Will_Pearson

Karma: 196

Will_Pearson 20 Feb 2008 23:55 UTC
1 point
on: Taboo Your Words
I’d really like to taboo, “probability,” and, “event,” when discussing intelligence.

Will_Pearson 23 Feb 2008 14:54 UTC
4 points
on: Entropy, and Short Codes
There is different-base-concepts-alien who views the world with radar, x rays and sonar

Dbc-alien says “I don’t understand half of your coding (colour, translucency, glowingness) and the other things are high level concepts I don’t tend to bother with. It is like trying to ask me to identify a cat by density, I can always tell between what has vanadium and palladium via the way they refract x rays”.

There is also not-important-for-me ant who gives not a fig whether something is a blegg or a rube.

Nifm ant goes to eats remnants of the pizza and beer given to ihapshbic and us, and out can survive because it hasn’t even bothered to try and build a big brain to remember anything.

Will_Pearson 23 Feb 2008 17:12 UTC
1 point
on: Entropy, and Short Codes
“This wrong assumption is done becouse people think that every object , every binary string can happen . This is wrong , only few bit string with lenght 1000000 can happen becouse a system that produce 2^1000000 object , string can not exist.”

So these people are frauds?

Will_Pearson 24 Feb 2008 11:49 UTC
2 points
on: Mutual Information, and Density in Thingspace
Since we are resting all our language construction and reasoning on thingspace there are a few things that need to be defined.

What is the distance metric for thingspace? How is thingspace extended?

Will_Pearson 25 Feb 2008 1:44 UTC
1 point
on: Superexponential Conceptspace, and Simple Words
I’ll second the recommendation for Tom Mitchell’s book (although it has been a long time since I have read it and I have moved away from the machine learning philosophy since).

Are you going to go on to mention that the search in a finite concept space can be seen as a search the space of regular languages and therefore a search in the space of FSM? And then move onto Turing Machines and the different concepts they can represent e.g. the set of strings that have exactly the same number of 0s and 1s in.

Hmm, lets fast forward to where I think the disagreement might lie in our philosophies.

Let us say I have painstakingly come up with a Turing machine that represents a concept, e.g. the even 0s and 1s I mentioned above. We shall call this the evenstring concept, I want to give this concept to a machine as it I have found it useful for something.

Now I could try and teach this to a machine by giving it a series of of positive and negative examples

0011 +, 0101 +, 000000111111 +, 1 -, 0001 - etc...

It would take infinite bits to fully determine this concept, agreed? You might get there early if you have a nice short way of describing evenstring in the AIs space of TM.

Instead if we had an agreed ordering of Turing machines I could communicate the bits of the Turing machine corresponding to evenstring first and ignore the evidence about evenstring entirely, instead we are looking at evidence for what is the TM of! That is I am no longer doing traditional induction. It would only take n bits of evidence to nail down the Turing Machine, where n is the length of the turing machine I am trying to communicate to the AI. I could communicate partial bits and it could try and figure out the rest, if I specified the length or a bound on it.

If you want to add evidence back into the picture, I could communicate the evenstring concept initially to the AI and make it increase the prior of the evenstring concept in some fashion. Then it collect evidence in the normal way, in case we were wrong when we communicated evenstring in some fashion, or it had a different coding for TMs.

However this is still not enough for me. The concepts that this could deal with would only be to do with the outside world, that is the communicated TM would be a mapping from external senses to thing space. I’m interested in concepts that map the space of turing machines to another space of turing machines (“‘et’ is the french word for ‘and’”), and other weird and wonderful concepts.

I’ll leave it at that for now.

Actually I’ll skip to the end. In order to be able to represent all the possible concepts (e.g. concepts about concept formation, concepts about languages) I would like to be able to represent I need a general purpose, stored program computer. A lot like a PC, but slightly different.

Will_Pearson 25 Feb 2008 11:32 UTC
0 points
on: Mutual Information, and Density in Thingspace
While it is true that you don’t need a metric to draw a boundary, I personally need a metric to be able to envision high concentrations of probability density.

A concentration implies a region, which implies a metric space. While your sphering of the space normalises it somewhat and deals with part of the trouble, it still skips over the question of metric space. For example is 2, 2, 2 closer to 1, 1, 1 than 4, 1, 1? If that was a co-ordinate of a position in three dimensional space you would want to use the euclidean metric i.e. d = ((x2 - x1)^2 + (y2 - y1)^2+ (z2 - z1)^2)^1/2 or you that might not be appropriate and you would have to use city block distances and put them equally far away (if they were average energy usage, weight and how many copies of the gene for green eyes it had).

See this page for more possible metrics http://www.cut-the-knot.org/do_you_know/far_near.shtml.

Will_Pearson 26 Feb 2008 14:47 UTC
6 points
on: Leave a Line of Retreat
There hasn’t been much evidence of atheists forming groups that have the positive aspects that a church/synagogue/mosque holds in the social life of some humans. So you might forgive a theist pretending to be a rationalist, for not holding the probability of this happening very high, and that the world would lack said institutions and would be a worse place.

If rationalists truly wants to get rid of religions, without getting rid of humans, we would have to ask ourselves, “What do humans get out of being part of a religion?” And then provide that through organisations.

And please no strawmen of the comfort of ignorance, I am talking about reassurance of being with people who are trying to hold the same goal system.

Will_Pearson 27 Feb 2008 12:53 UTC
−1 points
on: The Second Law of Thermodynamics, and Engines of Cognition
“But suppose you already knew where all the gas molecules were?”

I assume by this you mean I have an exact knowledge of position and momentum. Why should I suppose a scenario that is contrary to what I know of the uncertainty principle? Can’t I reject it for the same reasons you reject the possibility of waking up with a purple tentacle.

Will_Pearson 27 Feb 2008 20:49 UTC
0 points
on: The Second Law of Thermodynamics, and Engines of Cognition
I don’t mind people ignoring elements of science when they are not important. e.g. ignoring general relativity when calculating ball trajectories.

But molecules and atoms are very much in the quantum realm. So it seemed to me to be like saying, ignoring special relativity, when things are travelling faster than the speed of light then this analogy holds, from this we can conclude blah. To me it seems unlikely to hold any insights.

I don’t see why I should accept any conclusion drawn from the premises if I do not hold with the premises. But this brings up an interesting point, when is it valid to ignore data? Is it ever?

To me your first point seems elementary as I don’t have good evidence for pyschic powers, and can be derived from the uncertainty principle or probably preferably from the no cloning theorem. Your second would be better derived from quantum physics as well by showing a minimum energy required for a bit flip, if it can.

Will_Pearson 29 Feb 2008 1:49 UTC
−1 points
on: Searching for Bayes-Structure
Bayesian health warning, above argument does not take all the evidence into account.

Remember all of the above is ignoring quantum physics, including such things as the no cloning theorem. Which, I think, has significant things to say about getting into the state of mutual information with the environment.

Will_Pearson 29 Feb 2008 12:09 UTC
6 points
on: Searching for Bayes-Structure
“You cannot write a Bayes program that inputs all the right data and generates garbage.”

That sounds like a challenge. Care to formalise things so this theory can be tested?

Will_Pearson 1 Mar 2008 11:09 UTC
1 point
on: Searching for Bayes-Structure
“So much for begging the question. Please do a calculation, using the theorems of Bayes (or theorems derived from Bayesian theorems), which gives an incorrect number given correct numbers as input.”

Couldn’t we say the same thing for Turing machines? “Please do a computation, using a Universal Turing Machine (or equivalent), which gives an incorrect number, given correct numbers as input.”

Remember that a Universal Turing Machine takes a Turing machine as an input, so you can’t muck around with the algorithm it runs, without making the input “incorrect”.

I thought the whole point of probabilistic methods is that it doesn’t matter too much what the prior is, it will always eventually converge on the right answer...

Well apart from in some cases. The following is a situation where, unless you give the system exactly the right prior it will never come to the right answer. Not quite what you were after but shows a hole in bayes to my mind.

Environmental output is the entire affect that a computation has on the environment (e.g. heat, radiation, reduction in the energy of the power source).

In the Sensitive Urn the colours of the balls are dependent upon the average environmental output from the processing done in the area since the last sample. That is they are a function of the processing done. We could represent knowledge about the probability function in the following way with the standard notation

P (r|Φ(μ, ts − 100, ts ) > 10) Being the probability that a ball is red with having there been at least 10 environmental output per millisecond in the 100 milliseconds before the time of the current sample ts . We shall say that the probabilistic reasoner outputs 20 outputs per millisecond and so fulfils this property. This value is therefore found during its normal operation and sampling. However

P (r| ∼ Φ(μ, ts−1 ts ) > 10) , the probability that the ball will be red if there is no such processing in the area is harder to find. For the sake of argument say that this is the most efficient bayesian reasoner that we could build. In order to find this value would require that the sampler no longer process to the same extent and because processing is required to update probabilities it can no longer update probabilities. It is in effect a blind spot, a place that the sampler cannot go with out changing itself and stopping being a Bayesian sampler.

Will_Pearson 1 Mar 2008 23:56 UTC
1 point
on: The Second Law of Thermodynamics, and Engines of Cognition
If you have the time I would be interested in seeing a mathematical description of a system that increases its mutual information with the environment, with the total entropy of the system+environment increasing.

Will_Pearson 3 Mar 2008 21:25 UTC
3 points
on: The Second Law of Thermodynamics, and Engines of Cognition
Douglas Knight: “In particular, when you say that knowledge of particles makes something colder, makes it possible to extract work, you’ve gone back to the ideal observer.”

Eliezer: “I think emphatically not! To extract work, you’ve got to be inside the system, extracting it.”

I think what Douglas may be implying is that unless you are perfectly insulated from what you are getting knowledge of (e.g. and ideal observer), the act of getting knowledge of something will heat it up. As you are doing work and increasing the entropy in the surroundings.

It raises some interesting and quirky ideas in me. I’m picturing future the future where an intelligence explosion or at least expansion where a statistical machine is the dominant producer of entropy on the planet and it deciding to not go perform too much statistics so it doesn’t go over the hypsithermal limit of its environment and make its environment less rather than more predictable.

Will_Pearson 7 Mar 2008 16:40 UTC
0 points
on: Gary Gygax Annihilated at 69
Why not take this time to deal with some irrationalities surrounding death and the identity?

Please tell me what happens in physical terms when someone dies? It is obviously not as simple as a stopped heart/brain activity if you take the transhumanist view of things.

How many potential different human beings are there? Are they all different in important ways (e.g. how many apples they remember having eaten). Should we mourn when one human being eats an apple and thus changes his memories and therefore the potential human that he is.

If not how many potential importantly different humans are there?

Identity (and the destruction of the same) is one of the things that people have a lot of trouble being rational about.

Will_Pearson 9 Mar 2008 15:10 UTC
3 points
on: Righting a Wrong Question
I’m sure the meta-physicists will suggest something like the following. How do you know the causal chain you trace is meaningful? That is you are resting our ability to see thing on physics, and our ability to have a valid physics on being able to see things in the world. It is self-reinforcing but requires axioms taken on faith or blind chance to start things off. So is not really the same thing as meta-physics.

My reply would be to say, “Well, it works so far.” And then get on with my life, and not worry about it.

Will_Pearson 12 Mar 2008 18:55 UTC
0 points
on: Probability is in the Mind
If you honestly subscribe to this view of probability, please never give the odds for winning the lottery again. Or any odds for anything else.

What does telling me your probability that you assign something actually tell me about the world? If I don’t know the information you are basing it on, very little.

I’m also curious about a formulation of probability theory that completely ignores random numbers and other theories that are based upon them (e.g. The law of large numbers, Central limit theorem).

Heck a re-write of http://en.wikipedia.org/wiki/Probability_theory with all mention of probabilities in the external world removed might be useful.

Will_Pearson 12 Mar 2008 20:35 UTC
0 points
on: Probability is in the Mind
Cyan, sorry. My comment was to Eliezer and statements such as

“that probabilities express ignorance, states of partial information; and if I am ignorant of a phenomenon, that is a fact about my state of mind, not a fact about the phenomenon.”

Will_Pearson 13 Mar 2008 13:04 UTC
0 points
on: Probability is in the Mind
Rolf Nelson: “Follow-up question: If Bob believes he has a >50% chance of winning the lottery tomorrow, is his belief objectively wrong? I would tentatively propose that his belief is unfounded, “unattached to reality”, unwise, and unreasonable, but that it’s not useful to consider his belief “objectively wrong”.”

It all depends on what information Bob has. He might have carefully doctored the machines and general setup of the lottery draw to an extent that he might have enough information to have that probability. Now if Bob says he thinks he has a greater than 50% chance of winning the lottery because he is feeling lucky, and that is it, you can probably say that is unattached to reality or ignoring lots of relevant information.

Will_Pearson 20 Mar 2008 9:43 UTC
1 point
on: Joy in the Merely Real
“Your choice is either:
- Decide that things are allowed to be unmagical, knowable, scientifically explicable, in a word, real, and yet still worth caring about;
- Or go about the rest of your life suffering from existential ennui that is unresolvable.”
A few comments. Do all people have this choice? What do you exactly mean about a choice anyway? Surely their past experience will determine their answer to this question.

Isn’t there other paths people take? Immersing themselves into the fantasies of celebrities or WoW, ignoring the dull real.