Model-Free, Model-Based, and General Intelligence [pdf]
1–10 of 32 posts
Re: Model-Free, Model-Based, and General Intelligence [pdf]
#2I attended this talk at IJCAI, and I must say that the whole system 1 / system 2 analogy rubbed me the wrong way.
A solver for e.g. 3-SAT is general only in a very narrow sense, namely that an entire class of problems can be reduced to the specific problem it solves. However, the solver itself is not doing the reducing, rather it is being spoon-fed instances generated by somebody, and that somebody is doing all the hard work of actually thinking. The solver is just doing a series of dumb steps very quickly, with lots of heuristics thrown in. How is that not also "system 1"?
Anyway, the whole thing was just a fancy way of saying that you can either solve problems exactly, in the way that complexity theorists and algorithm designers do things, or statistically, in the way that learning theorists do things. No need to superimpose a strained analogy.
Re: Model-Free, Model-Based, and General Intelligence [pdf]
#3Was this an invited talk?
Re: Model-Free, Model-Based, and General Intelligence [pdf]
#4I attended this talk at IJCAI, and I must say that the whole system 1 / system 2 analogy rubbed me the wrong way. A solver for e.g. 3-SAT is general only in a very narrow sense, namely that an entire class of problems can be reduced to the specific problem it solves. However, the solver itself is not doing the reducing, rather it is being spoon-fed instances generated by somebody, and that somebody is doing all the h…
I'm curious to know what your definition of "actually thinking" is. I suspect your argument is circular.
Re: Model-Free, Model-Based, and General Intelligence [pdf]
#5It seems the fundamental problem with bottom up/learning AI is that it is opaque and essentially unknowable. I find it all very hackish. We can develop systems now which we can test and seem to work, but we don't know exactly why they work (eg: what parts of the training data they are promoting) and when (or why) they will fail. The effectiveness of adversarial inputs to trained vision systems illustrates this.
Zoom forward to a super-human AI that mimics our brains in its approach but exceeds its capacity. What is stopping it, for instance, learning that it can play the long game of being good until it has sufficient power at its disposal and then becoming evil? No matter what training data you present, you can't know exactly what the result will be.
I get the feeling that learning systems will be combined with model systems with the former performing "low level" tasks and the latter providing a verifiable "executive" that guides high level goals or outcomes.
Re: Model-Free, Model-Based, and General Intelligence [pdf]
#6Was this an invited talk?
Yep, it was.
Re: Model-Free, Model-Based, and General Intelligence [pdf]
#7I attended this talk at IJCAI, and I must say that the whole system 1 / system 2 analogy rubbed me the wrong way. A solver for e.g. 3-SAT is general only in a very narrow sense, namely that an entire class of problems can be reduced to the specific problem it solves. However, the solver itself is not doing the reducing, rather it is being spoon-fed instances generated by somebody, and that somebody is doing all the h…
Not to mention that there is no conclusive evidence of the dual process theory yet, see for example this experimental study finding that logical "type 2" answers are actually typically faster and that intuitive "type 1" answers are typically also logical:
https://www.sciencedirect.com/science/article/pii/S001002771...
Re: Model-Free, Model-Based, and General Intelligence [pdf]
#8It seems the fundamental problem with bottom up/learning AI is that it is opaque and essentially unknowable. I find it all very hackish. We can develop systems now which we can test and seem to work, but we don't know exactly why they work (eg: what parts of the training data they are promoting) and when (or why) they will fail. The effectiveness of adversarial inputs to trained vision systems illustrates this. Zoom…
One approach being considered is "AI Safety Via Debate"[0], which hopes to prevent deception by carefully constructing games in which a superhuman agent's best strategy is honesty. Note that this is the goal; much work to be done!
Re: Model-Free, Model-Based, and General Intelligence [pdf]
#9"If we want good AI, we can’t look away from culture and politics."
At the end AI will join our tense political atmosphere of parties fighting for ruling the world?
Re: Model-Free, Model-Based, and General Intelligence [pdf]
#10It seems the fundamental problem with bottom up/learning AI is that it is opaque and essentially unknowable. I find it all very hackish. We can develop systems now which we can test and seem to work, but we don't know exactly why they work (eg: what parts of the training data they are promoting) and when (or why) they will fail. The effectiveness of adversarial inputs to trained vision systems illustrates this. Zoom…
One approach being considered is "AI Safety Via Debate"[0], which hopes to prevent deception by carefully constructing games in which a superhuman agent's best strategy is honesty. Note that this is the goal; much work to be done! [0] https://arxiv.org/abs/1805.00899
Do we know the entire game theory well enough so that we can structure such games with no theoretical way for AI to sneak out? I doubt that, but even so, funny things start happening when theory meets practice. I recall the example of quantum entanglement, which (I read) enables communications that cannot be spied upon without the intended parties knowing. Except, (I also read) it was attacked at the interface between quantum and classical domain. The world is complex, and superhuman AI is by definition better equipped to find loopholes than humans are.