Is anyone working on an embodied AI? Even a simulated body might help. Ultimately intelligence is only useful insofar as it guides the body's motion. We often tend to minimize the physical act of say, writing down a theorem or actually applying paint to the canvas, but there are certain actions like playing a musical instrument that certainly blur the distinction between "physical" and "mental". Indeed, even 'purely…
Yann LeCun's comment on AlphaGo and true AI
21–30 of 216 posts
Re: Yann LeCun's comment on AlphaGo and true AI
#22Can someone elaborate the difference between reinforcement learning and unsupervised learning? It seems that I mistakenly think that human learns through reinforcement learning, that we learn by the feedback from the outside world. I mean without feedback from aldult can a baby even learn how to walk?
Not an expert, but my understanding is that humans can learn many things through reinforcement learning, but most of our intelligent decisions are a result of unsupervised learning. For instance, if the stove element was red hot and you touched it, you'd receive a feeling of pain. Reinforcement learning would suggest that you shouldn't do this again, and you might learn to not touch stove elements when they are red h…
Interesting, so it's the ability to generalize attributes selectively? That sounds like it would make for the difference between the specialized deep learning we have and a more general intelligence.
Could that be accomplished if NN problems are broken into features, and those features are individually tested against new information? Though you'd need a layer for feature selection, and it still lacks the ability to pick features without training.
Re: Yann LeCun's comment on AlphaGo and true AI
#23Earlier quoted context omitted.
Well, it just seems unlikely that psychology will produce significant insights here, because it mostly just looks at how the brain behaves. While this can be insightful, I doubt that it will explain intelligence in the end, because this happens a layer below. That's precisely what neuroscience covers. The other approach (just thinking about the problem and trying to to build a AI from first principles) is CS. So I wo…
I think someone needs to come up with a good theory of what intelligence even is, then we can try to discover its mechanism(s).
AI has some good definitions as far as intelligence is concerned. Perhaps you are worried about consciousness or something, but this is not needed for a definition of what intelligence means.
Re: Yann LeCun's comment on AlphaGo and true AI
#24Can someone elaborate the difference between reinforcement learning and unsupervised learning? It seems that I mistakenly think that human learns through reinforcement learning, that we learn by the feedback from the outside world. I mean without feedback from aldult can a baby even learn how to walk?
Unsupervised learning in a technical sense means things like clustering algorithms where the goal is to discover structure in a data set without known labels (or numeric response).
If you show a human a single unlabeled picture of a platypus (or whatever) they will know instantly with a high degree of certainty that it is a new category of thing and be able to recognize additional images of it as belonging to that class even without being told a label for it.
Our best image classification algorithms can't do that, even with labels they need a lot of example images to learn to identify a new class.
Re: Yann LeCun's comment on AlphaGo and true AI
#25Once an AI algorithm (even just one for Go) realizes that it can hijack the bank accounts of all the world's other 9 dan players in order to demand an analysis of its planned move, and figures out how to do that, then we've made the cake.
N.B. the genericity of the deepmind stuff that is the basis of AlphaGo makes this seem not entirely far-fetched.
Yum, cake.
Re: Yann LeCun's comment on AlphaGo and true AI
#26Earlier quoted context omitted.
Neural networks are the big driver and arguably were taken from neuroscience. The reason why psychology is 'too high-level' is exactly what is meant with 'we don't understand it', we're approaching the psyche at the macro level of observable traits, but there is a very large gap between the 'wiring' and the 'traits', some of that gap belongs to neuroscience but quite possibly the larger parts belongs to psychology. T…
They were taken from neuroscience... 50 years ago. Since then, very few ideas have been explicitly taken from neuroscience.
Exactly, and even then, half of the details or how real neurons work were ignored or discarded. NN are now often taught by sticking closely to the math and avoiding the term and any reference to biology completely.
Re: Yann LeCun's comment on AlphaGo and true AI
#27Earlier quoted context omitted.
Neural networks are the big driver and arguably were taken from neuroscience. The reason why psychology is 'too high-level' is exactly what is meant with 'we don't understand it', we're approaching the psyche at the macro level of observable traits, but there is a very large gap between the 'wiring' and the 'traits', some of that gap belongs to neuroscience but quite possibly the larger parts belongs to psychology. T…
They were taken from neuroscience... 50 years ago. Since then, very few ideas have been explicitly taken from neuroscience.
That's like saying there has been no development in automobiles since 1890. Sure, at first glance the cars from then are still like the cars from now. ICE (or electrical) power source, maybe a gearbox, some seats, a steering wheel and something to keep you out of the weather. But that's at the same time ignoring many years of work on those concepts in order to further refine them.
The neural networks that were taken 'explicitly from neuroscience' have gone through a vast transformation and that + a whole lot of work on training and other stuff besides is what powers the current crop of AI software. All the way to computers that learn about games, that label images and that drive cars with impressive accuracy to date.
The problem is - and I think that was what the original question was about - that neuroscience is rather very low level. We need something at the intermediate level, a 'useful building block' approach if you will, something that is not quite a fully formed intelligence but also not so basic as plumbing and wiring.
Re: Yann LeCun's comment on AlphaGo and true AI
#28Earlier quoted context omitted.
They were taken from neuroscience... 50 years ago. Since then, very few ideas have been explicitly taken from neuroscience.
Exactly, and even then, half of the details or how real neurons work were ignored or discarded. NN are now often taught by sticking closely to the math and avoiding the term and any reference to biology completely.
Does it matter? As long as the original source for the idea is remembered I don't particularly care which field originated it. There are so many instances and examples of cross pollination between IT and other sciences that in the end whether or not we stick to the original in a literal fashion or not should not matter (and if we did we'd probably lose out on a good bit of progress).
Re: Yann LeCun's comment on AlphaGo and true AI
#29I think we need more advances in neuroscience and, I know this will be controversial, psychology before we really know what the cake even is. Edit: I actually think the major AI breakthrough will come from either of those two fields, not computer science.
Just like ornithologists invented the first airplane, and horse vets built the first automobile, etc.
Re: Yann LeCun's comment on AlphaGo and true AI
#30There's also a huge issue around problem-posing and degrees of freedom, that doesn't necessarily get better as your AI tools improve. Go has a fairly large state space, but limited potential moves per turn, well-defined decision points, limited time constraints, and only one well-defined victory condition. The complexity is minuscule compared to even something relatively well-structured like "maximize risk-adjusted return via stock trades".