YouSaid · the spoken record

Juergen Schmidhuber

lines on the record: 75
first: 2018-12-23
most recent: 2018-12-23
sittings or episodes: 1
sources: podcast

Every line below is reproduced as it was said and linked to the record it came from. Nothing here is summarised or generated. Directory · Search · Corrections

“And suddenly many, many of these observations became much more compressible, because as long as you can predict, the next thing, given what you have seen so far, you can compress it. You don't have to store that data extra. This is called predictive coding. And then there was still something wrong with that theory of the universe and you had deviations from these predictions of the theory, and three hundred years later another guy came along whose name was Einstein. And he was able to explain away all these deviations from the predictions of the old theory through a new theory which was called the general theory of relativity, which at first glance looks a little bit more complicated and you have to warp space and time, but you can't phrase it within one single sentence, which is”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“Indeed, the history of science is a history of compression progress. What does that mean? Hundreds of years ago there was an astronomer whose name was Kepler, and he looked at the data points that he got by watching planets move, and then he had all these data points and suddenly turned out that he can greatly compress the data by Predicting it through an ellipse law. So it turns out that all these data points are more or less on ellipses around the sun. And another guy came along, whose name was Newton, and before him Hook, and they said the same thing that is making these planets move like that is what makes the apples fall down, and it also holds for stones and for Kinds of other objects”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“Because the explanation becomes shorter. A universe is That is compressible to a short program is much more elegant and much more beautiful than another one which needs an almost infinite number of bits to be described. As far as we Many things that are happening in this universe are really simple in terms of short programs that compute gravity and the interaction between elementary particles and so on. So all of that seems to be very, very simple. Every electron seems to reuse the same sub-program all the time as it is interacting with other elementary particles. If we now Required an extra oracle injecting new bits of information all the time for these extra things which are currently not understood, such as Better dec Then the whole Description length of the data that we can observe of the history of the universe would become”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“Yes, including all the entanglement things and all the spin up and down measurements that have been Taken place since 13.8 billion years ago and so yeah so We don't have a proof that it is random, we don't have a proof that it is Compressible to a short program, but as long as we don't have that proof, we are obliged as scientists to keep looking for that simple explanation.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“We don't have any fundamental reason at the moment to believe that this is truly random and not just a deterministic video game. If it was a deterministic video game it would be much more beautiful because beauty is simplicity and many of the basic laws of the universe like gravity and the other basic forces are very simple so very short programs can explain what these are doing. And it would be awful and ugly, the universe would be ugly, the history of the universe would be ugly if for the extra things, the random, the seemingly random data points that we get all the time. That we really need a huge number of extra bits to describe all these extra bits of information. So as long as we don't have evidence that there is no short programs that computes the entire history of the entire universe”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“Roughly one in a thousand times, and every five digit sequence appears roughly one in ten thousand times. What you would expect. If it was random, but there's a very short algorithm, a short program that computes all of that. So it's extremely compressible. And who knows, maybe tomorrow somebody, some grad student at CERN goes back over all these data points, better decay and whatever, and figures out, oh, it's the second billion digits of pi or something like that.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“A couple of years ago, a famous physicist Quantum physicist Antoine Zeilinger, he wrote an essay in Nature. And it started more or less like that. One of the fundamental insights of the After the 20th century was that The universe is fundamentally random on the quantum level. And that whenever You measure spin up or down or something like that. A new bit of information enters the history of the universe. And while I was reading that I was already typing the response and they had to publish it because I was right. That there is no evidence, no physical evidence for that. So there's an alternative explanation where everything that we consider random is actually pseudo-random, such as the decimal expansion of pi, 3.141, and so on, which looks random, but isn't sur pi is interesting because every three digit sequence of three digits.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“So far, the only example we have This one, this universe. Maybe not, but we are part of this whole process. Apparently, so it might be the case that the code that runs the universe is really, really simple. Everything points to that possibility because gravity and other basic forces are really simple laws that can be easily described also in just a few lines of code, basically. And then there are these other events that the apparently random events in the history of the universe, which as far as we know at the moment don't have a compact code, but who knows, maybe somebody in the near future is going to figure out the pseudo-random generator, which is computing, whether the measurement of that spin up or down thing here is going to be positive or negative.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, of course, we are building on all these great abstractions that people have invented over the millennia, such as matrix multiplications and real numbers and Basic arithmetics and calculus and derivations of error functions and derivatives of error functions and stuff like that. So without that language that greatly simplifies our way of thinking about these problems, we couldn't do anything, so in that sense as always we are standing on the shoulders of the giants who in the past simplified the problem of problem solving so much that now we have a chance to do the final step.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“Experience tells us that the stuff that works best is really simple. So the asymptotically optimal ways of solving problems, if you look at them, then just a few lines of code. It's really true. Although they are these amazing properties, just a few lines of code, then the most promising and most useful practical things. Maybe don't have this proof of optimality associated with them, however they are also just a few lines of code. The most successful recurring neural networks, you can't write them down and five lines are pseudocode.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“Equipped with local search techniques, and we are happy that it works better than any competing method, but that doesn't mean that we think we are done.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“There's an old saying, and I don't know who brought it up first, which says there is nothing more practical than a good theory. And a good theory of problem solving. Under limited resources, like here in this universe or on this little planet, Has to take into account these limited resources. And so proudly there is locking A theory which is related to what we already have, these asymptotically optimal problem solvers, which tells us what we need in addition to that to come up with a practically optimal problem solver. So I believe we will have something like that. And maybe just a few little tiny twists unnecessary to change what we already have, to come up with that as well. As long as we don't have that, we admit that we are taking suboptimal ways and recurrent neural networks and long short-term memory for”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“To try to find a program that is running on these recurrent networks such that it can solve some interesting problems such as speech recognition or machine translation and something like that. And there is very little theory behind the best solutions that we have at the moment that can do that.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“So P versus NP, that's super interesting from a theoretical point of view. And in fact, as you are thinking about that problem, you can also get inspiration for better practical problem solvers. On the other hand, we have to admit that at the moment the best practical problem solvers for all kinds of problems that we are now solving through what is called AI at the moment. Say I am not of the kind that is inspired by these questions. There we are using general purpose computers such as recurrent neural networks, but we have a search technique which is just local search, gradient descent.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“That's right, yeah. So they seem large and even unsolvable in a practical sense today, but they are still small compared to almost all problems, because almost all problems are large problems which are much larger than any constant.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“Of one plus a constant number of steps that you need for the pro searcher which you need to show that this particular class of problems that travelling salesman problems can be solved within a certain time bound within Oda into the five steps basically and this additive constant doesn't care for n, which means as n is getting larger and larger as you have more and more cities, the constant overhead pales in comparison and that means that almost all large problems are solved in the best possible way already today we already have a universal problem solver like that. However, it's not practical because the overhead, the constant overhead is so large that For the small kinds of problems that we want to solve in this little biosphere.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“With traveling salesman proudlands, you have a number of cities, n cities, and you try to find the shortest path through all these cities without visiting any city twice. And nobody knows the fastest way of solving traveling salesman problems. let's assume there is a method of solving them with an n to the five operations where n is the number of cities. Then the universal method of Marquis is going to solve the same Charlie Salesman problem also within n to the five steps plus.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“And local search techniques, which aren't universal at all, which aren't provably optimal at all, like the other stuff that we did, but which are much more practical as long as we only want to solve the small problems that we are. Typically trying to solve this environment here. So the universal problem solvers, like the Google machine, but also Marcus Hutter's fastest way of solving all possible problems. Which he developed around two thousand two in my lab, they are associated with these cars in overheads for proof search, which guarantees that the thing that you're doing is optimal. For example, there is this fastest way of solving all problems with a computable solution which is due to Macus, Macro Sutter. And to explain what's going on there, let's take traveling salesman problems.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“Yes, we had these two different types of fundamental research, how to build a universal problem solver. One basically exploiting And things like that that you need to come up with asymptotically optimal, theoretically optimal self-improvers and problem solvers. However, one has to admit that through this proof search, Comes in an additive constant, an overhead, an additive overhead. Vanishers in comparison to what you have to do to solve large problems. However, for many of the small problems that we want to solve in our everyday life, we cannot ignore this constant overhead. And that's why we also have been doing other things, non-universal things such as recurrent neural networks which are trained by gradient descent.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“So that is transfer learning, and it has been done in principle for many decades. People have done similar things for decades, but Mada learning true meta learning is about having the learning algorithm itself open to introspection by the system that is using it. and also open to modification such that the lying system has an opportunity to modify any part of the learning algorithm and then evaluate the consequences of that modification and then learn from that to create a better learning algorithm and so on recursively. So that's a very different animal where you are opening the space of possible learning algorithms to the learning system itself.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“Let's take the example of a deep neural network that has learned to classify images. And maybe you have trained that network on 100 different databases of images. And now a new database comes along and you want to quickly learn the new thing as well. So, one simple way of doing that is you take the network which already knows 100 types of databases, and then you just take the top layer of that and you retrain that. Using the new label data that you have in the new image database. And then it turns out that it really, really quickly kind of learned that too. One shot, basically, because from the first 100 data sets, it already has learned so much about computer vision that it can reuse that and that is then almost good enough to solve the new task except you need a little bit of adjustment on the top.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“And that was my 1987 diploma thesis, which was all about that hierarchy of metal learners, that Have no computational limits except for the well-known limits that Goethe identified in 1931 and for the limits are physics.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“So, in the 80s. I thought about how to build this machine that learns to solve all these problems that I cannot solve myself. And I thought it is clear it has to be a machine that not only learns to solve this problem here and this problem here, but it also has to learn to improve the learning algorithm itself. So it has to have the learning algorithm in a representation that allows it to inspect it and modify it. that it can come up with a better learning algorithm. So I call that meta learning learning to learn and recursive self improvement that is really the pinnacle of that where you then not only learn but How to improve on that problem and on that, but you also improve the way the machine improves. And you also improve the way it improves the way it improves itself.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“Yes, so if you can build a machine that learns to more and more complex problems and more and more general problem solver than you basically have solved all the problems, at least all the solvable problems.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source
“When I was a boy, I'm I was thinking about what to do in my life, and then I thought the most Exciting thing is to solve the riddles of the universe, and that means you have to become a physicist. However, then I realized that there's something even grander you can try to build a machine that isn't really a machine any longer that learns to become a much better physicist than I could ever hope to be. And that's how I thought maybe I can multiply my tiny little bit of creativity into infinity.”
2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source