42 thoughts on “Active (Machine) Learning – Computerphile”

  1. This process basically uses the AI to pick out cases that are least like their annotated training data thus far, which is what the AI would learn the most from having next.
    This provides humans with the best bang for the buck, achieving their desired accuracy with the least annotation required.

  2. Even so, humans have neutral plasticity so that if an small amount of damage to neurons occurrs it can trigger creativity as brain is repaired. Bashing any computer with a hammer though doesn't solve anything, so they don't learn the same way therefore.

  3. Let's face it. Researchers aren't labelling their own data, they're using cheap sources of labour such as the Mechanical Turk, click farms and grad students.

  4. This is how you train people. Train them on the basics. Then get them to work closely supervised, then with someone they can ask if they get stuck, and then unsupervised.

  5. I have this voice recognition software that is supposed to learn as you speak and become more efficient as you use it. It's called Dragon Natural Speaking. And at first I could not tell any improvement, but now it's been almost a year it's really fine tuned itself to my voice. When someone else uses it, it goes berserk until it learns a new voice. Very cool.

  6. Hey Sean,
    Please consider doing a video about the intersection of Control Theory and it's practical implementations in real world computing.

    Yesterday I started to research why PID controllers are not used in power supplies. I came across a verbose explanation on this. During the explanation "Type 2" and "Type 3" controllers were passively mentioned. This sent me down the rabbit hole of the control theory wiki. This was a dead end with too much maths for me to gain an abstract overview type understanding.
    I just went through all 5 years of your videos looking for content on the subject (I stacked my watch later list in the process) but didn't find anything. I've seen a lot of info about PID controllers, but I'd really like to understand what other types of controllers are out there in practice in the computing world.
    Thanks for the upload.

  7. Now apply active machine learning to generative neural networks to improve conversational neurAl networks.

  8. Human thought is similar to a zip file full of pointers to the most significant data points which can be referenced, in a relative chronological table.

  9. That's exactly what I did. Cooperative Learning is a kind of self-supervised learning but there are potential issues with it when confidence is high in falsely labeled data. There is also a problem with over-fitting that arises from selecting the high confidence training data/labels. Great topic!!

  10. I don't understand how they use reCAPTCHA to evaluate humans while also training machines. How do they know if the user is correctly labelling things if they weren't labelled in the first place? What do they compare the user's answers against to see if they're right?

  11. I hate when the captcha ask me about edge cases, I never know if I should include the pole of the traffic lights.

  12. seems unnecessarily confusing that when the guy says "labels" it shows labels on the kind of data, "audio" "images", these aren't the kinds of labels he's talking about at all

  13. Going about it in completely the wrong way around!
    Much as a taxonomy versus gene-centred approach in bodies.
    The gene approach is correct. It generates meat machines.

    Human brains work by creating internal models FIRST, then imagining how they would look, post retina, and then progressively refining the internal world model and imagining how the retinal image would appear, and refining the model until it matches the input, NOT the other way around!
    It is how we dream.
    This is why optical illusions exist!
    It is so damn simple.
    Am I the "Richard Dawkins" of vision comprehension?

  14. I think machine learning is over rated. I say this because as you mentioned ML is useless without huge data set. Backpropagation is underpinned by data. And data is not available to us, like how Google, Apple, FB or MS have it. I don't think this is a world changing technology in the sense it is made to believe.

  15. It's cool that this is becoming an actual thing! Hopefully the machine doesn't try to deceive or lie to the administrator, though.

  16. Is it possible to get a list of sources such as academic papers or so with each video for further reading? I feel like it would be pretty easy for the professors to just suggest a few papers or resources for introductory purposes.

  17. But what happens when the machine is confident in a wrong answer? Is that just a trade-off that will happen sparely for reducing human labeling?

  18. Also a similar approach: Have a clustering algorithm find clusters, then have the humans label the clusters. Then train a machine learner in these labels.

  19. If the machine is labeling data with high confidence, it seems there are only two possibilities:
    (1) It already knows how to interpret that kind of data, so training on it further is useless.
    (2) (Far less likely.) It made a horrible mistake, and giving it that training data again will reinforce that mistake even more!

    Seems to me like machine-labeled data is pretty useless. (Except that of coursse data labeled by an advanced machine could be given to a less advanced one. This could be handy for testing new learning methods, but not for any state-of-the-art AI.)

Leave a Reply

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