SEES Lab

@sees_lab

Roger Guimerà & Marta Sales-Pardo - Science and Engineering of Emergent Systems at Universitat Rovira i Virgili & ICREA

Tarragona, Catalonia
Vrijeme pridruživanja: ožujak 2010.

Tweetovi

Blokirali ste korisnika/cu @sees_lab

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

  1. Prikvačeni tweet
    31. sij

    "A Bayesian machine scientist to aid in the solution of challenging scientific problems" is our new paper just out in

    Prikaži ovu nit
    Poništi
  2. prije 5 sati
    Poništi
  3. prije 17 sati
    Poništi
  4. proslijedio/la je Tweet

    🚀🤓I have always loved making math models, but using a "machine scientist" to take data and get the equation that represents a phenomenon is really epic, I do want to use this on my regular work!

    Poništi
  5. 3. velj
    Poništi
  6. proslijedio/la je Tweet
    3. velj

    New algorithm developed at SEES:lab, Dept of Chemical Engineering, Universitat Rovira i Virgili claims to make more accurate predictions & generate models making it possible to understand predictions.

    Poništi
  7. proslijedio/la je Tweet
    31. sij

    A Bayesian machine scientist to aid in the solution of challenging scientific problems

    Poništi
  8. proslijedio/la je Tweet
    2. velj
    Poništi
  9. proslijedio/la je Tweet
    31. sij

    Nice approach: A Bayesian machine scientist to aid in the solution of challenging scientific problems

    Poništi
  10. proslijedio/la je Tweet
    1. velj

    URV and ICREA researchers have designed an algorithm that can automatically identify mathematical models that not only improve the reliability of the predictions they make but also provide information for understanding the data as a scientist would

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    1. velj

    Very interesting article on using machine selection of models & to form models of & , as we have Bayesian machine scientist to aid in the solution of challenging scientific problems

    Poništi
  12. proslijedio/la je Tweet
    1. velj

    How to find new models from a given data set? This is a major challenge with great relevance to many disciplines, from physics to complexity. Here's a very important contribution to creating a Bayesian Scientist Machine by et al.

    Poništi
  13. 1. velj
    Poništi
  14. proslijedio/la je Tweet
    1. velj
    Poništi
  15. proslijedio/la je Tweet
    1. velj

    Very relevant work on to obtain mathematical interpretable models in instead of blackbox predictions. Congrats and team!

    Poništi
  16. proslijedio/la je Tweet
    31. sij

    Congratulations to my colleagues and friends Roger and Marta I've been hearing for so long the "scientific robot" in our meetings, and finally there you go! Now I can read it, although not sure I can understand it...😅

    Poništi
  17. proslijedio/la je Tweet
    1. velj

    A Bayesian machine scientist to aid in the solution of challenging scientific problems

    Poništi
  18. proslijedio/la je Tweet
    31. sij

    Investigadors de la i ICREA han dissenyat un que identifica automàticament models matemàtics que milloren la fiabilitat de les prediccions que fan i aporten informació per comprendre les dades, com ho faria un científic.

    Poništi
  19. 31. sij

    This is the result of >6 years of work with a fantastic team including and others without (known) Twitter accounts. Fair to point out that funding for this work has repeatedly been turned down for reasons going from "this is impossible" to "this is old news"

    Prikaži ovu nit
    Poništi
  20. 31. sij

    We develop a Bayesian approach to the problem of automatically finding parsimonious closed-form mathematical models (as opposed to black boxes) from data. Here is the machine scientist finding the correct model for some synthetic data

    Prikaži ovu nit
    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:

    ·