YouSaid · the spoken record

Risto Miikkulainen

lines on the record
113
first
2021-04-19
most recent
2021-04-19
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. “Counterintuitive. So, yeah, and biologically, it's like, you know, you have a limited amount of time. What can you do with it that matters? You have done your exploration, you committed.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  2. “There is a reason for this life arc that younger folks are more fearless in many ways. That's part of the exploration. They are the individuals who think, hmm, I wonder what's over those mountains. What if I go really far in that ocean? What would I find? I mean, older folks don't necessarily think that way, but younger do. And it's kind of...”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  3. “So from an individual's perspective, you've got to think of a bigger picture that this is a huge engine that is innovative. And these elements are all part of it, potentially innovations on their own and also as raw material perhaps or stepping stones for other things that could come after.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  4. “In evolution, there is meaning. Everything is a potential direction. Everything is a potential stepping stone. Not all of them are going to work out. Some of them are foundations for further improvement. And even those that are perhaps going to die out where potential lineages, potential solutions. In biology, we see a lot of species die off naturally, and like the dinosaurs. I mean, they have a really good solution for a while, but then it didn't turn out to be not such a good solution in the long term when there's an environmental change. You have to have diversity, some other solutions become better. It doesn't mean that there was an attempt. It didn't quite work out or last, but there are still dinosaurs and mountainous, at least they're relatives. And they may one day again be useful. Who knows?”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  5. “And then beyond that, after that exploration, you actually can focus and build a career. And even there, it's multiple times. But I think the diversity exploration is fundamental to having a successful career, as is concentration and spending an effort where it matters. But you're in a better position to make the choice when you have done your homework.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  6. “Now, also at some point then, when you have this diversity and you have this experiences exploration, you may want to find something that you can't stay away from. Like for us, it was computers. It was AI. I just have to do it. And then it will take decades maybe and you are pursuing it because you figured out that this is really exciting and you can bring in your experiences. And there's nothing wrong with that either. But you asked, what's the advice for young people? That's the expiration part.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  7. “Yeah, so you don't have to explore hundred things, but maybe a few topics where you can take a deep enough time dive that you gain an understanding. You yourself have to decide at some point that this is deep enough. And I've obtained what I can from this topic. And now it's time to move on. And that might take years. People sometimes switch careers and they may stay on some career for decade and switch to another one. You can do it. You're not pretty determined to stay where you are. But, you know, in order to achieve something, you know, 10,000 hours, you need 10,000 hours to become an expert on something. So you don't have to become an expert, but even develop an understanding and gain the experience that you can use later. You probably have to spend, like I said, it's not easy. You got to spend some effort on it.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  8. “Yes, definitely explore. Exploration And individuals take classes in music, history, philosophy You know, math, engineering, see connections between them, travel, you know, learn a language. I mean, all this diversity is fascinating and we have it at our fingertips today. It's possible. You have to make a bit of an effort because it's not easy. But the rewards are wonderful.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  9. “So you have encoded the fundamentals of your world, and then you make changes to those fundamentals you get further away. So that's probably what's happening in these systems of emergence, that the fundamentals are there. And when you follow those fundamentals, you get into points, and some of those are actually interesting and useful. Now, even in that robotic walker simulation, there was a large set of garbage, but among them there were some of these gems. And then those are the ones that somehow you have to outside recognize and make useful. But this kind of productive systems, if you code them the right kind of principles, I think that encode the structure of the domain, then you will get to these solutions and these discoveries.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  10. “Gestani and Joe Lehman did this one study where they actually tried to evolve walking behavior on robots. And that's actually we talked about earlier where your robot actually failed in all kinds of ways and eventually discovered something that was a very efficient walk. And it was because they rewarded things that were different that you were able to discover something. And I think that this is crucial because in order to be really different from what you already have, you have to utilize what is there in the domain to create something really different.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  11. “And that is something we talked about earlier that evolution competition is very impatient. We have a goal we wanted right away This biology has a lot of time and deep time and weak pressure and large populations. One great example of this is the novelty search. So evolutionary computation where you don't actually specify a fitness call, something that is your actual thing that you want, but you just reward solutions that are different. What you've seen before Nothing else And you know what? You actually discover things that are interesting and useful that way.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  12. “Is along the same lines. We have simple representations, DNA. If you really think of it, it's not that complex. It's a long sequence of them. There's lots of them, but it's a very simple representation. And similar evolutionary computation, whatever string or tree representation we have and the operations, you know, the amount of code that's required to manipulate those is really, really little. And of course, Game Alive even less. how complexity emerges from such simple principles. That's absolutely fascinating. The challenge is to be able to control it and guide it and direct it so that it becomes useful. And I game of life is fascinating to look at and evolution, all the forms that come out is fascinating. But can we actually make it useful for us?”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  13. “Yeah, yeah. And similarly, evolution does not have a goal. It is responding to the current situation. And so survival then creates more complexity. And therefore, we have something that we perceive as progress, but that's not what evolution is inherently set to do. And yeah, that's really fascinating how a simple set of rules, a simple mappings can such simple mappings complexity can emerge. So it's a question of emergence and self-organization. And the game of life is one of the simplest ones and very visual and therefore it drives home the point that it's possible that non-linear interactions and this kinds of complexity can emerge from them. And biology and evolution.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  14. “And generally, we can deal with the world even if we don't understand all the details. We can use computers. Even though most of us don't know all the structures that are underneath or drive a car, I mean, there are many components, especially new cars that you don't quite fully know. But you have the interface, you have an abstraction of it that allows you to operate it and utilize it. And I think that's perfectly adequate. And we can build on it. And AI can be play a similar role.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  15. “Yes, and it's fascinating, like I said before, that we can keep up somehow biologically. We are bewildered to a point where we can keep up with this meme evolution. Literature, you know, internet. We understand DNA and we understand fundamental particles. We didn't start that way. I mean, thousand years ago, and we haven't evolved biologically very much, but somehow our minds are able to extend. And therefore, for AI can be seen also as one such step that we created and it's our tool. And it's part of that meme evolution that we created, even if our biological evolution does not progress as fast.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  16. “And I think that artificial life is a great tool to understand life. And there are questions like sustainability, species. We're losing species. How bad is it? Is it natural? Is there a tipping point? And where are we going? I mean, like the hyena evolution, we may have understood that there's a pivotal point in their evolution. They discovered cooperation and coordination artificial simulations can identify that. And maybe encourage things like that. And also societies can be seen as a form of life itself. I mean, we're not talking about biological evolution of societies. Maybe some of the same phenomena emerge in that domain. And having artificial life simulations and understanding could help. Us build better societies.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  17. “Different levels of definition and goals there. I mean, at some level, artificial life can be considered multi-agent systems that build a society that, again, achieves a goal. And it might be robots that go into a building and clean it up or after earthquake or something. You can think of that as an artificial light problem in some sense. Or you can really think of it artificial life as a simulation of life and a tool to understand what life is and how life evolved in Earth. And like I said, in the Artificial Life Conference, there are branches of that conference sessions of people who really worry about molecular designs and the start of life. Like I said, primordial soup where eventually you get something self-replicating. And they're really trying to build that. So it's a whole range of topics.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  18. “And we've seen society change over time quite a bit along those rides. There were rules in society that we don't believe are fair anymore, even though they were considered proper behavior before. So things are changing. And I think that in that sense, I think it's a good idea to be able to tolerate some of that cheating because eventually we might turn into something better.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  19. “Diversity is the bread and butter. I mean, if you're running a foundation, you see diversity is the one fundamental thing you have to have. And absolutely also, it's not always good diversity. It may be something that can be destructive. We had in this hyena simulations we have hyenas that just are suicidal. They just run and get killed. But they form the basis of those who actually are really fast. Stop before they get killed and eventually turn into this mob. So there might be something useful there if it's recombined with something else. So, I think that as long as we can tolerate some of that, it may turn into something better. You may change the rules because it's so much more efficient to do something that was actually against the rules before.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  20. “But if you have trust, you also have opportunity for cheaters and liars. And I don't think that's ever going to go away. There will be hopefully a minority so that they don't get in the way. And we studied and it's high in assimilations, like what the proportion needs to be before it's no longer functional. And you can point out that you can tolerate a few cheaters and a few liars and the society can still function. And that's probably going to happen when we build these systems that autonomously learn. The really successful ones are honest because that's the best way of getting things done. But there probably are also intelligent agents that find that they can achieve their goals by bending the rules of cheating.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  21. “Your point about lying is very interesting. Even in Heine societies, for instance, when a number of these hyenas band together and they take a risk and steal the kill, they're always hyenas that hang back and don't participate in that risky behavior, but they walk in later and join the party after the kill. And there are even some that may be ineffective and cause others to have harm so and like I said, even bacteria cheat. And we see in biology, there's always some element, an opportunity. If you have a, I think that this is because if you have a society in order for society to be effective, you have to have this cooperation and you have to have trust. And if you have enough of agents who are able to trust each other, you can achieve a lot more.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  22. “Definitely hope that we can get there. One, I think, important perspective is that we are building AI to help us. It is a tool like cars or language Communication, AI will help us be more productive and And therefore, we are always in a position of limiting what it can or cannot do”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  23. “They may be saying things just to make us feel good or get us to do what we want, whatever, not turn them off or something. But so we would have to understand their internal representations much better to really make sure that that translation is political. But it can be useful. And I think it's possible to do that. There are examples where visualizations are automatically created so that we can look into the system. Language is not that far from it. I mean, it is a way of communicating and logging what you're doing in some interpretable way. I think a fascinating topic, yeah, to do that.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  24. “We see that in even very low level, like bacterial level evolution, there are cheaters. And who's to say that what they say is actually what they think? But that's why I'm saying that there would have to be some common goal so that we can evaluate whether that communication is at least useful.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  25. “We can certainly try, and if it's an evolution competition system, for instance, you reward those solutions that are actually functional, that communication makes sense, it allows us together, again, achieve common goals. I think it's possible. But even from that paper that you mentioned, the anecdotes, it's quite likely also that the agents learn to. And fake and do all kinds of things like that.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  26. “Yes, and if we do that enough, we have Perhaps an idea what an alien language might be like, the space of where those languages can be. Because we can set up their environment differently. It doesn't need to be gravity. You can have all kinds of societies can be different. They may have no predators. They may have everybody, all kinds of situations, and then see what the space possibly is where those languages are and what the difficulties are. That'd be really good actually to do that before the aliens come here.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  27. “So, one, and again, being a computational scientist and trying to build intelligent agents, what I would like to do is have a simulation where the agents actually evolve communication, not just communication. We've done that people have done that many times. They communicate, they signal, and so on, but actually develop a language. And language means grammar. It means all these social structures and on top of that grammatical structures. And we do it under various conditions and actually try to identify what conditions are necessary for it to come out. And then we can start asking that kind of questions. Are those languages that emerge in those different simulating environments, are they understandable to us? Can we somehow make a translation? We can make it a concrete question.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  28. “Yes, that's, I do think about that. I mean, I think a lot of people who are in computing, and AI in particular, they got into it because they were fascinated with science fiction. And all of these options, I mean, Star Trek generated all kinds of devices that we have now they envision first. And it's a great motivator to think about things like that.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  29. “Language good at being the original proto language. We don't quite know, but the language is more fundamental than the medium in which it's communicated. And I think that it comes from those representations. Now, in current world, they are so strongly integrated, it's really hard to say which one is fundamental. You look at the brain structures. even visual cortex, which is supposed to be very much just vision. Well, if you are thinking of semantic concepts, if you're thinking of language visual cortex lights up. Still useful, even for language computations. So there are common structures underlying them. So utilize what you need. And when you are understanding a scene, you're understanding relationships. Well, that's not so far from understanding relationships between words and concepts. So I think that that's how they integrate it.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  30. “Yeah, that's a very good guess. We are visual animals, though. A lot of the brain is dedicated to vision and also when we think about various abstract concepts, we usually reduce that division and images. And that's, you know, we go to a whiteboard, you draw pictures of very abstract concepts. So we tend to resort to that quite a bit. And that's a fundamental representation. possible that it predated language even i mean animals a lot of they don't talk but they certainly do have vision uh and and language is interesting development in um from from mastication from eating you develop an organ that actually can produce sound and manipulate them Maybe that was an accent. Maybe that was something that was available. And then allowed us to do the communication. Or maybe it was gestures.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  31. “Yeah, well earlier we talked about the social structures and that may be what's underlying the language. That's the more fundamental part. And then language has been added on top of that.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  32. “But having both together and then learning A semantic understanding of what is happening. I think that will be the next step in the next few years”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  33. “Visual world, the 3D, what are the objects doing and predicting what will happen, the relationships? That's what makes vision difficult. And language, obviously, it's what is being said, what the meaning is. And the meaning doesn't stop at who did what to whom. There are goals and plans and themes. And eventually you have to understand the entire human society and history in order to understand a sentence very much fully. There are plenty of examples of those kind of short sentences when you bring in all the world knowledge to understand it. And that's the big challenge. Now, we are far from that, but even just bringing in the visual world together with the sentence will give you already a lot deeper understanding of what's happening. And I think that that's where we're going very soon. I mean, we've had ImageNet for a long time, and now we have all these text collections.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  34. “Yeah, absolutely the ladder. Learning both at the same time, I think, is a fascinating direction in the future. So you have data sets where there's visual component as well as verbal descriptions, for instance. And that way you can learn a deeper representation, a more useful representation for both. But it's still an interesting question of which one is easier. I mean, recognizing objects or even understanding sentences, that's relatively possible. But where it becomes where the challenges are is to understand the world.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  35. “Yeah, and also it turns out, and that's again a surprise that Elliot found, was that those tasks don't have to be very related. You know, you can learn to do better vision by learning language or better language by learning about DNA structure. Somehow the world...”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  36. “I think it's fundamentally how biological intelligence works as well. You don't build a representation just for one task. You try to build something that's general, not only so that you can do better in one task or multiple tasks, but also future tasks and future challenges. So you learn the structure of the world, and that helps you in all kinds of future challenges.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  37. “Yes, and people do that all the time. I mean, you use knowledge of domains that you know in new domains. And certainly neural networks can do that. When your evolution comes in is that what's the best way to combine these tasks? Now there's architectural design that allow you to decide where and how the embeddings, the internal representations are combined and how much you combine them. And there's quite a bit of research on that. My team Elliot Mayerson's worked on that in particular, like what is a good internal representation that supports multiple tasks?”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  38. “Yes, it's a very good problem for neurovolution. And the reason is that when you have multiple tasks, they support each other. So let's say you're learning to classify x-ray images to different pathologies. So you have one task is to classify this disease and another one this disease, another one, this one. And when you're learning from one disease, that forces certain kinds of internal representations on embeddings and they can serve as a helpful starting point for the other tasks. So, you are combining the wisdom of multiple tasks into these representations. And it turns out that you can do better in each of these tasks when you're learning simultaneously other tasks than you would by one task alone.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  39. “And this kind of coevolution, that's competitive coevolution, it's a fascinating topic because there's a promise or possibility that you will discover something new that you don't already know. You didn't build it in. It came from this arms race. It's hard to keep the arms race going. It's hard to have RIDS enough simulation that supports all of these complex behaviors. But at least for several steps, we've already seen it in the spread of the prey scenario, yeah.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  40. “And initially, you know, hyenas just tried to hunt them, and when they actually stumbled upon the zebra, they ate it and were happy. And then the zebras learn to escape. And the hyenas learn to team up. And actually two of them approach in different directions. And now the zebras then next step, they generated a behavior where they split in different directions just like actually gazelles do when they are being hunted. They confuse the predator by going in different directions. That emerged. And then more hyenas joined and kind of circled them. And then when they circled them, they could actually herd the zebras together and eat multiple zebras. So there was like an arms race of predators and prey. And they gradually developed more complex behaviors, some of which we actually do see in nature.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  41. “Yeah, yeah. Oh, totally, yeah, yeah, yeah. And we actually simulated also that Bret the Prey and it was interesting what happened there with Badmin Radic Bolland did this and Gay Holkamp was a zoologist. So we had, again, We had simulated hyenas simulated zebras.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  42. “Yeah, the neural networks that you are creating, interacting the world, and learning from these sequences of interactions, perhaps communication with others”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  43. “Yeah, there are proteins like that. Esteban Real and Cochlea, for instance, I worked on evolving a smaller network and then systematically expanding it to a larger one. Your elements are already there and scaling it up will just give you more power. So, again, evolution gives you that starting point. And then there's a mechanism that gives you the final result and a very powerful approach. But you could also simulate the actual growth process. And I said before, evolving a starting point and then evolving or training the network. There's not that much work that's been done on that yet. We need some kind of a simulation environment so the interactions at will. The supervised environment doesn't really, it's not as easily usable here.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  44. “You have to train it. I mean, you have to actually try it out, and that's currently very expensive, right? I mean, deep learning networks may take days to train. Well, imagine having a population of 100 and have to run it for 100 generations. It's not yet quite feasible computationally. It will be, but also there's a large carbon footprint and all that. I mean, we are using a lot of computation for doing it. Intelligent methods and intelligent, I mean, we have to do some science in order to figure out what a right representations are and right operators are and how do we evaluate them without having to fully train them. And that is where the current research is and we're making progress on all those fronts. So yes, there are certain architectures demo amenable to that approach, but also I think we can create our own architecture and all representations that are.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  45. “Around the network design that humans had come up with, Orioviniels and others. But that's starting from a point that humans have produced. But we could do something more general. It doesn't have to be that kind of network. The hard part is a couple of challenges. One of them is to define the search base. What are your elements and how you put them together? And the space is just really, really big. So you have to somehow constrain it and have some hunch of what will work because otherwise everything is possible. And another challenge is that in order to evaluate how good your design is.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  46. “I think we can. And most of the work up to now is taking architects as already exist, that humans have designed and tried to optimize them further. And you can totally do that. A few years ago, we did an experiment. We took a winner of the image captioning competition. And the architecture and just broken into pieces and took the pieces, and that was our search base. See if you can do better.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  47. “Starting point and then have a learning algorithm that will construct the final product. And this interaction of intelligent evolution that has produced a good starting point for the specific purpose of learning from it with the interaction with the environment, that can be a really powerful mechanism for constructing brains and constructing behaviors.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  48. “Of the design of deep learning experiments could be optimized that way. So that's an interaction between two mechanisms. But there's also, when we get more into cognitive science and the topics that we've been talking about, you could have learning mechanisms at two level timescales. So you do have an evolution that gives you baby neural networks that then learn during their lifetime. And you have this interaction of two timescales. And I think that can potentially be really powerful. Now, in biology, we are not born with all our faculties. We have to learn. We have a developmental period in humans. It's really long. And most animals have something. And probably the reason is that evolution and DNA is not detailed enough or plentiful enough to describe them. We can't describe how to set the brain up, but we can evolution can decide on a”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  49. “Between known situations. So you want to have a neural network in such a task, even if you don't have the supervised targets. So that's the reason and that's a solution. And also more recently now when we have all this deep learning literature, it turns out that we can use evolution to optimize many aspects of those designs. The deep learning architectures have become so complex that there's little hope for us little humans to understand their complexity and what actually makes a good design. And now we can use evolution to give that design for you. And it might mean optimizing hyperparameters like the depth of layers and so on or the topology of the network. How many layers, how they connect it, but also other aspects, like what activation functions you use where in the network during the learning process or what loss function you use. You generate that. Even data augmentation, all the different aspects.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source

  50. “Yeah, neuroevolution is a combination of neural networks and evolution computation in many different forms, but the early versions were simply using evolution the way as a way to construct the neural network. Instead of, say, stochastic gradient descent or backpropagation, because evolution can evolve these parameters, weight values in a neural network, just like any other string of numbers, you can do that. And that's useful because some cases you don't have those targets that you need to backpropagate from. And it might be an agent that's running a maze or a robot playing a game or something. Again, you don't know what the right answer is. You don't have backup, but this way you can still evolve a neural net. And neural networks are really good at these tasks because they recognize patterns and they generalize.”

    2021-04-19 · Lex Fridman Podcast · #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation · IDENTIFIED FROM THE TRANSCRIPT · source