Rezultati pretraživanja
  1. 27. sij

    For all their marvels, no ConvNet could survive training 1% as hard as Kobe Bryant. RIP

  2. 23. lis 2017.

    TODAY (4pm, D1.07): is talking about using deep learning to infer house prices from Google Street View images

  3. Arguably AI/ML research was held up pre-deep learning by the mistaken belief that empirical questions required foundational answers. Now, as AI researchers look beyond supervised learning (causality, robustness, distribution shift) the folly’s turned converse.

    Prikaži ovu nit
  4. Odgovor korisnicima i sljedećem broju korisnika:

    Exactly the response I would expect from a troll who thinks lying to others on twitter and besmirching an honest campaign is okay. You might want to try to .

  5. Who’s awake in London? The session is popping until 3a at Ronny Scott’s .

  6. 4. sij

    In 2020, I predict we sill see the first ***ConvPuter***—a fully-functioning computer system where every function in every application, from the OS kernel to user-facing apps, is learned w. deep convolutional neural networks.

  7. 14. pro 2019.

    Abraham getting roasted by two "deepfakes" wearing Yann LeCun masks. 😂😂 Well done , and touché.

  8. 14. pro 2019.

    Yann LeCun (?)’s talk at Machine Learning for Creativity and Design Workshop

    Prikaži ovu nit
  9. 28. stu 2019.

    Whether training yourself, or training your neural network to track your workout, make sure to always have dogs in the training data

  10. 20. stu 2019.

    Aquent Gymnasium’s new Take 5 tutorials are like mini-workouts for your mind. Every 5-minute lesson teaches you a new skill to keep your thinking fresh and your career on track

  11. 1. stu 2019.

    My mate says we need more symbols in AI. Here's a symbol for you baby: *

  12. 24. lis 2019.

    Quedan solo algunos días para que mi curso "Deep Learning" con Pytorch este al aire en Platzi!

    Prikaži ovu nit
  13. 27. lip 2019.

    Google: Self-driving cars are just around the corner!!!1! Also Google:

  14. Morning all from some wild swimming this morning with new friends, coffee then Tea Uglow founder of Creative Labs opens with “how to lead when you don’t know what your doing” 🙌🏽

  15. *Clean hands* may prevent those health maladies due to *poo hands*—but do not in general lead to good health! Too many papers make claims that overreach precisely in the style of the SFO bathroom copy writer.

  16. 2. sij 2019.

    AI to be introduced in Indian high school syllabus!

  17. 5. pro 2018.

    Our poster on "How the Softmax Output is Misleading for Evaluating the Strength of Adversarial Examples" will be on display during the workshop on Friday at . Many thanks to for helping out, given our visa issues.

    Prikaži ovu nit
  18. 20. stu 2018.

    Professional announcement: While it might seem that fictional personae would be un-promotable, I've been upgraded to the station of Chairman of the Board at ! Looking forward to solving AGI in 2019!

  19. 16. stu 2018.

    Paper accepted at the NIPS 2018 Workshop on Security in Machine Learning (): "How the Softmax Output is Misleading for Evaluating the Strength of Adversarial Examples". Impressive line-up of other accepted workshop papers.

    Prikaži ovu nit
  20. 31. lis 2018.

    Happy HalloweeNN

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.