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. 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!