Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Artificial intelligence pioneer says we need to start over

axios.com

Post reply on HN
Print view View original

41–50 of 156 posts

Re: Artificial intelligence pioneer says we need to start over

#41

Post by iandanforth »

eanzenberg wrote: post #35
iandanforth wrote: post #22

Brief description of the issue for non-experts: Supervised learning You can judge the output of your network against ground truth. You say that's a cat? Nope, it's a dog! And then slightly adjust your network so it's less likely to give that wrong answer in the future. How exactly you adjust the network is what backpropagation describes (in combination with something called a learning rate). Unsupervised learning You…

Actually: >>Most of the time for biological intelligence there isn't an oracle describing the truth at every moment of life This is false for most of learning of human intelligence. Most of schooled human intelligence looks like supervised learning. Innate intelligence and other animal intelligence looks like pre-trained models and some reinforcement learning.

Can we go with 'incomplete' rather than 'false'? :) One of the most interesting areas of study for me is early childhood motor learning which is a fascinating combination of unsupervised, reinforced, and imitation learning. There are even significant intrinsic knowledge (instinctual/reflexive/morphological) effects. Also I really like to encompass non-human learning when talking about this stuff to remind myself of all the work nature did before we got to cultural transmission of knowledge.

Re: Artificial intelligence pioneer says we need to start over

#42

Post by toss1 »

tw1010 wrote: post #8
bra-ket wrote: post #5

If you are interested in biologically plausible models of cognition check out 'vector symbolic architectures' and 'associative memory' research of the 90s.

Biological plausibility is just silly. What it mostly does is just put artificial constraints on the problem that doesn't need to be there. It's all mathematics. However you want to interpret or metaphorize the mathematics is up to each math-phobic field, but constraining yourself to what randomly evolved serves little good.

Biological plausibility is only silly if you assume that biology has NOT in ~4 billion years of evolution managed to explore the design space and arrive at good general maxima/peak design for intelligent processes and are not merely stuck on the first local peak design encountered.

It assumes that outside of this biological design space lies both lower peaks and much higher unexplored peaks.

While it is likely that somewhere in the universe are higher peaks of design schemes for intelligence, it is also likely that those peaks are difficult to reach from here (4B+ years of evolution hasn't done it yet). It's also possible that the Fermi Paradox is showing is that there is no substantially better general design schema.

So, the more successful approach would probably be to seek designs for the first Automated General Intelligence in a design space that has already demonstrably succeeded, then perhaps use that AGI to search for other better design spaces.

Re: Artificial intelligence pioneer says we need to start over

#43

Post by chubot »

eanzenberg wrote: post #35
iandanforth wrote: post #22

Brief description of the issue for non-experts: Supervised learning You can judge the output of your network against ground truth. You say that's a cat? Nope, it's a dog! And then slightly adjust your network so it's less likely to give that wrong answer in the future. How exactly you adjust the network is what backpropagation describes (in combination with something called a learning rate). Unsupervised learning You…

Actually: >>Most of the time for biological intelligence there isn't an oracle describing the truth at every moment of life This is false for most of learning of human intelligence. Most of schooled human intelligence looks like supervised learning. Innate intelligence and other animal intelligence looks like pre-trained models and some reinforcement learning.

"Schooled human intelligence"? What does that even mean?

I think you are severely underestimating humans, and probably animals too.

People have multiple modes of learning. You can try to get an A in school ("optimize" for the objective function), but you also might be skeptical of what the teacher tells you. Likewise you might be skeptical of what you read in a book.

You can also correct the teacher based on common sense and what you already know.

Currently, a computer can do no such thing. I think he's right that there is a fundamental difference.

Humans also learn from extremely small amounts of data. (Sometimes they learn badly, but they can change their minds, or not if they still manage to navigate the world.)

Re: Artificial intelligence pioneer says we need to start over

#44

Post by felippee »

eanzenberg wrote: post #35
iandanforth wrote: post #22

Brief description of the issue for non-experts: Supervised learning You can judge the output of your network against ground truth. You say that's a cat? Nope, it's a dog! And then slightly adjust your network so it's less likely to give that wrong answer in the future. How exactly you adjust the network is what backpropagation describes (in combination with something called a learning rate). Unsupervised learning You…

Actually: >>Most of the time for biological intelligence there isn't an oracle describing the truth at every moment of life This is false for most of learning of human intelligence. Most of schooled human intelligence looks like supervised learning. Innate intelligence and other animal intelligence looks like pre-trained models and some reinforcement learning.

Except that by the age you reach school you already know amazing wealth of knowledge about the world and how it works, particularly the kind of commonsense knowledge that AI has always had enormous trouble to acquire. See Moravec's paradox.

Re: Artificial intelligence pioneer says we need to start over

#45

Post by Animats »

Machine learning may be nearing its ceiling.

The history of AI goes in cycles. Someone has a good idea which solves some problems, followed by "strong AI Real Soon Now" enthusiasm, followed by that idea hitting its ceiling. AI has been through search, backtracking, the General Problem Solver, hill-climbing, and expert systems. Each was overhyped at the time, and each hit its ceiling.

The big difference this time is that the ceiling with machine learning is high enough for large-scale profitable applications. That wasn't the case with the previous rounds. AI used to be a dinky field - about 30-50 people each at Stanford, CMU, and MIT, plus a few tiny groups elsewhere. Now it's a huge field with big companies and big profits. That makes it self-sustaining.

Hinton has a point in that we're missing something. Back-propagation is an extremely inefficient method, especially since the slower you do it, the better it seems to work. More generally, most of machine learning is "turn the problem into an optimization problem and bang on it really hard with lots of compute power". This works for a useful class of problems. But it has limits.

How long until the next big idea? The last "AI winter", after expert systems, was 15 years.

Re: Artificial intelligence pioneer says we need to start over

#46

Post by fsavard »

That article is pretty light on details. I wonder if he pointed towards a specific form of unsupervised learning.

Anyway it's pretty funny in light of an intro I remembered from one of his old papers:

"It would be truly wonderful if randomly connected neural networks could turn themselves into useful computing devices by using some simple rule to modify the strength of synapses. This was the hope that lay behind the original Hebb learning rule and it is the vision that has driven neural network modelers for half a century. Initially, researchers tried simulating various rules to see what would happen. After a decade or two of messing around, researchers realized that there was a much better way to explore the space of possible learning rules: First write down an objective function [...] and then use elementary calculus to derive a learning rule that will improve the objective function." [1]

ie. backprop

So actually backprop was the solution to all that initial "messing around" with unsupervised rules. Though of course to be fair (if I understand correctly) those rules had very little to do with modern "unsupervised learning" methods (e.g. autoencoders, which still rely on backprop or similar optimization).

[1] http://www.cs.toronto.edu/~fritz/absps/hebbdot.pdf published in 2003

Re: Artificial intelligence pioneer says we need to start over

#47

Post by fngl51 »

31reasons wrote: post #40
eanzenberg wrote: post #35

Earlier quoted context omitted.

Actually: >>Most of the time for biological intelligence there isn't an oracle describing the truth at every moment of life This is false for most of learning of human intelligence. Most of schooled human intelligence looks like supervised learning. Innate intelligence and other animal intelligence looks like pre-trained models and some reinforcement learning.

I think innate intelligence/ animal intelligence is developed by evolutionary algorithm. You don't need to do back prop for it. If the network is wrong, the animal just dies.

I would agree with this approach. In evolution, it would be the equivalent to a conditional lethal mutation. In humans and even non-humans, may behaviors are learned through a form of adaptive behavior that oftentimes becomes a form of abductive reasoning. What is learned is "good enough" to serve as ground truth until there is evidence to contradict.

Re: Artificial intelligence pioneer says we need to start over

#48

Post by Zee2 »

zebrafish wrote: post #34

I don't know. I think backprop is probably utilized a lot in biological networks. Isn't that why we take tests in school? Obviously backprop doesn't make sense in an unsupervised setting. There's no label to backprop on. But here's an example: I see a stove eye is black when cold, then when I see it turn red, I touch it. Ow, it hurts. That's supervised learning. Don't touch things that are glowing red when they don't…

I think an important part of this is the label that the network creates itself. So, in your example of "four legs and fluffy = 'animal'", that label of "animal" must be a completely computer-created label. Not necessarily using the word "animal", or using any kind of identifier that humans would use. A completely artificial grouping, or domain, that is identified by the computer on its own, and maintained and stored as a potentially useful label for future use.

Re: Artificial intelligence pioneer says we need to start over

#49

Post by eanzenberg »

chubot wrote: post #43
eanzenberg wrote: post #35

Earlier quoted context omitted.

Actually: >>Most of the time for biological intelligence there isn't an oracle describing the truth at every moment of life This is false for most of learning of human intelligence. Most of schooled human intelligence looks like supervised learning. Innate intelligence and other animal intelligence looks like pre-trained models and some reinforcement learning.

"Schooled human intelligence"? What does that even mean? I think you are severely underestimating humans, and probably animals too. People have multiple modes of learning. You can try to get an A in school ("optimize" for the objective function), but you also might be skeptical of what the teacher tells you. Likewise you might be skeptical of what you read in a book. You can also correct the teacher based on common s…

How >>Humans also learn from extremely small amounts of data. (Sometimes they learn badly, but they can change their minds, or not if they still manage to navigate the world.) ??

What does this mean? That 18 years of schooling is a "small amount of data"? Do you think you show 2 pictures of an airplane to a child and they know what an airplane is? Do you even have kids?

Re: Artificial intelligence pioneer says we need to start over

#50

Post by eanzenberg »

iandanforth wrote: post #41
eanzenberg wrote: post #35

Earlier quoted context omitted.

Actually: >>Most of the time for biological intelligence there isn't an oracle describing the truth at every moment of life This is false for most of learning of human intelligence. Most of schooled human intelligence looks like supervised learning. Innate intelligence and other animal intelligence looks like pre-trained models and some reinforcement learning.

Can we go with 'incomplete' rather than 'false'? :) One of the most interesting areas of study for me is early childhood motor learning which is a fascinating combination of unsupervised, reinforced, and imitation learning. There are even significant intrinsic knowledge (instinctual/reflexive/morphological) effects. Also I really like to encompass non-human learning when talking about this stuff to remind myself of a…

Please describe what "unsupervised learning" a child may be doing.
Post reply on HN