Neural networks with input gates

An architecture of multi layer neural networks is proposed. The networks are equipped with gates on their input channels to control flow of the input signals. A gate on an input channel opens and closes depending on the current values of the other input signals. The dependency is automatically determined based on training data so that the gate opens when the corresponding input is necessary and closed when not necessary. These gates give the networks a good generalization ability because they can eliminate harmful inputs. And they provides us with an insight into the input-output relationship since they can indicate which input is significant in what situation.