I have a neural network that is already trained to predict two continuous outputs from a set of 7 continuous features.
Is there any way to apply the network to predict one of the input features, given other 6 features and the two outputs?
Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.Sign up to join this community
From your question, it appears that you would like to use other features in your data to predict one of the features. I am not sure I understood your question clearly, but anyways, either, you would be using the feature you want to predict as the output of the network.
Also, if you want to use the output of the network and other features to predict the new output, I think possibly you are trying to use a Recurrent Neural Network based approach, in which the past output is taken into account for future predictions. My personal experience with RNN's is that they are really good at learning such dependencies, as the RNN cells consider the present input, as well as the past output in modelling such tasks. If your problem is a sequence to sequence prediction task, I would definitely suggest trying RNN's (especially LSTMs, ideal for learning long term temporal dependencies) but ultimately, there is No Free Lunch. So try different approaches and see which one works for you best. Good Luck!