The Brain Is Not Probabilistic
Debunking a myth: there is no degree of certainty in the brain
The brain is not probabilistic. Either you see the cow or you don’t. You don’t see 1%, 50% or 90% cow. It’s either cow or no cow. Don’t worry, some people never see the cow. It is obvious that, unlike deep neural networks, the brain uses an all-or-nothing, winner-take-all mechanism for recognition. When asked “What was the greatest challenge you have encountered in your research?” during a 2012 Cambridge University Press interview, famed computer scientist Judea Pearl replied:
In retrospect, my greatest challenge was to break away from probabilistic thinking and accept, first, that people are not probability thinkers but cause-effect thinkers and, second, that causal thinking cannot be captured in the language of probability; it requires a formal language of its own.
This is a complete 180 coming from a man who built his entire career on the Bayesian brain hypothesis.
Now take a look at the hand drawn image above. Notice that, when looking at the bottom word, you can switch between seeing “wave” and “particle” but you cannot see both at the same time. A deep neural net trained on handwriting recognition would have serious trouble recognizing the word. It may not recognize it at all, or it may detect both “wave” and “particle” at the same time with two different levels of certainty.
This is all. I just thought I would write a short article to debunk a widespread myth in the mainstream artificial intelligence community.
