The inconvenient but amazing truth about deep learning is that, unlike neural networks, the brain does not learn complex patterns. It can see new complex patterns and objects instantly without learning them. Besides, there are not enough neurons in the brain to learn every pattern we encounter in life. Not even close.
The brain does not model the world. It learns to see it.
"It can see new complex patterns and objects instantly without learning them."
Except, it doesn't. It is clearly false. When animals grow up in an environment without certain patterns, they will be unable to see these patterns (or complex combinations of these) at a later stage. We see complex patterns as combinations of patterns we have seen before and semantically encode them as such. This is very similar to how neural networks work at the last fully connected layers.
"Besides, there are not enough neurons in the brain to learn every pattern we encounter in life."
There is a lot of self-similarity in our environment. Compression algorithms (and NN auto-encoders) are able to leverage this self-similarity to encode information in a very small number of data-points / neurons.
"The brain does not model the world. It learns to see it."
Except, it doesn't. Your brain continually makes abstractions of the world. When you 'see' the world you see a (lossy) compressed version of it, compressed towards utility. Similar to how MP3 compression works: the information gain of higher frequencies is low, so your brain can safely filter these out.
We learn to see patterns, but we see through physical and cultural action patterns that are simply present, not learned.
It’s like a river flowing... yes, the water molecules each “discover” the their path, but the path of the river is a property of the landscape. It is not learned.
we don’t even see the world, we see a hyperdimensional action space. Anything we can’t relate analogically back to some embodied action will literally be invisible to us.
The brain does not model the world. It learns to see it.