Hidden layers in Flux

Specific Domains Machine Learning
1

I’m starting to work with Flux and I want to build a neural network with 5 entries and 6 exits. I have already built a network with no hidden layers, but now I want to add hidden layers. How should I do that? I believe I need to use the Dense function, but I’m not sure how to do that.

2

An example:

model = Chain(Dense(5, n), Dense(n, 6))

where n is the number of neurons in the hidden layer.
You can see the Documentation of Flux, it is improving a lot lately.

3

Thank you for your answer!! But what about the number of hidden layers? How do I define that in the Dense function?

4

You just add an other (e.g. Dense) layer to the Chain function.

5

Thank you!! So, for example, if I want to create a network with 1 hidden layer with 7 neurons, I’d have:
model = Chain(Dense(5,7), Dense(7,6), Dense(6,6))?

6

Have you tried it?