Shawn Le

@letrungson1

Vrijeme pridruživanja: siječanj 2012.
262 fotografije ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @letrungson1

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @letrungson1

  1. proslijedio/la je Tweet
    31. sij

    An Opinionated Guide to ML Research: “To make breakthroughs with idea-driven research, you need to develop an exceptionally deep understanding of your subject, and a perspective that diverges from the rest of the community—some can do it, but it’s hard.”

    9 replies 238 proslijeđenih tweetova 858 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    8. stu 2017.

    in today’s Stats 385 lecture, Jeffrey Pennington of Google studies Theory of Neural Nets using Random Matrix Theory

    2 proslijeđena tweeta 3 korisnika označavaju da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    8. sij

    Many aspiring AI engineers ask me how to take the next step and join an AI team. This report from , a affiliate, walks you through how AI teams work and which skills you need for different AI career tracks. Download it here:

    446 proslijeđenih tweetova 1.594 korisnika označavaju da im se sviđa
    Poništi
  4. proslijedio/la je Tweet
    26. pro 2019.

    So, "deep learning" is the idea of doing representation learning via a chain of learned feature extractors. It's all about describing some input data via *deep hierarchies of features*, where features are *learned*. A further question is then: is the brain "deep learning"?

    18 replies 147 proslijeđenih tweetova 672 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    11. pro 2019.

    Courses 1 & 2 of ‘s newest Specialization is now available on ! Training a model is only one step in building a working AI system. These courses teach you how to navigate some key deployment scenarios. Enroll here:

    371 proslijeđeni tweet 1.453 korisnika označavaju da im se sviđa
    Poništi
  6. 28. stu 2019.

    How Boston Dynamics Is Redefining Robot Agility - IEEE Spectrum

    Poništi
  7. proslijedio/la je Tweet
    22. lis 2019.

    More on domain randomization here by

    1 proslijeđeni tweet 3 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    12. stu 2019.

    Want to improve accuracy and robustness of your model? Use unlabeled data! Our new work uses self-training on unlabeled data to achieve 87.4% top-1 on ImageNet, 1% better than SOTA. Huge gains are seen on harder benchmarks (ImageNet-A, C and P). Link:

    i
    462 proslijeđena tweeta 1.544 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    10. stu 2019.

    😊Self-supervised learning opens up a huge opportunity for better utilizing unlabelled data while learning in a supervised learning manner. My latest post covers many interesting ideas of self-supervised learning tasks on images, videos & control problems:

    11 replies 487 proslijeđenih tweetova 1.797 korisnika označava da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    22. lis 2019.

    Pushy robots learn the fundamentals of object manipulation

    1 proslijeđeni tweet 1 korisnik označava da mu se sviđa
    Poništi
  11. proslijedio/la je Tweet
    30. tra 2019.

    I Now call it "self-supervised learning", because "unsupervised" is both a loaded and confusing term. In self-supervised learning, the system learns to predict part of its input from other parts of it input. In...

    36 replies 394 proslijeđena tweeta 1.515 korisnika označava da im se sviđa
    Poništi
  12. proslijedio/la je Tweet
    13. ruj 2019.

    Yann LeCun: Deep Learning, Convolutional Neural Networks, and Self-Supervised Learning on … - Yann

    2 proslijeđena tweeta
    Poništi
  13. proslijedio/la je Tweet
    20. ruj 2019.

    Self-Supervised Learning of Depth and Motion Under Photometric Inconsistency by Tianwei Shen et al.

    1 proslijeđeni tweet 4 korisnika označavaju da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    3. ruj 2019.

    RoBERTa demonstrates the potential for self-supervised training techniques to match or exceed the performance of more traditional, supervised approaches. Read more:

    61 proslijeđeni tweet 159 korisnika označava da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    4. ruj 2019.

    Neural structured learning in TensorFlow

    5 replies 187 proslijeđenih tweetova 640 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    6. ruj 2019.

    In our new blog post, we review how brains replay experiences to strengthen memories, and how researchers use the same principle to train better AI systems:

    192 proslijeđena tweeta 567 korisnika označava da im se sviđa
    Poništi
  17. proslijedio/la je Tweet
    20. ruj 2019.

    We see more significant improvements from training data distribution search (data splits + oversampling factor ratios) than neural architecture search. The latter is so overrated :)

    45 replies 405 proslijeđenih tweetova 2.031 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    27. kol 2019.

    Can neural network architectures alone, without learning any weight parameters, encode solutions for a given task? We search for “weight agnostic neural network” architectures that can perform various tasks even when using random weight values. Learn more→

    13 replies 403 proslijeđena tweeta 1.111 korisnika označava da im se sviđa
    Poništi
  19. proslijedio/la je Tweet
    16. kol 2019.

    The wonderful has been working on this podcast with the team for a while and I’m really excited to see the series launch! It was great fun talking to Hannah for episode 8, and I think she's captured 's culture and research brilliantly.

    Curious about AI and want to learn more? Introducing the DeepMind podcast! will be taking you behind the scenes at DeepMind, exploring everything from AlphaGo to the future of AI. Read our blog, listen to the trailer and subscribe:
    5 replies 86 proslijeđenih tweetova 378 korisnika označava da im se sviđa
    Poništi
  20. proslijedio/la je Tweet
    19. kol 2019.

    Nice blog post about a series of optimizations to reduce training time of a CIFAR10 image model. Many of these options are likely applicable to lots of different kinds of models. Nice work, !

    Ever wanted to train CIFAR10 to 94% in 26 SECONDS on a single-GPU?! In the final post of our ResNet series, we open a bag of tricks and drive training time ever closer to zero... Colab: Blog:
    42 proslijeđena tweeta 227 korisnika označava da im se sviđa
    Poništi

@letrungson1 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:

    ·