Rezultati pretraživanja
  1. 16. lip 2019.

    Notes from here:

    20 replies 231 proslijeđeni tweet 874 korisnika označavaju da im se sviđa
  2. 11. lip 2019.

    Modern convnets ignore the Nyquist sampling criterion, making them unstable. Come see how simple antialiasing can make your net more stable, accurate, and robust! 3pm tomorrow (Wed) in Seaside Ballroom.

    31 proslijeđeni tweet 133 korisnika označavaju da im se sviđa
  3. 11. lip 2019.

    best paper honourable mention for Carl Allen and for their work on explaining word embeddings! Paper:

    12 proslijeđenih tweetova 38 korisnika označava da im se sviđa
  4. 12. lip 2019.

    Attending and interested in uncertainty, calibration & out-of-distribution robustness? Chk out our poster at the Uncertainty in DL workshop :) Can You Trust Your Model’s Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift Paper:

    40 proslijeđenih tweetova 193 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
  5. 15. lip 2019.

    Best paper award at main idea: unsupervised learning of disentangled representations is fundamentally impossible without inductive biases. Verified theoretically & experimentally.

    52 proslijeđena tweeta 210 korisnika označava da im se sviđa
  6. 10. lip 2019.

    Mila members are presenting twenty-two papers at this week! Here are some highlights:

    22 proslijeđena tweeta 97 korisnika označava da im se sviđa
  7. 15. lip 2019.

    Slides from my talk on "Recent Trends in Personalization: A Netflix Perspective" at the workshop on Adaptive and Multi-Task Learning.

    33 proslijeđena tweeta 95 korisnika označava da im se sviđa
  8. 12. lip 2019.

    highlight (jetlag special): A Contrastive Divergence for Combining Variational Inference and MCMC

    38 proslijeđenih tweetova 169 korisnika označava da im se sviđa
  9. 7. lip 2019.

    Iranian Women have strong presence at . Stop by their poster if you are attending the conference next week.

    12 proslijeđenih tweetova 55 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
  10. 15. lip 2019.

    So glad that we got the Best Paper Award at the AI for social good Workshop at 🥳

    Me and are going to present this poster on our work on deep learning for breast cancer screening at the AI for Social Good Workshop at on Saturday. Come and say hi! Paper: Code:
    7 replies 28 proslijeđenih tweetova 216 korisnika označava da im se sviđa
  11. 18. lip 2019.

    Slides and video are now available for the Theoretical Physics for Deep Learning workshop at

    60 proslijeđenih tweetova 206 korisnika označava da im se sviđa
  12. 8. svi 2019.

    List of accepted papers:

    111 proslijeđenih tweetova 274 korisnika označavaju da im se sviđa
  13. 19. stu 2019.

    For all researchers working on music auto-tagging, here is the new MTG-Jamendo dataset we have created this year and presented on at : . Over 55,000 full audio tracks labeled with almost 200 tags by genres, instruments, and moods/themes.

    12 proslijeđenih tweetova 46 korisnika označava da im se sviđa
  14. 15. lip 2019.

    Slides from my talk at the Multitask and Lifelong RL workshop at : . Thanks for a great program!

    12 proslijeđenih tweetova 61 korisnik označava da mu se sviđa
  15. 15. lip 2019.

    Come to Invertible Neural Nets and Normalizing Flows () at 14:20 where I will be giving an invited talk on Neural Ordinary Differential Equations for Continuous Normalizing Flows & FFJORD!

    28 proslijeđenih tweetova 143 korisnika označavaju da im se sviđa
  16. 11. lip 2019.

    I'm glad to share that we have received the Best Paper Award!

    I am excited and honored that we received the Best Paper Award with "Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations" (). W/ , S. Bauer, , , ,
    Prikaži ovu nit
    8 proslijeđenih tweetova 65 korisnika označava da im se sviđa
  17. 24. lip 2019.

    Pre-training is a hot topic in NLP research and models like BERT and GPT have definitely delivered exciting breakthroughs. The challenge is in upping our game in finer sequence to sequence based language generation tasks. Enter MASS:

    52 proslijeđena tweeta 214 korisnika označava da im se sviđa
  18. 24. lip 2019.

    Blog post - Five more music papers from with my incredibly shallow introductions.

    17 proslijeđenih tweetova 29 korisnika označava da im se sviđa
  19. 14. lip 2019.

    Come and check out the "tractable probabilistic models" workshop at in room 202. My students will present 8 papers, on tractable reasoning, missing data, discriminative learning, probabilistic programming and databases, and hybrid models.

    5 proslijeđenih tweetova 28 korisnika označava da im se sviđa
  20. 15. lip 2019.

    Should we be trying to prove anything at all? While it seems much ML theory comes via physicists, *the physicist in the Deep Phenomena audience* characterizes physics as a “purely empirical” discipline, questions whether we should try to prove anything in ML.

    10 replies 15 proslijeđenih tweetova 95 korisnika označava da im se sviđa

Nema rezultata.

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.