Belz...
Fiend God
Well, there you have it. You've constructed an inassailable ivory tower: you won't improve until you get sensible feedback, but you don't accept feedback because you think you know best.
Merged Artificial Intelligence Research: Supermathematics and Physics
- Thread starter ProgrammingGodJordan
- Start date
Well, there you have it. You've constructed an inassailable ivory tower: you won't improve until you get sensible feedback, but you don't accept feedback because you think you know best.
I have merged the Supermathematics and Artificial General Intelligence with the thread regarding Bengio's paper and also the earlier Thought Curvature thread, as they are all essentially on the same subject. Please stay on topic and refrain from personalising your posts.
Replying to this modbox in thread will be off topic Posted By: Agatha
theprestige
Penultimate Amazing
What's the difference between "supermathematics" and regular mathematics? PGJ uses the term in his title, but he doesn't define or discuss it anywhere.
ProgrammingGodJordan
Banned
Some crucial links in old OP are dead.
Please edit the old OP to include these new links where "Thought curvature" appears.
New replacement link:
https://www.researchgate.net/publication/316586028_Thought_Curvature_An_underivative_hypothesis
ProgrammingGodJordan
Banned
halleyscomet
Penultimate Amazing
- Joined
- Dec 7, 2012
- Messages
- 10,259
You make a valid point. Human babies, or indeed any living creature capable of learning from experience, are a viable source of inspiration for developing an AI that is itself capable of learning. Indeed, this is the central thesis of a thought provoking video that argues All Arnold Schwarzenegger Movies Are In The Same Terminator Universe
If that is the entirety of your point, then I think the thread has progressed as far as it can. If you have a point beyond that, what is it?
halleyscomet
Penultimate Amazing
- Joined
- Dec 7, 2012
- Messages
- 10,259
He is making fun of your ideas by referencing a physical reaction to particularity bad poetry described in The Hitchhiker's Guide to the Galaxy.
ProgrammingGodJordan
Banned
The thread was merged, so you may have missed the new thread.
Here is the data from the new thread: https://jordanmicahbennett.github.io/Supermathematics-and-Artificial-General-Intelligence/
In summary, the new thread deals with:
[imgw=650]https://i.imgur.com/L96rxC3.png[/imgw]
Footnote:
Take all the time you need to understand the above...
And also, babies and physics and machine learning, are regular considerations in not just fiction, but machine learning:
Last edited:
Thermal
August Member
Oh Great and Wondrous PGJ, parse thusly:
Nononononono. Not once has repeatedly reposting yourself benefited anyone, anywhere, for any reason. Just get on with it without the robot-speak and endless repetition and a discussion just might spring forth, as a lily in the desert.
halleyscomet
Penultimate Amazing
- Joined
- Dec 7, 2012
- Messages
- 10,259
Why are you bringing this to a skeptic's forum and not one focused on mathematics? I don't post descriptions of my adventures in homebrewing here, nor do I discuss the best ways to culture koji for home sake production. I certainly don't start a discussion on the best .NET methods to use for connecting to SFTP and FTPS servers and the security merits of the two protocols.
Why have you come HERE with this topic?
Have you tried discussing this on forums dedicated to mathematics?
ProgrammingGodJordan
Banned
Your question may be rephrased as "Why post scientific matters in a 'Science, Mathematics, Medicine, and Technology' forum?"
I will leave you to imagine the answer to the query above.
halleyscomet said:
Yes.
Discussions elsewhere, on Math forums too, have actually lead to some of the descriptions contained in the papers.
Also, discussions on forums that don't specialize in Math, have also helped to make the papers clearer and clearer. (A recent example on this very thread)
Thermal
August Member
Perhaps He wants His musings reviewed with a skeptical eye. He is certainly getting that. In spades.
ProgrammingGodJordan
Banned
Hardly any sensible feedback though...
halleyscomet
Penultimate Amazing
- Joined
- Dec 7, 2012
- Messages
- 10,259
Please, elaborate. Give examples.
Thermal
August Member
There ya go! Coherent wording, no repetition or linking the same things over and over. Keep up the good work and you'll engage serious discussion in no time!
Thermal
August Member
Don't encourage Him. We're making headway.
halleyscomet
Penultimate Amazing
- Joined
- Dec 7, 2012
- Messages
- 10,259
That was a legalistic dodge, not an answer. It does however tell me far more about your intentions here than I think you intended to reveal. Thank you for tipping your hand so blatantly and obviously.
abaddon
Penultimate Amazing
It is beyond belief that this continues.
How anyone can think that a spamfest of copypasta convinces anyone of anything is incomprehensible.
How anyone can think that a spamfest of copypasta convinces anyone of anything is incomprehensible.
ProgrammingGodJordan
Banned
That was a legalistic dodge, not an answer. It does however tell me far more about your intentions here than I think you intended to reveal. Thank you for tipping your hand so blatantly and obviously.
I don't know what you are on about, but my intentions are not hidden; and I've gone "as far" as to include a "What is the goal?" section in a github url in the new OP.
Intention pretty clear there.
barehl
Master Poster
- Joined
- Jul 8, 2013
- Messages
- 2,655
My take on it is that he's saying that you can create estimates of probability using Bayesian statistics for separate abstract elements. Then you can combine the estimates to form a stronger prediction about the environment for a given intelligent agent. In Bayesian statistics a diffuse prior only provides vague predictions and therefore isn't very useful. His suggestion is that you can combine diffuse priors to make a much stronger prediction.
He seems to be trying to solve the problem of an intelligent agent acting within an environment without sufficient information about the environment. This is an ongoing problem with AI and machine learning. He seems to see this as a pattern matching problem which is why he refers to recurrent neural networks.
None of that is so bad, but after that it pretty much falls apart. He suggests that this mechanism would be useful for awareness and consciousness. He shows misunderstanding of focus and seems to believe the language of thought theory. For example, if you did try to use his structure for awareness you would fall into the Frame problem. Maybe he isn't aware of it. His notion about focus is ludicrous since it could give you a random, divergent, or convergent process. This is a common problem with bottom up approaches. To date there has been no supporting evidence for a language of thought other than that it goes along with computational theory.
That's my opinion about it. In other words, he might well be able to make a contribution to Bayesian statistics but I don't see this as advancing AI in the least.
Last edited: