Sunday, August 26, 2012

The Myth of the Bayesian Brain, Part I

Part I, II, III

Abstract

Previously, I wrote that, by embracing Bayesian statistics, the artificial intelligence community has embarked on yet another great red herring chase. I claimed that Bayesian statistics will prove to be just as wasteful of time, brain and money as the symbolic AI craze of the last century. In this article, I explain why the Bayesian mindset is injurious to progress in our understanding of intelligence. I do not argue that the Bayesian approach is bad in and of itself but that, when it comes to explaining the brain’s ability to handle uncertainty, there is a competing model that is orders of magnitude better.

The Last Great Barrier to Fully Understanding Intelligence

Scientists are a conservative and taciturn lot. They will live with a myth or obvious falsehood for decades and even centuries because the humiliation and other hardships that come from rejecting the lie are too painful for them to bear. The Bayesian brain is just such a myth. The problem is that it is now so firmly entrenched in the AI community that accommodating a different perspective would be suicidal to many careers. I will argue that the Bayesian mindset is the last great barrier to progress in AI because it cripples our understanding of the most important aspect of intelligence: perception. I believe that having a correct understanding of perception will unleash a flood of insights that will quickly lead to a full understanding of intelligence, artificial or otherwise.

Two Competing Models of Perception

Below is the essence of the two competing models of perception.
  • The Bayesian model assumes that events in the world are inherently uncertain and that the job of an intelligent system is to discover the probabilities.
  • The Rebel Science model, by contrast, assumes that events in the world are perfectly consistent and that the job of an intelligent system is to discover this perfection.
As you can see, the two models are polar opposites of each other in their assumptions. The two views have drastically different consequences in the way we design our perceptual systems. In my next post in this series, I will explain why the Rebel Science model is far superior to the Bayesian model. Hang in there.

See Also:

The Second Great AI Red Herring Chase

4 comments:

dashxdr said...

Is the AI community still in love with Bayesian claptrap?

I remember a painful phone conversation with the highly overrated Eliezar Yudkowsky, and he was all over the Bayesian bandwagon. This was in 2006. It was obvious then it was a complete dead end. EY's infatuation with the concept was what indicated to me his utter incompetence and just how worthless his is as a banner carrier of machine intelligence.

Mainstream AI will never figure anything out. And when someone does figure it out, they'll be the first to claim credit for it, saying, "Of course, that was obvious from the start, you just didn't understand what we were saying..."

Louis Savain said...

Is the AI community still in love with Bayesian claptrap?

They can't seem to get enough of it. They've convinced Silicon Valley investors that the Bayesian brain is the future of AI. What a waste.

I remember a painful phone conversation with the highly overrated Eliezar Yudkowsky, and he was all over the Bayesian bandwagon. This was in 2006. It was obvious then it was a complete dead end. EY's infatuation with the concept was what indicated to me his utter incompetence and just how worthless his is as a banner carrier of machine intelligence.

Eliezar is an elitist and so is that entire Singularity movement that he belongs to. It's really a religion if you ask me. They are essentially a bunch of nerds who think of themselves as being the smartest and most rational people on earth and who are disdainful of the rest of humanity. It would be scary if they weren't so wrong about almost everything.

Mainstream AI will never figure anything out. And when someone does figure it out, they'll be the first to claim credit for it, saying, "Of course, that was obvious from the start, you just didn't understand what we were saying..."

Yeah. Elitists, in general, rarely admit that they are wrong about anything. Now that you mention it, I'm beginning to think that I might be giving away too much already.

JosephHyde said...

Along with the 'Singularity 'Movement'' I think that you can also through in 'The Edge' but I have enjoyed some of their 'presenters' as on TED as well. It reminds me that they all took a Big Bite or Gulp of the Kool Aid that was hanging off The Tree of Knowledge.

Technology evil in it's own right? Don't know if I'm ready to go that far, just because I have not read enough of that thinking yet.

Be Well Louise and Wife. Tks.

Jeerouss R said...

Such angriness against facts....
I thought your faith was all about love but I only see angriness and unrespectful comments here.i totally agree with you about the space time and stuff...but it is sad but we need to understand that there is no such god. Maybe there is one that started it all but if there is, I still cant conceive that he was always there. And countless proofs against every religion makes me believe we're all wrong. And the worst part is we will probably never know the truth if dualism is not real which really seems to be (Not our reality).