I have a question about the architecture of the Keras layers. About kind of unfolding the architecture of the layer. For example, I would like to see the main equation used for the Dense layer in Keras, how the n. of neurons, activation function, and bias are tied to each other. This seems pretty simple in logical understating for the Dense layer. However, finding out the tfa.ESN layer multiplication inside the corresponding layer, for instance, would be very helpful for me.
Thanks to everyone, J