I have to create a Neural Network for regression purpose. Basically, I created a Model which predict next 5 values when we give past 6 values. enter image description here I want to make a change in this neural network. For example,

when giving 6 past values I have to predict the next 10 values.

Here, is there any issue of selecting the number of output dimension greater than the input dimension. Which type of parameters arrangement makes the Neural Network achieve good accuracy? do I have to decide the number of input parameters always greater than output parameters?

Thanks in Advance!


1 Answer 1


This should be possible given the fact that ANNs have the ability to do the feature engineering and feature selection tasks by themselves.

This means that given a lesser number of input parameters, the model will be able to generate and select additional features by itself. You will obviously not be able to understand or model these features manually.

The only thing to keep in mind is that you will need a large dataset and a number of iterations before you are able to achieve a decent accuracy.

For example, there are networks that can generate image from classes. Give this a read and here is an example where the output layer is larger than the input layer.


You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .