I built a multi-layer perception model, from online tutorials. They are very good tutorials. However, when I come down to build my own model, with 32 variables(input layer), one output(regression problem). How many hidden layer should be a starting point? How many neurons in each hidden layer?
I am using the structure like,
32(input) - 64 - 128 - 64 - 16 - 1,
because the results look like it worked. But I would very like to hear some advice and start over again.
