Tweetovi

Blokirali ste korisnika/cu @walrus_md

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

  1. proslijedio/la je Tweet
    25. ruj 2019.

    Our new preprint on the ‘Neural dynamics of perceptual inference and its reversal during imagery’ with and is out now! We reveal feedforward and feedback dynamics of stimulus processing during perception and imagery. A thread 1/N

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    31. ožu 2019.

    Just finished this by - to write so well and so clearly about statistics is a rare skill. Reminds me of Doug Altman’s papers. All doctors should read it, whether they are researchers or not.

    Poništi
  3. proslijedio/la je Tweet
    15. ožu 2019.

    This. Don't waste time on domain specific tricks. Do work on abstract & general inductive biases like smoothness, relational structure, compositionality, in/equivariance, locality, stationarity, hierarchy, causality. Do think carefully & deeply about what is lacking in AI today.

    Poništi
  4. proslijedio/la je Tweet
    4. sij 2019.

    So every time we jump to the conclusion that evolution favors a specific human behavior without a BOATLOAD of truly cross-cultural proof, we're being patently ridiculous. We're supposed to prefer different things, behave differently, think differently. It's a feature, not a bug.

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    3. sij 2019.

    Question for neuro people: can you say concretely what you feel this style of analysis provides? I too think it has been important for my thinking, but I can't exactly say why that is or what really crucial advance it has offered

    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    31. srp 2018.

    Learn: 1. linear algebra well (e.g. matrix math) 2. calculus to an ok level (not advanced stuff) 3. prob. theory and stats to a good level 4. theoretical computer science basics 5. to code well in Python and ok in C++ Then read and implement ML papers and *play* with stuff! :-)

    Poništi
  7. proslijedio/la je Tweet

    If you had to teach some motivated, intelligent people to program (for the first time) in Python, what books / online resource would you use?! Any standouts?

    Poništi
  8. proslijedio/la je Tweet
    19. ožu 2018.

    Reasoning challenges for machine learning by Allen Institute. So so fascinating.

    Poništi
  9. proslijedio/la je Tweet
    17. ožu 2018.
    Poništi
  10. proslijedio/la je Tweet

    A beautiful, visual statistics textbook: "Seeing Theory – A visual introduction to probability and statistics.” I shared this a year ago, when it was already very cool. But the page now got a major upgrade by the authors and is now just incredibly cool!

    Poništi
  11. proslijedio/la je Tweet
    11. ožu 2018.

    Highly recommend this paper for practitioners of / those with an interest in Evolutionary Computation and Artificial Life. Overview of the many ways that evolution will "cheat" and hack its way around your oh-so-clever reward function!

    Poništi
  12. proslijedio/la je Tweet
    7. ožu 2018.

    The Lighthill debate (1973): Extraordinary video to understand the history of and how winter came. Many arguments on both sides are still valid today about approaches

    Poništi
  13. proslijedio/la je Tweet
    6. ožu 2018.

    Syntax-Directed Variational Autoencoder for Structured Data, a VAE for structured discrete objects where the grammar is known. blog post: paper: open review:

    Poništi
  14. proslijedio/la je Tweet
    4. ožu 2018.

    New blog post: Requests for research. A collection of interesting research directions around transfer learning and NLP

    Poništi
  15. proslijedio/la je Tweet
    28. velj 2018.
    Poništi
  16. proslijedio/la je Tweet
    25. sij 2018.

    AI2 Research Engineer shows you how to run models on free GPUs using Google’s Colab notebooks! Learn more:

    Poništi
  17. proslijedio/la je Tweet
    12. velj 2018.

    Great talk by Andy Clark on predictive processing as a model for integrating the many core information processing strategies we use in perception. also here's a podcast on the topic

    Poništi
  18. proslijedio/la je Tweet
    14. pro 2017.

    Deep Learning, Language and Cognition: Video of an introductory talk on computational linguistics for a broad audience—from hand-written rules to modern neural net models—by Christopher Manning () at IAS, Princeton.

    Poništi
  19. proslijedio/la je Tweet

    The difference between weak and strong non-ergodicities, based on Peters and Gell-Mann (2016) cc:

    Poništi
  20. proslijedio/la je Tweet
    29. sij 2018.

    Great news - the second version of the amazing deep learning tutorial has been launched! I did the first version and I learned a ton, highly recommended

    Prikaži ovu nit
    Poništi

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:

    ·