Neural networks for data-streams

Primary tabs

Hoeffding Trees are an established method for classification; at the same time, gradient descent methods are becoming increasingly popular, owing in part to the successes of deep learning. We are investigating the benefits of using GPUs for data-stream learning due to their high scalability.


In this project we are studying new ways to adapt Neural Networks for real-time analysis. The main challenges we are facing are:

  • Gradient descent methods have strong convergence guarantees but this convergence is slow. This method requires a large amount of samples in order to achieve good accuracy, and as a consequence,  the training requires large amount of time.
  • Neural Networks are trained to solve an specific task due to their high sensitivity to hyper-parameters configurations.
  • Moving data efficiently  to/from the GPU is a the key factor  to meet the real-time analysis constrains.


We are currently studying how prune NN hyper-parameters so they can become an effective ‘off-the-shelf’ data-streams solution. The ideal target we pursue is:

  • Be able to make a classification at any time.
  • Deal with a potentially infinite number of examples.
  • Access each example in the stream just once.
    • In a bounded pre-defined time.
    • With limited amount of memory.