Google team’s neural network approach works on street numbers

( – A Google team has worked out a neural network approach to transcribe house numbers from Street View images, reading those house numbers and matching them to their geolocation. Google Street View has the user advantage of allowing the user to advance to street level to see the area of interest in detail. Google’s accomplishment in automation is impressive both in the scope of the task involved and the way in which it was done. Consider that Google’s Street View cameras have recorded massive numbers of panoramic images carrying massive numbers of house numbers. “We can for example transcribe all the views we have of street numbers in France in less than an hour using our Google infrastructure,” said the researchers, who have authored the paper, “Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks.” Ian J. Goodfellow, Yaroslav Bulatov, Julian Ibarz, Sacha Arnoud, Vinay Shet are the authors. The team used a neural network that contains 11 levels of neurons trained to spot numbers in images. The researchers describe the network as “a deep convolutional neural network that operates directly on the image pixels.” They said they used the DistBelief implementation of deep neural networks to train large, distributed neural networks on high quality images. (More information “Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks“)

Choosing the right estimator

Often the hardest part of solving a machine learning problem can be finding the right estimator for the job because as we all know different estimators are better suited for different types of data and different problems.

The flowchart below is designed to give users a bit of a rough guide on how to approach problems with regard to which estimators to try on your data. (reference: (Read more))

Choosing the right estimator

Machine Learning resources

Great resources for anyone who would like to learn more about Machine Learning:

  • Apache Mahout – machine learning library for Hadoop.
  • brain – Neural networks in JavaScript.
  • Cloudera Oryx – real-time large-scale machine learning.
  • Concurrent Pattern – machine learning library for Cascading.
  • convnetjs – Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.
  • Decider – Flexible and Extensible Machine Learning in Ruby.
  • etcML – text classification with machine learning.
  • Etsy Conjecture – scalable Machine Learning in Scalding.
  • H2O – statistical, machine learning and math runtime for Hadoop.
  • MLbase – distributed machine learning libraries for the BDAS stack.
  • MLPNeuralNet – Fast multilayer perceptron neural network library for iOS and Mac OS X.
  • nupic – Numenta Platform for Intelligent Computing: a brain-inspired machine intelligence platform, and biologically accurate neural network based on cortical learning algorithms.
  • PredictionIO – machine learning server built on Hadoop, Mahout and Cascading.
  • scikit-learn – scikit-learn: machine learning in Python.
  • Spark MLlib – a Spark implementation of some common machine learning (ML) functionality.
  • Vowpal Wabbit – learning system sponsored by Microsoft and Yahoo!.
  • WEKA – suite of machine learning software.

Get the full list here »