -- Ann Arbor and Software Engineering Intern at Google^?

Read More..

ICSE 2015 and Software Engineering Research at Google

Posted by Mohsen Vakilian, Software Engineer

The large scale of our software engineering efforts at Google often pushes us to develop cutting-edge infrastructure. In May 2015, at the International Conference on Software Engineering (ICSE 2015), we shared some of our software engineering tools and practices and collaborated with the research community through a combination of publications, committee memberships, and workshops. Learn more about some of our research below (Googlers highlighted in blue).

Google was a Gold supporter of ICSE 2015.

Technical Research Papers:
A Flexible and Non-intrusive Approach for Computing Complex Structural Coverage Metrics
Michael W. Whalen, Suzette Person, Neha Rungta, Matt Staats, Daniela Grijincu

Automated Decomposition of Build Targets
Mohsen Vakilian, Raluca Sauciuc, David Morgenthaler, Vahab Mirrokni

Tricorder: Building a Program Analysis Ecosystem
Caitlin Sadowski, Jeffrey van Gogh, Ciera Jaspan, Emma Soederberg, Collin Winter

Software Engineering in Practice (SEIP) Papers:
Comparing Software Architecture Recovery Techniques Using Accurate Dependencies
Thibaud Lutellier, Devin Chollak, Joshua Garcia, Lin Tan, Derek Rayside, Nenad Medvidovic, Robert Kroeger

Technical Briefings:
Software Engineering for Privacy in-the-Large
Pauline Anthonysamy, Awais Rashid

Workshop Organizers:
2nd International Workshop on Requirements Engineering and Testing (RET 2015)
Elizabeth Bjarnason, Mirko Morandini, Markus Borg, Michael Unterkalmsteiner, Michael Felderer, Matthew Staats

Committee Members:
Caitlin Sadowski - Program Committee Member and Distinguished Reviewer Award Winner
James Andrews - Review Committee Member
Ray Buse - Software Engineering in Practice (SEIP) Committee Member and Demonstrations Committee Member
John Penix - Software Engineering in Practice (SEIP) Committee Member
Marija Mikic - Poster Co-chair
Daniel Popescu and Ivo Krka - Poster Committee Members

Read More..

Vote for Lovelace Babbage at LEGO Ideas

If you are a regular reader of this blog youll know that Im a big fan of Charles Babbage and Ada Lovelace. Consequently Id be certain to want a set of these Lovelace & Babbage Lego bricks should they ever be made. They would be a  fanciful and historical collection of bricks that pay homage to the Victorian roots of the computer age. The set would let you build a lego steam punk analytical engine within which you could embed a Raspberry Pi or similar mini-computer board. You can find out more on the Lego Ideas website.

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..

Google Computer Vision research at CVPR 2015

Posted by Vincent Vanhoucke, Google Research Scientist

Much of the worlds data is in the form of visual media. In order to utilize meaningful information from multimedia and deliver innovative products, such as Google Photos, Google builds machine-learning systems that are designed to enable computer perception of visual input, in addition to pursuing image and video analysis techniques focused on image/scene reconstruction and understanding.

This week, Boston hosts the 2015 Conference on Computer Vision and Pattern Recognition (CVPR 2015), the premier annual computer vision event comprising the main CVPR conference and several co-located workshops and short courses. As a leader in computer vision research, Google will have a strong presence at CVPR 2015, with many Googlers presenting publications in addition to hosting workshops and tutorials on topics covering image/video annotation and enhancement, 3D analysis and processing, development of semantic similarity measures for visual objects, synthesis of meaningful composites for visualization/browsing of large image/video collections and more.

Learn more about some of our research in the list below (Googlers highlighted in blue). If you are attending CVPR this year, 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 hundreds of millions of people. Members of the Jump team will also have a prototype of the camera on display and will be showing videos produced using the Jump system on Google Cardboard.

Tutorials:
Applied Deep Learning for Computer Vision with Torch
Koray Kavukcuoglu, Ronan Collobert, Soumith Chintala

DIY Deep Learning: a Hands-On Tutorial with Caffe
Evan Shelhamer, Jeff Donahue, Yangqing Jia, Jonathan Long, Ross Girshick

ImageNet Large Scale Visual Recognition Challenge Tutorial
Olga Russakovsky, Jonathan Krause, Karen Simonyan, Yangqing Jia, Jia Deng, Alex Berg, Fei-Fei Li

Fast Image Processing With Halide
Jonathan Ragan-Kelley, Andrew Adams, Fredo Durand

Open Source Structure-from-Motion
Matt Leotta, Sameer Agarwal, Frank Dellaert, Pierre Moulon, Vincent Rabaud

Oral Sessions:
Modeling Local and Global Deformations in Deep Learning: Epitomic Convolution, Multiple Instance Learning, and Sliding Window Detection
George Papandreou, Iasonas Kokkinos, Pierre-André Savalle

Going Deeper with Convolutions
Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich

DynamicFusion: Reconstruction and Tracking of Non-Rigid Scenes in Real-Time
Richard A. Newcombe, Dieter Fox, Steven M. Seitz

Show and Tell: A Neural Image Caption Generator
Oriol Vinyals, Alexander Toshev, Samy Bengio, Dumitru Erhan

Long-Term Recurrent Convolutional Networks for Visual Recognition and Description
Jeffrey Donahue, Lisa Anne Hendricks, Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, Trevor Darrell

Visual Vibrometry: Estimating Material Properties from Small Motion in Video
Abe Davis, Katherine L. Bouman, Justin G. Chen, Michael Rubinstein, Frédo Durand, William T. Freeman

Fast Bilateral-Space Stereo for Synthetic Defocus
Jonathan T. Barron, Andrew Adams, YiChang Shih, Carlos Hernández

Poster Sessions:
Learning Semantic Relationships for Better Action Retrieval in Images
Vignesh Ramanathan, Congcong Li, Jia Deng, Wei Han, Zhen Li, Kunlong Gu, Yang Song, Samy Bengio, Charles Rosenberg, Li Fei-Fei

FaceNet: A Unified Embedding for Face Recognition and Clustering
Florian Schroff, Dmitry Kalenichenko, James Philbin

A Mixed Bag of Emotions: Model, Predict, and Transfer Emotion Distributions
Kuan-Chuan Peng, Tsuhan Chen, Amir Sadovnik, Andrew C. Gallagher

Best-Buddies Similarity for Robust Template Matching
Tali Dekel, Shaul Oron, Michael Rubinstein, Shai Avidan, William T. Freeman

Articulated Motion Discovery Using Pairs of Trajectories
Luca Del Pero, Susanna Ricco, Rahul Sukthankar, Vittorio Ferrari

Reflection Removal Using Ghosting Cues
YiChang Shih, Dilip Krishnan, Frédo Durand, William T. Freeman

P3.5P: Pose Estimation with Unknown Focal Length
Changchang Wu

MatchNet: Unifying Feature and Metric Learning for Patch-Based Matching
Xufeng Han, Thomas Leung, Yangqing Jia, Rahul Sukthankar, Alexander C. Berg

Inferring 3D Layout of Building Facades from a Single Image
Jiyan Pan, Martial Hebert, Takeo Kanade

The Aperture Problem for Refractive Motion
Tianfan Xue, Hossein Mobahei, Frédo Durand, William T. Freeman

Video Magnification in Presence of Large Motions
Mohamed Elgharib, Mohamed Hefeeda, Frédo Durand, William T. Freeman

Robust Video Segment Proposals with Painless Occlusion Handling
Zhengyang Wu, Fuxin Li, Rahul Sukthankar, James M. Rehg

Ontological Supervision for Fine Grained Classification of Street View Storefronts
Yair Movshovitz-Attias, Qian Yu, Martin C. Stumpe, Vinay Shet, Sacha Arnoud, Liron Yatziv

VIP: Finding Important People in Images
Clint Solomon Mathialagan, Andrew C. Gallagher, Dhruv Batra

Fusing Subcategory Probabilities for Texture Classification
Yang Song, Weidong Cai, Qing Li, Fan Zhang

Beyond Short Snippets: Deep Networks for Video Classification
Joe Yue-Hei Ng, Matthew Hausknecht, Sudheendra Vijayanarasimhan, Oriol Vinyals, Rajat Monga, George Toderici

Workshops:
THUMOS Challenge 2015
Program organizers include: Alexander Gorban, Rahul Sukthankar

DeepVision: Deep Learning in Computer Vision 2015
Invited Speaker: Rahul Sukthankar

Large Scale Visual Commerce (LSVisCom)
Panelist: Luc Vincent

Large-Scale Video Search and Mining (LSVSM)
Invited Speaker and Panelist: Rahul Sukthankar
Program Committee includes: Apostol Natsev

Vision meets Cognition: Functionality, Physics, Intentionality and Causality
Program Organizers include: Peter Battaglia

Big Data Meets Computer Vision: 3rd International Workshop on Large Scale Visual Recognition and Retrieval (BigVision 2015)
Program Organizers include: Samy Bengio
Includes speaker Christian Szegedy - “Scalable approaches for large scale vision”

Observing and Understanding Hands in Action (Hands 2015)
Program Committee includes: Murphy Stein

Fine-Grained Visual Categorization (FGVC3)
Program Organizers include: Anelia Angelova

Large-scale Scene Understanding Challenge (LSUN)
Winners of the Scene Classification Challenge: Julian Ibarz, Christian Szegedy and Vincent Vanhoucke
Winners of the Caption Generation Challenge: Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan

Looking from above: when Earth observation meets vision (EARTHVISION)
Technical Committee includes: Andreas Wendel

Computer Vision in Vehicle Technology: Assisted Driving, Exploration Rovers, Aerial and Underwater Vehicles
Invited Speaker: Andreas Wendel
Program Committee includes: Andreas Wendel

Women in Computer Vision (WiCV)
Invited Speaker: Mei Han

ChaLearn Looking at People (sponsor)

Fine-Grained Visual Categorization (FGVC3) (sponsor)

Read More..

How to Learn PC Repair at Home

Although you can gain a Computer repair education from a traditional university, this takes a lot of time and money. An easier way to learn the trade is to teach userself Computer repair at home. With the skills you learn from trying it at home, you should be able to fix both software and hardware problems on nearly any computer. Computer repair skills will open user career options and make you more useful to friends and family.

Instructions


Take classes from an online university. Penn Foster Career School offers an at-home Computer Maintenance and Repair program that teaches you about hardware, software, networking and troubleshooting. Also try classes from CBT Direct or Delmar Learning.


Purchase a few older Computers that you can use to study on. Open up the case while the power is unplugged so you can have a look at the innards of the computer. This is a better idea than testing out Computer repair concepts on user main computer as you may end up making a wrong move and damaging the computer beyond easy repair.


Read books about Computer repair. There are books at varying difficulty levels so you can gain a complete education. Visit a library or a bookstore to browse their selection of Computer repair books. "A+ Guide to Computer Hardware Maintenance and Repair" by Michael Graves is a good book for dealing with Computer hardware repair and can prepare you for A+ certification.


Subscribe to computer magazines such as ComputerWorld and ComputerMag. Not only will you learn Computer repair techniques, but you will also learn about new updates in technology throughout the computer industry. Since computer technology improves drastically every year, its important to stay up-to-date.


Watch videos about Computer repair on the internet. Video Jug has an entire section of how-to videos devoted to computers. Learn about hardware, software and more. YouTube has many Computer repair tutorial videos as well. Watch these videos when ever youre stuck on a problem or you want to learn a new technique.


Read more: http://www.ehow.com/how_6120991_learn-pc-repair-home.html#ixzz1SRWm6UQP

Read More..