Clarification on the rules

Two Birds, One Neural Network
1

Hi,

thank you very much for organizing this challenge !
I have a few questions that I hope you can help me with, to avoid infringing any rules:

  1. would it be possible to have a reference equation for calculating the diversity metrics ?
  2. would it be okay to have a model generate 100/200 samples and select in a ‘post-processing’ stage the 30 that would maximize the diversity metrics ?
  3. would it be possible to encode, inside the NN, the information on the properties that x0/x1 must have (for example by fitting the network to just predict slopes and biases and using a final, non-trainable layer, to transform those 4 coefficients into 2 straight lines of 50 samples) ?

Thank you in advance !

2

Dear @discourse-admin
would it be possible to have a clarification on these aspects of the authorized modelling strategies ? It would be of great help.

I actually have 2 further questions:

  1. Can we build an algorithm based on more than 1 NN or other ML strategies (also in recursive ways), or should we stick to only a final NN that takes some input ?
  2. Can we generate additional samples ?

Thank you.
Best,
Leonardo

3

Hello @Andrea_P

  1. Can we build an algorithm based on more than 1 NN or other ML strategies (also in recursive ways), or should we stick to only a final NN that takes some input?
    You are certainly encouraged to employ an ensemble of techniques.
  2. Can we generate additional samples?
    You could generate additional samples for gaining insights. However, for the final evaluation, you should provide a reproducible solution that is based on the provided datasets.

Best regards,
Onward Team