Ideal Neat API

[luiscarbonell]

I was going to write this in another issue, but since you asked for feedback here...

I have found the Neat class is much more complicated than it needs to be.

My ideal api would be:

• You extend network.evolve.
• You pass it a score that for the network to hit to finish.
• You pass in the scoring function.
• Select the population class. So you can extend and store data if needed.
• The population has ids.
• Multi-threading support.
• Able to give it your data and select what percentage is the training, validation and testing data.
• A setting that auto adjusts the mutation rate based on the validation results.
• Regularization support.

Originally posted by @dan-ryan in #25 (comment)

[dan-ryan]

Shuffle support is another one.

Having those suggestions would no longer have questions like this:
wagenaartje/neataptic#131
I did get it all working in the end, it was a very complex solution and still not perfect.