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

1. “It would make us much more important because if we mess it up through a nuclear war. Then maybe this will have an effect on the development of the entire universe.”

   2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

2. “Thing it's quite plausible that maybe you are the first, at least in our local light cone within A few hundreds of millions of light years that we can reliably”

   2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

3. “Gravity by itself explains the large scale structure of the universe, and that this is not a convincing explanation. And then I thought maybe it's the dark matter. Because as far as we know, today, 80% of the measurable matter is invisible. And we know that because otherwise our galaxy or other galaxies would fall apart. They are rotating too quickly. Then the idea was maybe Allah sees AI civilizations that are already out there. Just invisible because they are really efficient in using the energies of their own local systems. And that's why they appear dark to us. But this is also not a convincing explanation because Then the question becomes why is there Are there still any visible stars left in our own galaxy, which also must have a lot of dark matter? So that is also not a convincing thing. And today, I like to...”

   2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

4. “When I was a boy, I was thinking about these things. And I thought, hmm, maybe it has already happened because back then I know, I learned from Papla physics books that the structure, the large scale structure of the universe is not homogeneous. And you have these clusters of galaxies. And then in between there are these huge empty spaces. And I thought, hmm, maybe they aren't really empty. It's just that in the middle of that, some AI civilization already has expanded and then has covered a bubble of a billion light years diameter and is using all the energy of all the stars within that bubble for its own unfathomable purposes. And so it always happened and we just failed to interpret the signs. But then I learned that”

   2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

5. “And let's call the current age of the universe one eon, one eon. Now it will take just a few eons from now, and the entire visible universe is going to be full of that stuff. And let's look ahead to a time when the universe is going to be 1,000 times older than it is known. They will look back and they will say, look almost immediately after the Big Bang, only a few eons later. The entire universe started to become intelligent. Your question Do we see whether anything like that has already happened or has already in a more advanced stage in some other part of the universe, of the visible universe? We are trying to look out there and nothing like that has happened so far. Or is that true”

   2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

6. “AI civilization and AI ecologies consisting of trillions of different types of AIs. And so it seems inconceivable to me that this thing is not going to expand some AI ecology not controlled by one AI, but by trillions of different types of AIs competing in all kinds of Quickly evolving and disappearing ecological niches in ways that we cannot fathom at the moment, but it's going to expand, limited by light speed and physics, but it's going to expand. Now we realize that the universe is still young. It's only 13.8 billion years old. And it's going to be a thousand times older than that. So there's plenty of time to conquer the entire universe. And to fill it with intelligence, and senders and receivers such that AIs can travel the way they are traveling in our labs today, which is by radio from sender to receiver.”

   2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

7. “They will be fascinated by life and by their own urgence in our civilization. They will want to understand that completely, just like people today would like to understand how life works. And also... The history of our own existence and civilization, but then also in the physical laws that created all of them. So in the beginning they will be fascinated by life once they understand it, they lose interest. like anybody who loses interest in things he understands. And then, as you said, The most interesting sources of Information for them will be others of their own kind. At least in the long run, Seems to be some sort of protection. Through lack of interest on the other side. And now it seems also clear as far as we understand physics, you need matter and energy to compute and to build more robots and infrastructure and more”

   2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

8. “Be surprised if within the next few decades or something like that. We won't have AIs that are truly smart in every single way and better problem solvers in almost every single important way. And I'd be surprised if they wouldn't realize what we have realized a long time ago, which is that almost all physical resources are not here in this biosphere, but further out. The rest are the solar system gets 2 billion times more solar energy than our little planet. There's lots of material out there that you can use to build robots and self-replicating robot factories and all this stuff. They are going to do that, and they will be scientists and curious, and they will explore what they can do. And in the beginning,”

   2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

9. “It's not going to be swallowed up, but. I'd be surprised if we humans were the last step in the evolution of the universe and um you”

   2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

10. “New types of kudos and forms of likes and whatever, and even making money through that. So homoudens, the playing man, doesn't want to be unemployed and that's why he's inventing new jobs all the time. And he keeps considering these jobs as really important and is investing a lot of energy and hours of work into those new jobs.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

11. “30 years ago, who would have predicted all these people making money as YouTube bloggers, for example? 200 years ago, 60% of all people used to work in agriculture. Today, maybe 1% But still Only, I don't know, 5% unemployment. Lots of new jobs were created and homoudins, the playing man. Inventing new jobs all the time. Most of these jobs are not existentially necessary for the survival of our species. There are only very few existentially necessary jobs such as farming and building houses and warming up the houses, but less than 10% of the population is doing that. And most of these newly invented jobs are about Interacting with other people in new ways through new media and so on.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

12. “So let's first address the near future to We have had predictions of jar blasses for many decades, for example when industrial robots came along. Many people predicted lots of jobs are going to get lost. And in a sense, They were right. Because back then These factories assembled cars, and today the same car factories have hundreds of robots and maybe three guys watching the robots. On the other hand, those countries that have lots of robots per capita, Japan, Korea, Germany, Switzerland, a couple of other countries. They have really low unemployment rates. Somehow all kinds of new jobs were created. And nobody anticipated those jobs. And decades ago, I already said it's really easy to say which jobs are going to get lost, but it's really hard to predict the new ones.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

13. “Much bigger AI wave is coming than the one that we are currently witnessing, which is mostly about passive pattern recognition on your smartphone. This is about active machines that shapes data through the actions they are executing. And they learn to do that in a good way. So many of the traditional industries are going to be affected by that. All the companies that are building machines. Will equip these machines with cameras and other sensors, and they are going to learn to solve all kinds of problems. Through interaction with humans, but also a lot on their own to improve what they already can do. And lots of old economy is going to be affected by that. And in recent years, I have seen that old economy is actually waking up and realizing that this is the case.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

14. “Imitate me, but not in the supervised way where a teacher is giving target signals for all his muscles all the time. No, by doing this high-level imitation where he first has to learn to imitate me and then to interpret these additional noises coming from my mouth as helping helpful signals to Do that better. And then it will By itself, come up with faster ways and more efficient ways of doing the same thing. And finally, I stop his learning algorithm and make a million copies and sell it. And so at the moment, this is not possible, but we already see how we are going to get there. And you can imagine to the extent that this works economically and cheaply, it's going to change everything. Almost all of production is going to be affected by that. And a much bigger wave”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

15. “So I think in the not so distant future we will have for the first time Little robots that learn like kids I will be able to say to the robot. Lucky a robot, we are going to assemble a smartphone. Let's take the slab of plastic and the screwdriver and let's screw in the screw like that. Not like that. Like that. Not like that. Like that. And I don't have a data glove or something. He will see me and he will hear me and he will try to do something with his own actuators, which will be really different from mine, but he will understand the difference and will learn to”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

16. “As long as the problems have little to do with theore improving themselves, then as long as that is not the case, you just want to have better pattern recognition. So to build a self-driving car, you want to have better pattern recognition and pedestrian recognition and all these things and you want to minimize the number of false positives which is currently slowing down self-driving cars in many ways. And all of that has very little to do with logic programming.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

17. “It's very useful for Ethereum proving the best theorem provers today are not neural networks. No, they are logic programming systems and they are much better theorem provers than most math students in the first or second semester.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

18. “But then on the other hand, because we are very pragmatic guys also, we focused on recurrence networks and suboptimal stuff such as gradient-based search and program space rather than provably optimal things.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

19. “And deep learning has existed since 1965, since this guy in the Ukraine, Ivakenko started it. But the Japanese and many other people, they focused really on this largely programming. And I was influenced to the extent that I said, okay, let's take these biologically inspired algorithms like evolution programs and implement that in the language which I know, which was prologue, for example, back then. And then many ways this came back later because the Goodel machine, for example, has a proof searcher on board. And without that, it would not be optimal. Marcus Hutter's universal algorithm for solving all well-defined problems has a proof search on board. So that's very much logic programming. Without that, it would not be asymmetrical.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

20. “Yes or no, but we did all of that. So my first publication ever actually was... nineteen eighty seven was the implementation of genetic algorithm, of a genetic programming system in Prolog. That's what you learned back then, which is a logic programming language. And the Japanese, they had this huge fifth generation AI project, which was mostly about large programming back then, although neural networks existed and were well known back then.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

21. “And that's what was the future 30 years ago when you started that type of research, but it's still the future. And now we know much better how to go there to move forward and to really make working systems based on that, where you have a learning model of the world, a model of the world that learns to predict what's going to happen if I do that and that. And then... The controller uses that model to more quickly learn successful action sequences. And then, of course, always this curiosity thing. In the beginning, the model is stupid, so the controller should be motivated to come up with experiments, with action sequences that lead to data that improve the model.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

22. “So at the moment we have a tendency of using Physics simulations to learn behavior for machines that learn to solve problems that humans also do not know how to solve. However, this is not the future, because the future is in what little babies do. They don't use a physics engine to simulate the world. No, they learn a predictive model of the world, which maybe sometimes is wrong in many ways, but captures all kinds of important abstract high-level predictions which are really important to be successful”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

23. “So we have examples like that, and it's only in the beginning. This is just the tip of the iceberg, and I believe the next wave of AI. Is going to be all about that. So at the moment, the current wave of AI is about passive pattern observation and prediction. And that's what you have on your smartphone and what the major companies on the Pacific Rim are using to sell you ads, to do marketing. That's the current source of profit in AI. And that's only 1 or 2% of the world economy. Which is big enough to make these companies pretty much the most valuable companies in the world, but there's a much, much bigger Enough the economy going to be affected by the next wave, which is really about machines that shape the data through their own actions.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

24. “I do think so. We have a company called Nasense. Which has applied reinforcement running to little Audis. Lantu Park with Alata, the same principles were used of course, so these little Audis they are small, maybe like that, so much smaller than the real Audis, but they have all the sensors that you find in the real Audis, you find the cameras, the LIDAR sensors. They go up to 120 kilometers an hour if they want to. And they have pain sensors basically, and they don't want to bump against obstacles and other Audis. And so they must learn like little babies to park. Take the raw vision input and translate that into actions that lead to successful parking behavior, which is a rewarding thing. And yes, they learn that.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

25. “To learn by itself how to use the potentially relevant parts of the model network to solve new problems more quickly. And if it wants to, it can learn to ignore the M and sometimes it's a good idea to ignore the M because it's really bad. It's a bad predictor in this particular situation of life where the controller is currently trying to maximize reward. However, it can also learn to address and exploit some of the sub-programs that came about in the model network through compressing the data by predicting it. So it now has an opportunity to reuse that code, the algorithmic information in the model network, to reduce its own search space search that it can Of a new problem more quickly than without the model.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

26. “Now, how can a model of the world like that, a predictive model of the world, be used by the first guy, let's call it the controller and the model, the controller and the model? How can the model be used by the controller to efficiently select among these many possible futures? The naive way we had about 30 years ago was let's just use the model of the world as a stand-in, as a simulation of the world and millisecond by millisecond we plan the future and that means we have to roll it out really in detail and it will work only if the model is really good and it will still be inefficient because we have to look at all these possible futures and there are so many of them. So instead what we do now since 2015 in our CM systems controller model systems we give the controller the opportunity.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

27. “Gets in the video and the speech and whatever and is executing actions and is trying to maximize reward so there is no teacher who tells it what to do at which point in time. And then there's the other network which is Predicting what's going to happen if I do then, and that could be an LCM network, and it learns to look back all the way to make better predictions of the next time step. So essentially, although it's predicting only the”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

28. “And so a reinforcement learning system, which is trying to maximize its future expected reward and doesn't know yet which of these many possible futures should I select given this one single past? Facing problems that the LSM by itself cannot solve. So, the understim is good for coming up with a compact representation of the history so far, of the history of observations and actions so far. But now how do you plan in an efficient and good way among All these, how do you select one of these many possible action sequences that a reinforcement learning system has to consider to maximize reward in this unknown future? So again, we have this basic setup where you have Werner Recar network, which”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

29. “It's not clear what are the practical limits of the LSDM when it comes to looking back. Already in two thousand six, I think, we had examples where it not only looked back tens or thousands of steps, but really millions of steps. And Juan Perez Otis in my lab, I think was the first author of a paper where we really was in 2006 or something, had examples where it learned to look back for more than 10 million steps. For most problems of speech recognition, it's not necessary to look that far back. But there are examples where it does. Now, the looking back thing That's rather easy because there is only one past, but there are many possible futures.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

30. “So there you have already a problem of depth 50 because for each time step you have something like a virtual layer in the expanded unrolled version of this recurrent network which is doing the speech recognition. So these long time lags they translate into problem depth. And most problems in this world are such that you really have to look far back in time to understand what is the problem and to solve it.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

31. “What is now the depth? What is the importance of depth? Well, most problems in the real world are deep in the sense that the current input doesn't tell you all you need to know about the environment. So instead, you have to have a memory of what happened in the past. And often, important parts of that memory are dated. They are pretty old. So when you're doing speech recognition, for example, and somebody says 11. And that's about. Half a second or something like that, which means it's already 50 time steps. And another guy or the same guy says seven. So the ending is the same, Evan. But now the system has to see the distinction between 7 and 11. And the only way it can see the difference is it has to store that 50 steps ago there was an or an il, 11 or 7.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

32. “First of all, my first student ever Seb Hochreiter, who had fundamental insights already in his diploma thesis, then Felix Giers, who had additional important contributions, Alex Graves, a guy from Scotland, who is mostly responsible for this CTC algorithm, which is now often used to train the LSTM to do the speech recognition on all the Google Android phones and whatever, and theory and so on. These guys without these guys I would be nothing”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

33. “Since you mentioned the long short term memory and the LSTM, I have to mention the names of the brilliant students who made that.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

34. “You can use this model of the world to plan your future, and that's what yours have done since nineteen ninety, so the recurrent network, which is the controller, which is trying to maximize reward, can use this model of the network, of the world, this model network, Arthur Wild, this predictive model of the world, to plan ahead and say, let's not do this action sequence, let's do this action sequence instead, because it leads to more predicted reward. And whenever it's waking up, these little subnetworks that stand for itself, then it's thinking about itself, that it's thinking about itself. Exploring mentally the consequences of its own actions and And now you tell me what is still missing.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

35. “Deviations from the prototype. So it's compressing all the time with the stuff that frequently appears. There's one thing that appears all the time that is present all the time when the agent is interacting with its environment, which is the agent itself. So just for data compression reasons, it is extremely natural for this recurrent network to come up with little subnetworks that stand for the properties of the agents, the hand, the other actuators, and all the stuff that you need to better encode the data which is influenced by the actions of the agent. So there, just as a side effect of Data compression during problem solving, you have Internal self-models”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

36. “A separate recurrenial network which is just predicting what's happening if I do that and that. What will happen as a consequence of these actions that I'm executing and it's just trained on the long and long history of interactions with the world. So it becomes a predictive model of the world basically. And therefore also a compressor of the observations of the world because whatever you can predict, you don't have to store extra. Compression is a side effect of prediction. And how does this recur network compress? Well, it's inventing little sub-programs, little sub networks that stand for everything that frequently appears in the environment, like bottles and microphones and faces, maybe lots of faces in my environment, so I'm learning to create something like a prototype phase and a new phase comes along and all I have to encode are the”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

37. “We never have a procedure called consciousness in our machines. However, we get as side effects of what these machines are doing, things that seem to be closely related to what people call consciousness. So, for example, in 1990, we had simple systems which were basically recurrent networks and therefore universal computers trying to map incoming data into actions that lead to success. Maximizing reward in a given environment, always finding the charging station in time whenever the battery is low and negative signals are coming from the battery, always find the charging station in time without bumping against painful obstacles on the way. So complicated things, but very easily motivated. And then we give these little guys.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

38. “If you zoom back a little bit and you just look at general problem solving machine which is trying to solve arbitrary problems then this machine will figure out in the course of solving problems that it's good to be curious. So all of what I said just now about this pre wild curiosity and this will to invent new problems that the system doesn't know how to solve yet. Should be just a byproduct of the general search. However, Apparently, evolution has built it into us because it turned out to be so successful a pre wiring, a bias, a very successful exploratory bias that we are born with.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

39. “The second is the pure creativity that I would call what I just mentioned, I would call the applied creativity, like applied art, where somebody tells you, now make a nice picture of this pope and you will get money for that. Okay, so here is the artist and he makes a convincing picture of the Pope and the Pope likes it and gives him the money. And then there is the pure creativity, which is more like the power play and the artificial curiosity thing, where you have the freedom to select your own problem. Like a scientist who defines His own question to study. And so that is the pure creativity, if you will. As opposed to the applied creativity, which serves another.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

40. “We never have a program, a sub program that is called Creativity or something. It's just a side effect of what our problem solvers do. They are searching a space of problems or a space of canidates, of solution candidates, until they hopefully find a solution to a given problem. But then there are these two types of creativity, and both of them are now present in our machines. The first one has been around for a long time, which is human gives problem to machine. Machine tries to find a solution to that. And this has been happening for many decades, and for many decades, machines have found creative solutions to interesting problems where humans were not aware of these particularly creative solutions, but then appreciated that the machine found that.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

41. “More sophisticated versions of what I just described, they are what we have built in as well because evolution discovered that's a good way of exploring the unknown world and a guy who explores the unknown world has a higher chance of solving problems that he needs to survive in this world. On the other hand, Those guys who were too curious, they were weeded out as well. So you have to find this trade-off. Evolution found a certain trade-off. Apparently in our society there is a certain percentage of extremely explorative guys and it doesn't matter if they die because many of the others are more conservative. And so, yeah, it would be surprising to me if If that principle of artificial curiosity Wouldn't be present in almost exactly the same form here.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

42. “Yeah. So humans are curious and that means they behave like scientists, not only the official scientists, but even the babies behave like scientists and they play around with their toys to figure out how the world works and how it is responding to their actions. And that's how they learn about gravity and everything. And yeah, in 1990 we had the first systems like that. We just try to play around with the environment and come up with situations that go beyond what they knew at that time and then get a reward for creating these situations and then becoming more general problem solvers and being able to understand more of the world. So yeah, I think in principle that That curiosity strategy”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

43. “No, because that's the nature of power play that it's always trying to break its current generalization abilities? Cummings up with a new problem, which is beyond the current horizon. Just shifting the horizon of knowledge a little bit out there, breaking the existing rules such that the new thing becomes solvable but wasn't solvable by the old thing. So like adding a new axiom, like what G ⁇ del did when he came up with these new sentences, new theorems that didn't have a proof in the formal system, which means you can add them to the repertoire. Hoping that they are not going to damage the consistency of the whole thing.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

44. “And so by definition, power play is now trying always to search in this pair, in the set of pairs of problems and problems over modifications for a combination that minimize the time to achieve these criteria. So it's always trying to find the problem which is easiest to add to the repertoire.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

45. “Yes. So now let's look at the extreme case. Let's look at the set of all possible problems that you can formally describe, which is infinite, which should be the next problem. A scientist or a power play is going to solve. Easiest problem that goes beyond what you already know. It should be the simplest problem that the current problem solver that you have, which can already solve 100 problems. that he cannot solve yet by just generalizing? So it has to be new, so it has to require a modification of the problem solver such that the new problem solver can solve this new thing, but the old problem solver cannot do it. And in addition to that, we have to make sure that the problem solver doesn't forget any of the previous solutions.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

46. “And this additional Degree of freedom allows us to build curious systems that are like scientists in the sense that they not only try to solve, try to find answers to existing questions, know they are so free, but To pose their own questions. So, if you want to build an artificial scientist, we have to give it that freedom. And power play is exactly doing that.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

47. “Further? It's another very simple idea. So normally, what you do in computer science, you have Some guy who gives you a problem, and then there is a huge search space of potential solution candidates, and you somehow try them out and you have more less sophisticated ways of Moving around in that search space until you finally found a solution which you consider satisfactory. That's what most of computer science is about. Power play just goes one little step further and says, let's not only search for solutions to a given problem, but let's search to pairs of problems and their solutions, where the system itself has the opportunity to phrase its own problem. So we are looking certainly at pairs of problems and their solutions. Modifications of the problem solver that is supposed to generate a solution to that new problem.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

48. “Progress that is the depth of the insight that you have at that moment, that's the fun that you have, the scientific fun, the fun in that discovery. And we can build an artificial systems that do the same thing, that measure the depth of their insights as they are looking at the data which is coming in through their own experiments, and we give them a reward, an intrinsic reward in proportion to this depth of insight. And since they are trying to maximize The rewards they get, they are suddenly motivated to come up with new action sequences, with new experiments that have the property that the data that is coming in as a consequence are these experiments, has the property that they can learn something about, see a pattern in there which they hadn't seen yet before.”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

49. “Apples, my video of falling apples, I need so many data, so many pixels have to be stored, but then suddenly I realize, no, there is a very simple way of predicting the third frame in the video from the first tool, and maybe not every little detail can be predicted, but more or less most of these orange blobs that are coming down, they accelerate in the same way, which means that I can greatly compress the video. And the amount of compression”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source

50. “Matter how fast you accelerate and how fast you decelerate. And no matter what is the gravity in your local framework, light speed always looks the same. And from that, you can calculate all the consequences. So it's a very simple thing and it allows you to further compress all the observations because certainly there are hardly any deviations any longer that you can measure from the predictions of this new theory. So all of science is a history of compression progress. You never arrive immediately at the shortest explanation of the data, but you're making progress. Whenever you are making progress, you have an insight. You see, oh, first I needed so many bits of information to describe the data, to describe my falling”

    2018-12-23 · Lex Fridman Podcast · Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs · IDENTIFIED FROM THE TRANSCRIPT · source