Tweetovi

Blokirali ste korisnika/cu @artygadetsky

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

  1. proslijedio/la je Tweet

    Low-variance Gradient Estimates for the Plackett-Luce Distribution by , and Dmitry Vetrov in collaboration with Christopher Robinson and Novi Quadrianto

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet

    Check out our new paper "Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution", accepted as an oral to () on how to reduce the variance of gradients when optimizing w.r.t. a distribution over permutations. Paper:

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    4. tra 2019.

    Our team received the "Outstanding Educator Award" for the "Advanced Machine Learning" specialization we created! Very proud to be a part of it

    Poništi
  4. proslijedio/la je Tweet

    We are hiring a postdoc on deep reinforcement learning. Come work with us! Deadline 31 June 2019. Call for applications:

    Poništi
  5. proslijedio/la je Tweet

    The Deep Weight Prior by , , , Dmitriy Vetrov in collaboration with : an empirical prior for conv. layers in Bayesian Neural Nets that improves learning on small datasets

    Poništi
  6. proslijedio/la je Tweet

    Variance Networks: When Expectation Does Not Meet Your Expectations by , , , Dmitry Vetrov: stochastic neural networks with N(0,σ²) weights where only variances are learned work surprisingly well.

    Poništi
  7. proslijedio/la je Tweet

    Variational Autoencoder with Arbitrary Conditioning by Oleg Ivanov, , Dmitry Vetrov: an extension of conditional VAE allowing to condition on an arbitrary subset of the features and sample the remaining ones

    Poništi
  8. proslijedio/la je Tweet

    We've got 3 papers accepted to

    Poništi
  9. proslijedio/la je Tweet
    25. stu 2018.

    Check out the short video summarizing our paper "Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs". Come to our presentation (spotlight at 04:20 PM, poster #162, Tue Dec 4th). We would be happy to talk to you at the conference!

    Poništi
  10. proslijedio/la je Tweet

    We released a pre-print on the Deep Weight Prior - a flexible prior distribution for Bayesian CNNs via generative modeling of convolutional kernels. Thanks to and my awesome co-authors Kirill Struminsky Dmitry Vetrov

    Poništi
  11. proslijedio/la je Tweet

    At ? Come visit our poster on "Conditional Generators of Words Definitions" by and . Today (July 17), poster session 2D, poster no. D8

    Poništi
  12. proslijedio/la je Tweet

    We have significantly updated our preprint on Variance Networks! Training only variances of the weights w_ij ~ N(0, sigma_ij^2) leads to state-of-the-art performance. Now more explanation, practical and theoretical results.

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet

    Check out our new paper "Conditional Generators of Words Definitions" () by , and Dmitry Vetrov on how to generate word definitions in face of ambiguity by virtue of a usage example. Paper: Code:

    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:

    ·