Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Reservoir computing: Adaptive online machine le...

Reservoir computing: Adaptive online machine learning and neural networks

Neri van Otten, Data Scientist at Conversocial at Data Science London @ds_ldn meetup March 28th, 20123

Avatar for Data Science London

Data Science London

April 23, 2013
Tweet

More Decks by Data Science London

Other Decks in Technology

Transcript

  1. What is Reservoir Computing?  Temporal Recurrent Neural Network (Dominey

    1995)  Liquid State Machines (Natschläger, Maass and Markram 2002)  Echo State Networks (Jaeger 2001)  Decorrelation-Backpropagation Learning (Steil 2004)
  2. Recurrent Neural Networks (RNN)  RNN attractive solution to many

    engineering problems  learn by example  model highly nonlinear systems  Training phase is slow and unstable  Reservoir Computing avoids this problem by not training it at all
  3. RC Explained  Large random RNN as an excitable medium

     Driven by input signals, each unit in the RNN creates its own nonlinear transform of the input  Output signals are read out from excited RNN  Typically a simple linear combination of the reservoir signals  Outputs trained in supervised way  Typically by linear regression of the teacher output on the tapped reservoir signals.
  4. Advantages of RC  Training phase is computationally fast 

    Works as a dynamic system just as other RNN  Form of memory is used  Suited for a wide variety of problems:  epileptic seizure detection  brain computing interfaces  time series prediction
  5. Use RC with OGER  > import Oger  >

    resnode = Oger.nodes.ReservoirNode(output_dim = 100)  > readoutnode = Oger.nodes.RidgeRegressionNode()  > flow = resnode + readoutnode  > flow.train(data)