What learning algorithms can predict that our physics theories might not • Hacker News Board

Re: What learning algorithms can predict that our physics theories might not

#31

Post by mannykannot » Tue, Jul 12, 2016, 3:51 AM UTC

ad510 wrote: post #16

Well, I must say that I'm pleasantly surprised with the comments so far. I was actually expecting that this would be quickly shot down as either unoriginal or fundamentally flawed. But instead it seems no one has caught on to what this post is actually claiming, so I suppose I should now be very blunt about it. At the beginning of the blog post, it claims that it explains 2 things: 1. where exactly might you be able…

"So if we hooked up two people’s brains together in year 2050, would they feel like a single person?...We won’t know until we actually try it. If the answer is no then the rest of this blog post is completely irrelevant..." My guess is that if this were done to people who, up to that point, had lived independent lives (i.e. not born conjoined at the brain), they would each feel like individuals who had suffered some sort of major stroke, rather than that they had become a single person.

With regard to the cloning phase of your argument, is this not effectively the same as what the many worlds interpretation of quantum mechanics says happens all the time? FWIW, while I don't feel as if those other versions of me are me (assuming many-worlds is true), I realize that I am in no position to assert that I am the 'real' me, and in fact that it is beside the point to ask which one is.

Re: What learning algorithms can predict that our physics theories might not

#32

Post by goldenkey » Tue, Jul 12, 2016, 12:33 PM UTC

Strilanc wrote: post #28

goldenkey wrote: post #9

Earlier quoted context omitted.

The output of a program could be infinite and thus it never halts. Without Chatlin's constant or the Busy Beaver values, brute forcing is not feasible in a countably computable universe. It is still interesting to talk about Oracles, ie. Somehow getting hold of Chatlin's constant and thereby easily solving the halting problem and being able to use the induction.

These are easily fixed by dove tailing through the programs and using an increasing-over-time cutoff. Not fixed in the "made practical" sense, but in the "made non-contradictory" sense.

You can't use cutoffs. Timeouts deliver no guarantees within the universe of complexity.

Re: What learning algorithms can predict that our physics theories might not

#33

Post by eutectic » Wed, Jul 13, 2016, 9:11 AM UTC

hacker42 wrote: post #30

eutectic wrote: post #23

Earlier quoted context omitted.

More specifically, every incorrect expert is removed at each step, and the remaining experts have their probabilities uniformly rescaled to sum to 1.

That relies on noiseless, unbiased data, right? What if an expert gets ruled out by accident?

Being able to average over every possible computer program is so powerful that it doesn't really matter.

Re: What learning algorithms can predict that our physics theories might not

#34

Post by kordless » Wed, Jul 13, 2016, 4:02 PM UTC

jerf wrote: post #29

kordless wrote: post #25

Earlier quoted context omitted.

I would note that "computation" is work done over time. Causality. There may exist an alternate form of causality that isn't time bound, which may be exposed here over short periods of time. I would hesitate to judge it "computationally infeasible" until we know more. :)

I think it's important to distinguish arguments that hypothesize that our understanding of physics is fundamentally, deeply flawed, from arguments that are based on our current understanding of physics. I can't prove that our understanding of physics isn't deeply flawed and there isn't some source of infinite computation somehow available to us; for instance, one proposed explanation of the Fermi Paradox is that all…

Well, there are things we know and things we will know. If we take the hypothetical "all knowing I", we assume it has zero security and all knowledge (wisdom). With individuals, we have high security (you can't know what I'm thinking) and low wisdom. So, knowledge plays a part in all this, as is evident of the result of causality. There's a sutra that deals with this concept as well.

I have a hypothesis that reality is backed by a blockchain data structure, which is why it's robust and fairly immutable. One might create a simple reality based on a blockchain data structure and then attempt to model causality/matrix rotations with that structure in such a way that the behavior of "gravity" noted in a gyroscope can be observed to not occur, given the nature of the scientific method. i.e. model rotations in a blockchain without generating gravity/precision and you've disproved my hypothesis.

The correlation with this test and reality would be allowing brief access to a "search" across all knowledge (which could be optimized behind the scenes) and then allow that knowledge to exist until the block is closed, at which point you are left with whatever gets closed in the block and the resulting forces that have to occur to rationalize the rotation. Rinse and repeat.

Probably doing a horrible job of explaining it. First time I've really written it down.

Re: What learning algorithms can predict that our physics theories might not

#35

Post by Strilanc » Thu, Jul 21, 2016, 4:48 AM UTC

eli_gottlieb wrote: post #15

goldenkey wrote: post #9

Earlier quoted context omitted.

The output of a program could be infinite and thus it never halts. Without Chatlin's constant or the Busy Beaver values, brute forcing is not feasible in a countably computable universe. It is still interesting to talk about Oracles, ie. Somehow getting hold of Chatlin's constant and thereby easily solving the halting problem and being able to use the induction.

Solomonoff Induction starts by using Kolmogorov complexity to calculate its prior distribution, which already requires Chaitin's constant to be known. So yeah.

Solomonoff induction goes from program to output to prediction weighted by program's length. It never goes from type of prediction to shortest equivalent program. It doesn't need to compute Kolmogorov complexities.

(Well, more specifically, approximations to it with time cutoffs don't have to compute Kolmogorov complexities. Raw Solomonoff induction already trivially runs into the halting problem.)