81–90 of 103 posts
better remove all the Disney-based Alice in Wonderland character intellectual property from the book.
I was just thinking that's "cease and desist" bait right there.
Earlier quoted context omitted.
Before the recent AI boom, I was mystified by the possibility of AI and emulating humans (in no small part thanks to works of fiction showing AI powered androids). Then I created and trained some neural networks. Smaller ones, doing much of nothing special. That was enough to break the mysticism. To realize it was just multiplying matrices. Training them was a bit more advanced, but still applied mathematics. Only re…
Exactly, the people who are derisive of those who consider ML models to exhibit glimmers of true intelligence because it's only matrix multiplications always amuse me. It's like they don't even realize the contradiction in holding the position that seemingly complex and intelligent outward behaviour should not be used as an indication of actual complexity and intelligence.
My conclusion is we tend to overestimate our understanding and the power of our inventions.
> Stripped of anything else, neural networks are compositions of differentiable primitives I’m a sucker for statements like this. It almost feels philosophical, and makes the whole subject so much more comprehensible in only a single sentence. I think François Chollet says something similar in his book on deep learning: one shouldn’t fall into the trap of anthropomorphising and mysticising models based on the ‘neural…
> one shouldn’t fall into the trap of anthropomorphising and mysticising models based on the ‘neural’ name One also shouldn't fall into the dual trap of assuming that just because one understands how a model works, it cannot have any bearing on the ever-mysterious operation of the brain.
> Stripped of anything else, neural networks are compositions of differentiable primitives I’m a sucker for statements like this. It almost feels philosophical, and makes the whole subject so much more comprehensible in only a single sentence. I think François Chollet says something similar in his book on deep learning: one shouldn’t fall into the trap of anthropomorphising and mysticising models based on the ‘neural…
I feel like this statement is both obvious after spending a few minutes working with neural networks and completely useless in helping you build better neural networks. It's kind of like saying, "Stripped of anything else, works of literature are compositions of words"
Earlier quoted context omitted.
Exactly, the people who are derisive of those who consider ML models to exhibit glimmers of true intelligence because it's only matrix multiplications always amuse me. It's like they don't even realize the contradiction in holding the position that seemingly complex and intelligent outward behaviour should not be used as an indication of actual complexity and intelligence.
If you study this historically you will see that every generation thinks they have the mechanism to explain brains (gear systems, analog control/cybernetics, perceptrons). My conclusion is we tend to overestimate our understanding and the power of our inventions.
> Stripped of anything else, neural networks are compositions of differentiable primitives I’m a sucker for statements like this. It almost feels philosophical, and makes the whole subject so much more comprehensible in only a single sentence. I think François Chollet says something similar in his book on deep learning: one shouldn’t fall into the trap of anthropomorphising and mysticising models based on the ‘neural…
Ya so far this is the best introduction to neural networks from first principles that I've seen. Quickly skimming the draft pdf at https://arxiv.org/pdf/2404.17625 I can grok it instantly, because it's written in familiar academic language instead of gobbledygook. Anyone with an undergrad math education in engineering, computer science, etc or a self-taught equivalent understanding of differential equations should be…
I started self-studying programming some time ago, then pivoted to AI/ML and (understandably) ended up mostly studying math, these resources are a boon to my folk.
Earlier quoted context omitted.
If you study this historically you will see that every generation thinks they have the mechanism to explain brains (gear systems, analog control/cybernetics, perceptrons). My conclusion is we tend to overestimate our understanding and the power of our inventions.
The difference is that we now actually have a proof of computational power and computational universality.
Earlier quoted context omitted.
I was just thinking that's "cease and desist" bait right there.
Alice in Wonderland (the book) is in the public domain. The old Disney movie is still in copyright, and the cover image does look very much like it's from the movie, but that character design is from John Tenniel's illustrations which are also in the public domain.
His version, for example, does not have the distinctive bow. The art style is also completely different.
Earlier quoted context omitted.
The difference is that we now actually have a proof of computational power and computational universality.
Analog circuits have the same computational power. Piecewise linear functions have the same computational universality.