11–20 of 155 posts
(Seriously, though, this was a lot of fun!)
A real-parameter (r(theta) = sum(r_k cos(k theta))) Fourier series can only draw a "wiggly circle" figure with one point on each radial ray from the origin.
A compex parameter (z(theta) = sum(e^(z_ theta))) can draw more squiggly figures (epicycles) -- the pen can backtrack as the drawing arm rotates, as each parameter can move a point somewhere on a small circle around the point computed from the previous parameter (and recursively).
Obligatory 3B1B https://m.youtube.com/watch?v=r6sGWTCMz2k
Since a complex parameter is 2 real parameters, we should compare the best 4-cosine curve to the best 2-complex-exponential curve.
I'm always making the joke (observation) that ML (AI) is just curve-fitting. Whether "just curve-fitting" is enough to produce something "intelligent" is, IMO, currently unanswered, largely due to differing viewpoints on the meaning of "intelligent".
In this case they're demonstrating some very clean, easy-to-understand curve-fitting, but it's really the same process -- come up with a target, optimize over a loss function, and hope that it generalizes, (this one, obviously, does not. But the elephant is cute.)
This raises the question Neumann was asking -- why have so many parameters? Ironically (or maybe just interestingly), we've done a lot with a ton of parameters recently, answering it with "well, with a lot of parameters you can do cool things".
Sadly, the constant term (the average r_0) is never specified in the paper (it seems to be something in the neighborhood of 180?): getting that right is necessary to produce the image, and I can't see any way not to consider it a fifth necessary parameter. So I don't think they've genuinely accomplished their goal. (Seriously, though, this was a lot of fun!)
This is humorous (and well-written), but I think its more than that. I'm always making the joke (observation) that ML (AI) is just curve-fitting. Whether "just curve-fitting" is enough to produce something "intelligent" is, IMO, currently unanswered, largely due to differing viewpoints on the meaning of "intelligent". In this case they're demonstrating some very clean, easy-to-understand curve-fitting, but it's reall…
Continual "curve fitting" to the real world can create intelligence. What is missing is not something inside the model. It's missing a mechanism to explore, search and expand its experience.
Our current crop of LLMs ride on human experience, they have not largely participated in creating their own experiences. That's why people call it imitation learning or parroting. But once models become more agentic they can start creating useful experiences on their own. AlphaZero did it.
This is humorous (and well-written), but I think its more than that. I'm always making the joke (observation) that ML (AI) is just curve-fitting. Whether "just curve-fitting" is enough to produce something "intelligent" is, IMO, currently unanswered, largely due to differing viewpoints on the meaning of "intelligent". In this case they're demonstrating some very clean, easy-to-understand curve-fitting, but it's reall…
This is humorous (and well-written), but I think its more than that. I'm always making the joke (observation) that ML (AI) is just curve-fitting. Whether "just curve-fitting" is enough to produce something "intelligent" is, IMO, currently unanswered, largely due to differing viewpoints on the meaning of "intelligent". In this case they're demonstrating some very clean, easy-to-understand curve-fitting, but it's reall…
> Whether "just curve fitting" is enough to produce something "intelligent" is, IMO, currently unanswered Continual "curve fitting" to the real world can create intelligence. What is missing is not something inside the model. It's missing a mechanism to explore, search and expand its experience. Our current crop of LLMs ride on human experience, they have not largely participated in creating their own experiences. Th…
This is humorous (and well-written), but I think its more than that. I'm always making the joke (observation) that ML (AI) is just curve-fitting. Whether "just curve-fitting" is enough to produce something "intelligent" is, IMO, currently unanswered, largely due to differing viewpoints on the meaning of "intelligent". In this case they're demonstrating some very clean, easy-to-understand curve-fitting, but it's reall…
I mean the devil is in the details. In Reinforcement Learning, the target moves! In deep learning, you often do things like early stopping to prevent too much optimization.
This is humorous (and well-written), but I think its more than that. I'm always making the joke (observation) that ML (AI) is just curve-fitting. Whether "just curve-fitting" is enough to produce something "intelligent" is, IMO, currently unanswered, largely due to differing viewpoints on the meaning of "intelligent". In this case they're demonstrating some very clean, easy-to-understand curve-fitting, but it's reall…