Friday, February 2, 2018

People Ask Me, What Do You Have Against Deep Learning?

Yes, I Cannot Stand Deep Learning

I got a closetful of criticisms against deep learning. I have written about them in the past. I will not list them here because what would be the point? I am not really against the technology of deep learning per se. It is useful for what it does. I am just against the idea advanced by mainstream AI that deep learning is a step toward artificial general intelligence (AGI) or human-like intelligence. In this context, let me just say that, if you are researching AGI, deep learning must be thrown away like yesterday's garbage for this one specific reason if for no other: A deep neural net learns complex patterns but the brain does not. The brain can instantly see a new complex pattern without learning it. Let me say this again for emphasis because it is crucial to my position:
A deep neural net learns complex patterns but the brain does not. The brain can instantly see a new complex pattern without learning it.
Huh? That's right. In fact, almost everything the brain sees is new, that is, seen from different angles or under different lighting conditions. There aren't enough neurons and synapses in the brain to store all the possible patterns that it would need to learn in order to interact with the world. We can instantly see complex objects or patterns that we have never seen before. A deep learning system would be blind to them. We only remember high level bits and pieces of the patterns that we see. Most of the low level details are either forgotten or are written over by new experiences.

As the late philosopher and AI critic, Hubert Dreyfus, was fond of saying, the brain does not model the world. The world is its own model. The brain simply learns how to see it. There is huge difference between the two, one that I hope will, one day, be common knowledge in the scientific community. Dreyfus was saying this decades ago. He was at least a hundred years ahead of mainstream AI.

See Also:

The World Is its Own Model or Why Hubert Dreyfus Is Still Right About AI


Rick Deckard said...

According to Aristotle earth is comprised of 4 elements: water, fire, earth and air. While at the same time theory of the atoms came into light which Aristotle successfully destroyed by making his famous.

We can all thank the smartest man for impeding our progress and innovation.

Rick Deckard said...

I gave this some thought

"The brain can instantly see a new complex pattern without learning it"

You are right on point. Also, the blind spot in our eye is proof that the brain can take any complicated pattern and instantly replicate it.

It makes complicated patterns simple, instantaneous, while deep learning does the opposite. It takes simple and makes it complicated.

Louis Savain said...

Rick, these are things that are completely mysterious to mainstream AI. They don't even talk about it. They are amazed when I mention it and some refuse to even believe it. True AI will never come from the mainstream. They are clueless.

Michael Xu said...

Hey Louis, I hold extremely similar thoughts as you do. The biggest difference is that I classify your mainstream AI group as journalism, popular media, business etc. I don't think real AI researchers proclaim AGI is the goals of neural nets (or I may just be naive), but that neural nets is a very useful tool that is a byproduct of AGI research. That said the tool is now mainstream enough that it is easily utilized by non researchers and obfuscated with intelligence.