[Salgat]

The brain communicates with itself, so deep layers are equivalent to sections of the brain talking to each other. The only relevance white matter depth has is with regard to how it's trained, and since it doesn't use gradient descent, it's irrelevant to neural networks in that regard.

[blovescoffee]

Intercommunication does not equal layer depth.

[Salgat]

Why not? All a deep neural network is doing is progressive data transformations into something more abstract and meaningful to later layers.