Good job Mark and Geektrader!
This would be separate from using neural networks to train strategies. This would only allow for better selection of what fresh blood gets added so that better strategies can be added straight out of the gate. Just a suggestion to improve this feature later down the line. A neural net for strategy selection and one for strategy training should really beef up the capability of the evolution process of any strategy.
My suggestion for anyone considering implementing this in the future is using a Convolutional Neural Network for the training (reduces time complexity and outperforms other models on time series data), and for strategy selection, a Feed Forward Neural Network (for simplicity/ speed) or a Kohonen Neural Network (for performance) would probably work best.