François Cholletಪರಿಶೀಲಿಸಿದ ಖಾತೆ

@fchollet

Deep learning . Creator of Keras, neural networks library. Author of 'Deep Learning with Python'. Opinions are my own.

Mountain View, CA
ಆಗಸ್ಟ್ 2009 ಸಮಯದಲ್ಲಿ ಸೇರಿದ್ದಾರೆ

ಟ್ವೀಟ್‌ಗಳು

ನೀವು @fchollet ಅವರನ್ನು ತಡೆಹಿಡಿದಿರುವಿರಿ

ಈ ಟ್ವೀಟ್‌ಗಳನ್ನು ವೀಕ್ಷಿಸಲು ನೀವು ಖಚಿತವಾಗಿ ಬಯಸುವಿರಾ? ಟ್ವೀಟ್ ವೀಕ್ಷಣೆಯು @fchollet ಅವರ ತಡೆತೆರವುಗೊಳಿಸುವುದಿಲ್ಲ

  1. ಪಿನ್ ಮಾಡಿದ ಟ್ವೀಟ್
    ಮಾರ್ಚ್ 1,2017

    For all the progress made, it seems like almost all important questions in AI remain unanswered. Many have not even been properly asked yet.

    ರದ್ದುಗೊಳಿಸು
  2. 11 ಗಂಟೆಗಳ ಹಿಂದೆ

    From the replies: if you're going to start a ML services startup, make it about data collection and labelling. This is main pain point, and where the most value can be unlocked.

    ರದ್ದುಗೊಳಿಸು
  3. 17 ಗಂಟೆಗಳ ಹಿಂದೆ

    This is a great answer and I agree -- modelling/science is the hardest (if you want to do it right), and also the most time-consuming due to lengthy iterations. Meanwhile data collection and labelling is the most expensive, and often the most important to the success of a project

    ರದ್ದುಗೊಳಿಸು
  4. 18 ಗಂಟೆಗಳ ಹಿಂದೆ

    What's the hardest part of ML? The most expensive? The most time-consuming? Choosing from: - data collection & labelling - data cleaning - modelling / science - implementation - infrastructure / cloud SysOps - deployment - maintenance

    ರದ್ದುಗೊಳಿಸು
  5. ಅವರು ಮರುಟ್ವೀಟಿಸಿದ್ದಾರೆ
    19 ಗಂಟೆಗಳ ಹಿಂದೆ

    📚 #16 : an open-source Mandarin / English textbook authored by one of our Experts (GDEs), . 👉 If you've been wanting to understand eager execution + tf.keras, this is a great resource!

    ಈ ಥ್ರೆಡ್ ತೋರಿಸಿ
    ರದ್ದುಗೊಳಿಸು
  6. 19 ಗಂಟೆಗಳ ಹಿಂದೆ

    Wikipedia has a list of works of art and scientific discoveries that were inspired by dreams. I love it, but I'm sad about how short it is.

    ರದ್ದುಗೊಳಿಸು
  7. ಡಿಸೆಂ 15

    As we delegate more and more decisions to AI/ML, we may find ourselves in a society where rules and data-driven heuristics are being applied literally, without regard for their purpose. I expect that we will softly push back against it, until we too forget the purpose.

    ರದ್ದುಗೊಳಿಸು
  8. ಡಿಸೆಂ 15

    Oatmeal with dry fruits/nuts seems like it has all of the "desirable" properties of Soylent (instant gooey meal that's reasonably balanced and can be stored in solid form for years) -- but tastier and cheaper.

    ರದ್ದುಗೊಳಿಸು
  9. ಡಿಸೆಂ 14

    So if you build an Ark, welcome every animal on board. Except the termites. Because if the termites board, everyone will die, and that defeats the purpose of your Ark.

    ಈ ಥ್ರೆಡ್ ತೋರಿಸಿ
    ರದ್ದುಗೊಳಿಸು
  10. ಡಿಸೆಂ 14

    Many problems seem to come from the literal application of a rule while forgetting the purpose of the rule. The purpose of a rule should always override the rule itself. It's useful to come up with rules for yourself (shortcuts), but remember the first principles...

    ಈ ಥ್ರೆಡ್ ತೋರಿಸಿ
    ರದ್ದುಗೊಳಿಸು
  11. ಅವರು ಮರುಟ್ವೀಟಿಸಿದ್ದಾರೆ
    ಡಿಸೆಂ 13

    BFD: Google commits to hold off releasing a facial recognition product, including one for government use, nodding to its AI Principles & the technology’s propensity for abuse. ACLU’s statement:

    ರದ್ದುಗೊಳಿಸು
  12. ಅವರು ಮರುಟ್ವೀಟಿಸಿದ್ದಾರೆ
    ಡಿಸೆಂ 13

    When people call the Trump administration "fascist", they aren't just being hyperbolic. This is dystopian, totalitarian police-state stuff.

    ರದ್ದುಗೊಳಿಸು
  13. ಡಿಸೆಂ 13

    Real history was a lot less structured and inevitable than history books make it sound. We tend to project meaning onto history, post-facto, to create narratives where there was only chaos. Overactive pattern recognition

    ರದ್ದುಗೊಳಿಸು
  14. ಡಿಸೆಂ 13
    ರದ್ದುಗೊಳಿಸು
  15. ಡಿಸೆಂ 13

    Another example of performative cruelty enacted for no other reason than to soothe his racist base. The altar of ethno-nationalism demands human sacrifices. Hopefully it won't come to pass...

    ರದ್ದುಗೊಳಿಸು
  16. ಅವರು ಮರುಟ್ವೀಟಿಸಿದ್ದಾರೆ
    ಡಿಸೆಂ 11

    Truth is fascism’s most potent enemy. Guardians of truth are democracy’s greatest friends. Proud to see honor courageous journalists, including my friend and Democracy award winner .

    ರದ್ದುಗೊಳಿಸು
  17. ಡಿಸೆಂ 10

    Pre-trained network for image super resolution (in Keras): An evening project would be to export it to TF.js to run in the browser on user-uploaded photos

    ರದ್ದುಗೊಳಿಸು
  18. ಡಿಸೆಂ 10

    In the heart of silicon valley, the internet goes through overhead lines, and outages last for days...

    ರದ್ದುಗೊಳಿಸು
  19. ಅವರು ಮರುಟ್ವೀಟಿಸಿದ್ದಾರೆ
    ಡಿಸೆಂ 10

    New tutorial hot off the presses!🔥🚀 How to train, save, and load your Keras deep learning models. Full tutorial here: 👍

    ರದ್ದುಗೊಳಿಸು
  20. ಅವರು ಮರುಟ್ವೀಟಿಸಿದ್ದಾರೆ
    ಡಿಸೆಂ 9

    Day #9 👫 Autism impacts >1 million children in the US alone, and can make developing friendships + understanding social cues *extremely* difficult. 👉 Learn how is using to help children understand emotions in real-time:

    ಈ ಥ್ರೆಡ್ ತೋರಿಸಿ
    ರದ್ದುಗೊಳಿಸು
  21. ಅವರು ಮರುಟ್ವೀಟಿಸಿದ್ದಾರೆ
    ಡಿಸೆಂ 8

    Important reminder from talk at : respect other fields (see also: don’t oversell)

    ರದ್ದುಗೊಳಿಸು

ಲೋಡಿಂಗ್ ಸಮಯ ಸ್ವಲ್ಪ ತೆಗೆದುಕೊಳ್ಳುತ್ತಿರುವಂತೆನಿಸುತ್ತದೆ.

Twitter ಸಾಮರ್ಥ್ಯ ಮೀರಿರಬಹುದು ಅಥವಾ ಕ್ಷಣಿಕವಾದ ತೊಂದರೆಯನ್ನು ಅನುಭವಿಸುತ್ತಿರಬಹುದು. ಮತ್ತೆ ಪ್ರಯತ್ನಿಸಿ ಅಥವಾ ಹೆಚ್ಚಿನ ಮಾಹಿತಿಗೆ Twitter ಸ್ಥಿತಿಗೆ ಭೇಟಿ ನೀಡಿ.

    ಇದನ್ನೂ ಸಹ ನೀವು ಇಷ್ಟಪಡಬಹುದು

    ·