0 votes
1 view
in Data Science by (11.2k points)

I looked around online but couldn't find anything, but I may well have missed a piece of literature on this. I am running a basic neural net on a 289 component vector to produce a 285 component vector. In my input, the last 4 pieces of data are critical to change the rest of the input into the resultant 285 for the output. That is to say, the input is 285 + 4, such that the 4 morph the rest of the input into the output.

But when running a neural network on this, I am not sure how to reflect this. Would I need to use convolution on the rest of the input? I want my system to emphasize the 4 data points that critically affect the other 285. I am still new to all of this, so a few pointers would be great!

Again, if there is something already written on this, then that would be awesome too.

1 Answer

0 votes
by (16.1k points)

Basically, neural networks more or less tries to learn things by itself by newer approaches where there is little or no hand tuning.

So, in your case the will conclude that on its own by adjusting the weights for each input according to their importance of approach towards the desired output.

Now, what you can do is, have two networks, one is preliminary that is going to have 285 components as an input and other will have a four critical components and an output of the preliminary network as an input.

[285 compo.]---[neural network]---+---[neural network]---[output 285 compo]

                                  |

                       [4 compo.]-+

...