François CholletOvjeren akaunt

@fchollet

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

Mountain View, CA
Vrijeme pridruživanja: kolovoz 2009.

Tweetovi

Blokirali ste korisnika/cu @fchollet

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

  1. Prikvačeni tweet

    I've just released a fairly lengthy paper on defining & measuring intelligence, as well as a new AI evaluation dataset, the "Abstraction and Reasoning Corpus". I've been working on this for the past 2 years, on & off. Paper: ARC:

    Prikaži ovu nit
    Poništi
  2. Refreshingly honest

    Poništi
  3. proslijedio/la je Tweet
    30. sij
    Prikaži ovu nit
    Poništi
  4. I think really good fiction has the power to remake reality

    Poništi
  5. proslijedio/la je Tweet
    1. velj

    I feel like a lot of US citizens don’t quite get how hard it is to get an immigrant visa even if you are super qualified—many friends/family have struggled w the H1-B lottery or spent months applying for an O1 or got denied entry even though they have MIT degrees/great jobs/etc

    Prikaži ovu nit
    Poništi
  6. You can't always choose the situations you find yourself in, but you control how you react to them. When all is said and done, this is what defines who you are.

    Poništi
  7. Perhaps Trump -- his personality and his actions -- will end being emblematic of our times. Of perhaps it is our resistance to Trump that will define us in the eyes of future generations. We'll see

    Prikaži ovu nit
    Poništi
  8. From the perspective of an external observer, it's not president Trump that's on trial, it's America's system of government -- and the judge is History. We're all really curious how America's institutions will end up dealing with the situation.

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet

    Your organization will not acquire machine learning fluency with one big breakthrough project. You will build the right processes, mindset, and tooling over time through a series of small successes across a diverse range of problems.

    Poništi
  10. proslijedio/la je Tweet
    29. sij

    Anemia affects 1.6 billion people globally, and diagnosis typically involves a blood test. Now research shows how machine learning can help detect the disease.

    Poništi
  11. In 324 BC he organized a mass marriage between his generals and Persian noblewomen (most of these marriages didn't last long after his death). His long-term plan was a cultural and demographic merger of the populations in his empire into a new pan-mediterranean culture

    Prikaži ovu nit
    Poništi
  12. Notably, Alexander's take on empire-building wasn't one-sided colonialism (unlike his big fan Caesar much later). He was an advocate of multiculturalism. He adopted Persian customs (which was v controversial) and encouraged intermixing between Greeks and Persians

    Prikaži ovu nit
    Poništi
  13. Something to keep in mind when you'll score your own OKRs this quarter

    Prikaži ovu nit
    Poništi
  14. Asia was anything east of the Bosphorus.

    Prikaži ovu nit
    Poništi
  15. Shortly before his death, Alexander wrote down an OKR doc. It included: - Conquest of Arabia and the entire Mediterranean basin - Circumnavigation of Africa - Development of new cities in Asia (~Middle-East) and intermixing of Eastern and Western populations

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    30. sij

    I was just thinking it would be cool if you could do hyperparameter tuning directly in Keras and then found this blog post published yesterday 🤯 The best part? I got it working in 5 minutes!

    Poništi
  17. proslijedio/la je Tweet
    30. sij

    Flash a smile! 😁 We built a smile-detecting, voice controlled photo booth using Lite and . 📸 See how we did it →

    Poništi
  18. proslijedio/la je Tweet
    Odgovor korisniku/ci

    Make sure to check out the KerasTuner implementation for , as well! 😄✨ Vignettes, documentation, and more available on Turgut's Github.

    Poništi
  19. proslijedio/la je Tweet
    29. sij

    Good hyperparameters lead to ML success! 🙌 Learn how you can find the best parameters with Keras Tuner— a fully-featured, scalable, and easy-to-use hyperparameter tuning library for Keras and beyond. Read the blog →

    hyperparameters with keras tuner
    Poništi
  20. Between 2017 and 2018, the US military budget increased by 10%. That's $54 billion, which is approximately the same as the total budget for education ($59 billion)

    Poništi
  21. proslijedio/la je Tweet
    28. sij

    Google Dataset Search is officially out of beta! With new improvements and almost 25 million datasets indexed, Dataset Search has helped researchers, students, and others find the web data they need. 🔎📈 Learn more →

    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:

    ·