46 thoughts on “13. Learning: Genetic Algorithms”

  1. There's an incomplete subtitle line here:
    13:59: "So we'll just truncate anything like that at 0"

    Translations are locked so I can't correct it. MIT pls fix

  2. The creationist based inaccurate interjections are very unprofessional and unfortunate. I'm not saying he's not covering the subject effectively, but he is generalizing in unsubstantiated ways in fields which inspired this topic for no positive reason.

  3. This is very helpful for me. But I have a question. What is Pc ? And how much is it. I watch the screen ,find the rank probability is 0.05. (1-Pc) equals 0.95,so 0.95^39 always more than 0.05,if Pc equals 0.05. I think I need some help.

  4. Best greetings from Germany !

    I'm a high school student in Germany and
    I think AI and these algorithms are very useful and interesting.

    In Germany the most people don't care about it today, but our politians try to move the people in these for them new direction.
    In the direction of self learning machines, machines who do the most job of us.
    For example helping doctors while they run diagonstics on their patients or do operational things… 😉

    Maybe It's a huge thinking forward, in the future.

  5. I utterly love these MIT Lectures and have been watching them for the past couple days non stop…. However the way this guy breaths in this one is almost making me want to shut this the fuck off. I REALLY need to hear this for an evolution simulator that I am working on but I almost can't take this dude fucking breathing like hes doing some strenuous workout just writting on a fucking chalk board and talking. I wanna tell him to sit down and take a break, dont push yourself there man, you are giving a lecture not running a marathon. Damn its driving me fucking crazy.

  6. Kinda disappointed by this lecture:
    1. The lecturer said mutation is essentially hill-climbing which I agree. But he didn't explain what cross-over is and why it is important. At least he should have stressed that it was still a mystery.
    2. Crediting the artificial creature program for its "rich solution space" rather than genetic algorithm without even justifying it is kinda irresponsible. Because that's a bold and non-trivial claim.
    3. Yes, GA requires fine-tuning of parameters, in machine learning we have feature engineering which is doing the same thing. Isn't it naive to thinking an algorithm as general as GA would work well on all problem instances without feature engineering? There is no universal problem solving algorithm that works well for all problem instances (no free lunch theorem)

    Overall, I have the impression that the lecturer has prejudice against GA.

  7. actually, this video is almost 3 years out of date. OpenAI's neuroevolution algorithm (run in parallel among 2000 cores) was able to solve Atari games faster than Google's DeepMind, which uses Reinforcement Learning and backpropagation or something. but basically, if you have a whole company's resources to cores, then neuroevolution is the fastest way to teach a.i. to play video games, because it's much more parallelizeable.

  8. what a dry and miserable class, they never laugh or react to anything he says and hes funny, and interesting to listen to. spoiled bratts

  9. I watched your lecture with great interest. I'm teaching myself Python by coding a GA. Often, when selection and reproduction are discussed, the biological model of two parents are combined into one offspring. I have a different idea. Say you have a starting population of 200. You apply your fitness function to score each member and then the grim reaper function to kill the bottom half in terms of fitness. You have a population of 100 members. Why not combine each member with every other member? (think nested loops). 100 * 100 (crossover) produces 10,000 new members. apply a mutation function randomly against the population and against each cell in the DNA string. Then reduce the population by 99% by fitness back to the original level of 100. In effect producing the next generation from the top 1 percent of the current generation. Have you considered such an approach? Can you give me your opinion? Thank you!

  10. Brilliant stuff..!! Sparsely, you come across such content on the internet / youtube that is so sophisticated in concept & enriched by relevant detailing and live examples. Fulfilling..!!!
    Thanks @MIT OpenCourseWare, for sharing it..

  11. this guy is so boring…. and he chooses to present the material in a very non intuitive way

  12. Intellectually stimulating, the educator was very effective at cutting through large swaths of information summarily articulating them in ways I believe suitable for the students present. Very complex subject matter made easy and enlightening.

  13. To the guy in the black trench with his sneaker on the railing, you are hella attractive.

    He asks a poorly-thought-out question at 13:50 and makes skeptical faces throughout the rest of the lecture. Fitnesses can't be negative. Not with absolute fitness, and not if you're standardizing fitness as (number of offspring produced by genotype x)/(number of offspring of the fittest genotype). The lowest you can go in either case is zero. Didn't survive = 0, no reproduction = 0.

  14. what about the parameters in the video?I have tried many times ,but can't find the best parameters,please help! thanks

Leave a Reply

Your email address will not be published. Required fields are marked *