<To Do>
- Implement ways for Curve fitting using output as slopes
- Update Hidden Function stuff (activation stuff)
	- Add more functions ([true] RELU, sigmoid, etc.
	- Add property of AdvNet to save a default hidden function (activation)
- Add a 'draw net' feature that plots a diagram of the net in pyplot
	- Normal diagram and also heatmap visual option
- (Maybe not worth) Extend net feature
	- Adds height to hidden layers
	- Starts with all of the new weights at 0
	- Randomly tweak those new values until the weight medians are back to what they were in the original new

V0.1.5.3
<New>
- Changed validationVals to account for 1D vectors (LN588)
- Changed 'default' selection in TweakWeight to 'all'
- Corrected RELU and ELU names (to ELU and ATAN)

V0.1.5
<New>
- For nets with inSize = 1, a simple number can be given (no longer required to be that stupid 1x1 numpy array thing).
- Reduced maxCycles default value to 5 for the cycle training

V0.1.4
<New>
- Operational as package
- Printing an AdvNet now also prints the # of parameters it has