In a feedforward neural network, am I able to put in a feature input of “don't care”?

Question

I've created a feedforward neural network using DL4J in Java.

Hypothetically and to keep things simple, assume this neural network is a binary classifier of squares and circles.

The input, a feature vector, would be composed of say... 5 different variables:

[number_of_corners,

number_of_edges,

area,

height,

width]

Now so far, my binary classifier can tell the two shapes apart quite well as I'm giving it a complete feature vector.

My question: is it possible to input only maybe 2 or 3 of these features? Or even 1? I understand results will be less accurate while doing so, I just need to be able to do so.

If it is possible, how?

How would I do it for a neural network with 213 different features in the input vector?

Answer 1

In this case, you could use a Deep Belief Network or some autoencoder to infer the values of the other features given a small number of them. For example, a DBN can "reconstruct" a noisy output (if you train it enough, of course); you could then try to give the reconstructed input vector to your feed-forward network.

You can learn more about ANN on Artificial Neural Network.