I wonder if there is some framework or method to help visualising inner workings of a feedforward deep neural network?

What I mean by this is something similar to what is being done with CNNs where we can show what geometrical shape some neuron is responsible for finding in the picture, but for numerical tabular data. For example method that would show that for example given neuron is activated when three input features have certain values.


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.