Luca

@LucaAmb

Assistant professor in Machine Learning. Specialized in variational Bayesian inference and machine learning for healthcare.

Vrijeme pridruživanja: srpanj 2011.

Tweetovi

Blokirali ste korisnika/cu @LucaAmb

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

  1. proslijedio/la je Tweet

    Great example of the power of expectations to shape perception: The visual system is so determined to see faces as convex, rather than concave, that it’s virtually impossible not to see the illusion – even when you know what’s going on.

    Poništi
  2. proslijedio/la je Tweet
    30. sij

    🔴Is this my body? Check my new post with at the School of Robotics blog about body perception using variational inference.👇 🔜2nd part -> Deep Active Inference coming soon! [Great initiative from & ]

    Poništi
  3. proslijedio/la je Tweet
    6. pro 2019.

    Check out our extensive review paper on normalizing flows! This paper is the product of years of thinking about flows: it contains everything we know about them, and many new insights. With , , , . Thread 👇

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet

    ICYMI: Rank measures how many rational solutions to an equation one needs in order to find every other rational solution. For decades, mathematicians believed there was no limit to the rank of an elliptic curve. Not so, says a new model.

    Poništi
  5. proslijedio/la je Tweet
    3. velj

    Oldies but goldies: G. H. Golub, Christian Reinsch, Singular value decomposition and least squares solutions, 1970. The most popular algorithm to compute efficiently the SVD decomposition.

    Poništi
  6. 3. velj

    In the figure a example application to deep learning models:

    Prikaži ovu nit
    Poništi
  7. 3. velj

    We are happy to share our joint work on the Indian chef process. A nonparametric prior for directed Bayesian networks. You can use this process to infer the existence of new variables affecting your observations.

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    20. pro 2019.

    Yes! I got my first big conference paper accepted at ICLR, with spotlight! We improve the previous DeepMind paper "NALU" by 3x-20x. – This took 7-8 months, working without any funding as an independent researcher. Paper: Code:

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    20. stu 2019.

    I am hiring a graduate student to join our group at the (full position, 4 years funding)! Please apply if you are interested in working on machine/deep learning and visual cognitive neuroscience. Details here: Please share/RT far and wide!

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    18. stu 2019.

    Preprint: Causal inference using Bayesian nonparametric quasi-experimental design If you want to know your intervention worked, but you cannot do randomized controlled trials. Includes example on Dutch voting behaviour! With and

    Prikaži ovu nit
    Poništi
  11. 8. stu 2019.

    English should adopt "non" as a word so that we can get rid of all these dashes!

    Poništi
  12. proslijedio/la je Tweet
    25. ruj 2019.

    Our new preprint on the ‘Neural dynamics of perceptual inference and its reversal during imagery’ with and is out now! We reveal feedforward and feedback dynamics of stimulus processing during perception and imagery. A thread 1/N

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    21. kol 2019.

    We are currently researching new methods for constructing variational distributions automatically (beyond the standard mean field approach). If you know some literature about this topic please let us know! (And retweet if you have followers who could know!)

    Poništi
  14. proslijedio/la je Tweet
    13. kol 2019.

    A new preprint! We present DeepRF: ultrafast population receptive field (pRF) mapping with . With similar performance in a fraction of the time, it enables modeling of more complex pRF models, resolving an important limitation of the conventional method.

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    7. kol 2019.

    Check-out TaylorAlgebra. A small package for symbolic Taylor expansions. We are soon going to support and use it for perturbative machine learning in Brancher.

    Poništi
  16. proslijedio/la je Tweet
    21. srp 2019.
    Poništi
  17. proslijedio/la je Tweet
    22. srp 2019.

    We are happy to share Brancher .35 with dedicated support for stochastic processes, infinite models and timeseries analysis. Try this on our new tutorial! If you like our work, please share it and star us on Github! :)

    Poništi
  18. proslijedio/la je Tweet
    17. srp 2019.

    Our new-ish, neural, pure Python stanfordnlp package provides grammatical analyses of sentences in over 50 human languages! Version 0.2.0 brought sensibly small model sizes and an improved lemmatizer. Try it out: pip install stanfordnlp

    Poništi
  19. proslijedio/la je Tweet
    19. srp 2019.

    My lab at NYU has a new postdoc position in self-supervised learning. Work with me to model child headcam videos, with the aim of learning knowledge of objects and agents from raw input. Please circulate.

    Poništi
  20. proslijedio/la je Tweet
    19. srp 2019.

    Sad to hear of the passing today of AI pioneer Patrick Winston. His 1970 PhD on machine learning was one of my greatest inspirations when I was a PhD student - he went on to do so much more, including leading MIT's AI lab for 25 years. RIP Patrick.

    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:

    ·