Leonard Bereska

@LeonardBereska

Trying to make sense of the world.

Heidelberg, Germany
Vrijeme pridruživanja: srpanj 2018.
0 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @LeonardBereska

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @LeonardBereska

  1. proslijedio/la je Tweet
    30. sij

    Intuition question. You draw two vectors from an n-dimensional isotropic Gaussian where n>>1. What is the typical angle between them?

    7 proslijeđenih tweetova 46 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    31. sij

    Wealth is the power to choose. Financial wealth is the power to choose how to spend money. Social wealth is the power to choose who to hang out with. Calendar wealth is the power to choose how to spend your time. Mental wealth is the power to choose your thoughts.

    1.571 proslijeđeni tweet 5.492 korisnika označavaju da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    30. sij

    OpenAI → PyTorch:

    We're standardizing OpenAI's deep learning framework on PyTorch to increase our research productivity at scale on GPUs (and have just released a PyTorch version of Spinning Up in Deep RL):
    35 proslijeđenih tweetova 419 korisnika označava da im se sviđa
    Poništi
  4. proslijedio/la je Tweet
    29. sij

    I realized recently that we were late in sharing data from a published paper. Mea culpa!! We have now assembled the data (~500K decisions from 29 mice) & made it available: . Paper is this:

    1 reply 10 proslijeđenih tweetova 47 korisnika označava da im se sviđa
    Poništi
  5. 6. sij

    1 korisnik označava da mu se sviđa
    Poništi
  6. proslijedio/la je Tweet
    31. pro 2019.

    A secret for discovering really great things: look for things that are said to have a "cult" following. Sometimes this is literally true, but other times it's because the thing is genuinely great, but not everyone knows yet.

    277 proslijeđenih tweetova 2.235 korisnika označava da im se sviđa
    Poništi
  7. proslijedio/la je Tweet
    8. tra 2019.

    When making plans, think big. When making progress, think small.

    38 replies 2.727 proslijeđenih tweetova 8.145 korisnika označava da im se sviđa
    Poništi
  8. proslijedio/la je Tweet
    3. pro 2019.

    The definition of disruption

    2 proslijeđena tweeta 2 korisnika označavaju da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    27. pro 2019.

    These would be road tunnels for zero emissions vehicles only — no toxic fumes is the key. Really, just an underground road, but limited to EVs (from all auto companies). This is not in place of other solutions, eg light rail, but supplemental to them.

    2.916 proslijeđenih tweetova 66.225 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    27. pro 2019.

    What is the most important brain area to study in order to understand intelligence?

    16 replies 28 proslijeđenih tweetova 24 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    27. pro 2019.

    I am increasingly bothered by a question I keep encountering regarding China’s repression of the Uighurs: “Why aren’t Muslim-majority countries condemning it?” There are several things that bother me about this question.

    437 proslijeđenih tweetova 1.018 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    28. pro 2019.

    Reformer: The Efficient Transformer They present techniques to reduce the time and memory complexity of Transformer, allowing batches of very long sequences (64K) to fit on one GPU. Should pave way for Transformer to be really impactful beyond NLP domain

    5 replies 103 proslijeđena tweeta 412 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    28. pro 2019.

    I just published Why Time is so Annoying

    1 proslijeđeni tweet
    Poništi
  14. proslijedio/la je Tweet
    27. pro 2019.

    I think we tend to overestimate the importance of reciprocity -- a transactional mindset -- and underestimate the power of kindness. Even the smallest acts of kindness can change lives. None of the most important things in life are transactional.

    15 replies 168 proslijeđenih tweetova 813 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    29. pro 2019.

    Generalisation is about the simplicity of the model class that is compatible with all observed and experimental(interventional) data. Simplicity doesn't mean a small number of parameters. It means that we need a small number of bits to describe the model 2/5

    8 proslijeđenih tweetova 70 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    26. pro 2019.

    is one of the few intellectuals driven towards mending the political and social divides within society. I respect that he is willing to engage those he disagrees with while maintaining civility in times of conflict.

    4 proslijeđena tweeta 61 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    26. pro 2019.

    Bayesian methods are *especially* compelling for deep neural networks. The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. This difference will be greatest for underspecified models like DNNs. 1/18

    Controversial opinion: Bayesian NNs make no sense. You only want to use Bayes rule if you have a reasonable prior of what the parameters should be. Nobody knows what is encoded by any prior over the weights of a NN. So why would we use such a prior? 1/4
    Prikaži ovu nit
    14 replies 434 proslijeđena tweeta 1.674 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    25. pro 2019.

    Rephrasing with my own words: DL is a collection of tools to build complex modular differentiable functions. These tools are devoid of meaning, it is pointless to discuss what DL can or cannot do. What gives meaning to it is how it is trained and how the data is fed to it

    14 replies 90 proslijeđenih tweetova 466 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    24. pro 2019.

    Two neuroscience papers for the Christmas holidays: 1. 'Could a neuroscientist understand a microprocessor' by and // 2. 'Physical Principles for scalable neural recording' by et al. //

    1 proslijeđeni tweet 9 korisnika označava da im se sviđa
    Poništi
  20. proslijedio/la je Tweet
    25. pro 2019.

    ICYMI: The brain may be using its elegant “grid cell” solution for navigating through space to help us map out memories and abstract concepts.

    1 reply 43 proslijeđena tweeta 117 korisnika označava da im se sviđa
    Poništi

@LeonardBereska još nije objavio nijedan Tweet.

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·