…for that matter. But we still can’t deny the progress deep learning has brought about in the field. There could be high chances that the brain does not do gradient descent and stuff but it’s unfair to undermine deep learning on the basis of that.
…. So rather than bake this in the inference mechanism, assume alternatively that it does not exits. That is rather than taking a pessimistic approach that assumes uncertainty is every where, take an optimistic approach but with one that is adaptive. Assume there is no uncertainty and then perform a compensation when an unexpected event occurs. That’s is simply how the brain works.