Krishna D N

@Krishna_DN94

Believer of Recurrent Neural Network

Vrijeme pridruživanja: ožujak 2016.

Tweetovi

Blokirali ste korisnika/cu @Krishna_DN94

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @Krishna_DN94

  1. proslijedio/la je Tweet
    29. sij

    I've always been fascinated by Bayesian Nonparametrics. I struggled to grasp those ideas directly from papers. Today, by chance, I found the best (imo) single reference for anyone interested: A gentle introduction by and Michael Jordan

    Poništi
  2. proslijedio/la je Tweet
    28. sij

    OpenL3 v0.3.0 is out! Now with audio AND image embeddings, video file processing, and batch processing. Just run "pip install openl3" to try it out (requires ).

    Poništi
  3. proslijedio/la je Tweet
    26. sij

    I am thrilled to announce our paper “Feedback Recurrent AutoEncoder” was accepted at ! collaboration with Yang Yang, and Jon Ryu. . A quick thread.

    Prikaži ovu nit
    Poništi
  4. 25. sij

    I am very excited to announce that our paper "LANGUAGE INDEPENDENT GENDER IDENTIFICATION FROM RAW WAVEFORM USING MULTI-SCALE CONVOLUTIONAL NEURAL NETWORKS" has been accepted at

    Poništi
  5. proslijedio/la je Tweet
    22. sij

    BayesNet: A library for drawing Bayesian networks, graphical models and directed factor graphs in LaTeX.

    Poništi
  6. proslijedio/la je Tweet
    22. sij

    OpenMined + collaborating to advance open source software development. Learn about these talented teams on our blog: Many opportunities ahead. Join our Slack community to find out more!

    Poništi
  7. proslijedio/la je Tweet
    22. sij

    You got a bunch of GPU machines and are wondering which GPUs are still free? I used to ssh into the list of machines and checked manually until I built a small dashboard to show me: I thought other people might have the same problem..

    Poništi
  8. proslijedio/la je Tweet
    22. sij

    FixMatch: focusing on simplicity for semi-supervised learning and improving state of the art (CIFAR 94.9% with 250 labels, 88.6% with 40). Collaboration with Kihyuk Sohn, Nicholas Carlini

    Prikaži ovu nit
    Poništi
  9. 22. sij

    Checkout my new tutorial of the paper " Multi-source domain adaptation for text classification via DistanceNet-Bandits "

    Poništi
  10. 21. sij

    Checkout my new tutorial of the paper " H-vectors: Utterance level speaker embeddings using Hierarchical attention model"

    Poništi
  11. proslijedio/la je Tweet
    19. sij

    I'm pretty confused. with this level of details, they have presumably run some experiments already to be certain about this approach, and somehow couldn't wait a couple of weeks to put results in the manuscript.

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    13. sij

    Super fast and online speech recognition with time-depth separable convolutions from FAIR:

    Poništi
  13. proslijedio/la je Tweet
    6. sij

    10 ML & NLP Research Highlights of 2019 New blog post on ten ML and NLP research directions that I found exciting and impactful in 2019.

    Poništi
  14. proslijedio/la je Tweet

    Read my latest blog post detailing recent events around naming of and parallels it shares with name change. Also cluelessness of privileged men like and Aaronson Happy holidays!

    Prikaži ovu nit
    Poništi
  15. 22. pro 2019.

    New tutorial of the paper " Minimum Bayes risk training of RNN transducer for end to end speech recognition"

    Poništi
  16. proslijedio/la je Tweet
    15. pro 2019.

    I had a great time at the Bayesian Deep Learning Workshop! My talk on "Using Loss Surface Geometry for Practical Bayesian Deep Learning" starts at 6m40s:

    Poništi
  17. proslijedio/la je Tweet
    12. pro 2019.

    Hochreiter & Schmidhuber 🔥🔥 Two decades after the LSTM paper

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet

    Come and see @oxcsmls wonderful and present their fantastic work on Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders, poster 109. Work completed with

    Poništi
  19. proslijedio/la je Tweet
    10. pro 2019.

    Exact Gaussian processes on more than a million points, now in under 2 hours! Works in general settings. Our new paper, with , G. Pleiss, J. Gardner, S. Tyree, K. Weinberger, tomorrow 5:00-7:00 PM East Exhibition Hall B+C #169.

    Poništi
  20. proslijedio/la je Tweet
    9. pro 2019.

    Unsupervised pre-training now outperforms supervised learning on ImageNet for any data regime (see figure) and also for transfer learning to Pascal VOC object detection

    , , i još njih 2
    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:

    ·