I’m trying to make a Liquid State Machine in python and I already read many articles about it, but still there are many points I don’t understand.

The readout function is a Feed-forward Neural Network, but how is it taught to read out the states? In the echo state network I had a train period when I feed a train signal through backward weights and by saving each step’s state, the output weights were calculated.

Is it the same way in the Liquid State Machine, or is its “inner weight matrix” trained instead (the connections between the inner nodes / neurons)? Or does it have an entirely different method?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.