<whatToLearn>
	<summary>
		X audio samples of a few seconds each, and Y audio measures.
		X*Y total datasets.
		2 networks, 1 with X inputs and Y outputs, and the other with Y inputs and X outputs.
	</summary>
	<subgoalLearnThis>
		Learn which audio samples are similar, which are redundant,
			and which are probable when others are probable or improbable, etc.
	<subgoalLearnThis>
	</subgoalLearnThis>
		Learn which audio measures are similar, which are redundant,
			and which are probable when others are probable or improbable, etc.
	</subgoalLearnThis>
	<subgoalLearnThis>
		Keep samples and measures that are more unique and high-scoring.
	</subgoalLearnThis>
</whatToLearn>