Neri Van Otten [email protected] 

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) 

Types of Neural Networks 

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 

A Reservoir is like Water 

Reservoir Computing (RC) 

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. 

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 

Feedback Controller  “Feedback control by online learning an inverse model” (Waegeman 2012) 

Training 

Testing 

Feedback Controller 

Use RC with OGER  > import Oger  > resnode = Oger.nodes.ReservoirNode(output_dim = 100)  > readoutnode = Oger.nodes.RidgeRegressionNode()  > flow = resnode + readoutnode  > flow.train(data)