Hello, I'm working with artificial neural network.

Hello, I want to work on artificial neural network but I think I have something I don't understand.

First, this is how I understand ANN work. You have input layer where the input neurons are. Then you have hidden layer where you set the "random" values for hidden neurons (with random weights). Lastly, you have the output layer where the output neuron is the variable you want to predict. On your first run, you're expected to get a very large error but as you train the system, the hidden neurons and weights will adjust its values until you reach the target error you set.

My question is, does this mean you could practically use any input neuron? Random input neuron since the network will adjust anyway?

Is there any qualifications for the input neurons?

Sorry I'm really new to this.

Answer 1

[Greg Heath]

Three layers are sufficient: input/hidden/output

The input layer is NOT a neuron layer. The number of input nodes is the dimensionality of the input data.

The output layer IS a neuron layer. The number of nodes is the dimension of the target and output data.

This is sufficient for trivial transformations.

In general, a hidden layer with nonlinear neurons is required. Typically, the more complicated the I/O transformation,

the more hidden neurons are required.

Sometimes it is better to use two or more hidden layers instead of having a single hidden layer with a huge number of neurons.

I find the best approach is to minimize the number of trained weights subject to a limit on the output error.

The limit I typically choose is that the output error is at least 100 times smaller than the average variance of the target.

The latter is the minimum error that results if you guess that the output is just the target mean.

I have posted jillions of examples and tutorials in both the NEWSGROUP and ANSWERS.

Hope this helps.

THANK YOU FOR FORMALLY ACCEPTING MY ANSWER

Greg