Krzakala Florent

@KrzakalaF

I like physics, statistics, machine learning, computers & playing guitar... views are my own.

Paris
Vrijeme pridruživanja: studeni 2012.

Tweetovi

Blokirali ste korisnika/cu @KrzakalaF

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

  1. Prikvačeni tweet
    26. lis 2018.

    I always admired Ludwig Boltzmann, my scientific hero and the founder of my field, statistical physics. Still, i never expected so much fun reading his writting. Make yourself a favor: enjoy his retelling of his visit to Berkeley in and Stanford

    Poništi
  2. proslijedio/la je Tweet
    23. sij

    Les médias parlent : - du coronavirus - de la grève à la SNCF - de la grève de la RATP - de la grève de l'APHP - des retraites - ... Alors que je vous rappelle que la seule info est que demain est dispo sur

    Poništi
  3. 15. sij

    PhD student/postdoc/researcher interested in the theory of machine learning with a statistical physics twist? But where to start? No worry we've got you covered: A school in the french alps with an amazing list of teachers for a full month in August:

    Poništi
  4. proslijedio/la je Tweet
    13. sij

    Do you want to enjoy this view for a month while learning about Statistical Physics and Machine Learning from e.g. , , , , ? Applications just opened, more info at . Please help to spread the word.

    Poništi
  5. 13. sij

    Happy to be invited speaker @ Alan Turing institute in the British Institute in London for what seems to be a fantastic event with a great list of speakers "Statistics and Computation" The even is live on

    Poništi
  6. 11. sij

    Really proud of being editor of the special issue of on the theory Machine learning with long version of papers from 2018 , & . They are some real gems in there!

    Poništi
  7. proslijedio/la je Tweet

    Je répète: pendant la NUIT. Quand tout le monde dort et que la consommation est au plus BAS.

    Poništi
  8. 25. pro 2019.

    Dear Any Idea how to create a html link to your videos that starts at a given moment in time? Or at a given chapter? Many videos are long >1h collections of shorter (5 to 20mins) videos. It would be useful for future refs to link to directly to them

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

    Fascinating work by using techniques from statistical physics to understand deep learning. Phase transitions, computational gaps, etc. I’ve to see both big success and sharply posed open problems.

    Poništi
  10. 14. pro 2019.

    Full room for for the Machine Learning and the Physical Sciences session @ on "Understanding machine learning via exactly solvable statistical physics models"

    Poništi
  11. proslijedio/la je Tweet

    Brilliant book: "Graph Algorithms: Practical Examples in and " by & with the Foreward by me😎 ——— Get FREE PDF copy: ————

    Poništi
  12. proslijedio/la je Tweet

    A tous ceux qui pensent que "Mais pourquoi 11 vaccins ? Ca fait beaucoup trop dans le corps d'un bébé !!" Regardons ça de plus près :

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    14. pro 2019.
    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    9. pro 2019.
    Poništi
  15. proslijedio/la je Tweet
    10. pro 2019.

    Tomorrow come check out the work done with our Optical Processing Unit. It'll be from 5-7pm @ East Exhibition Hall B+C#112 "Don’t take it lightly: Phasing optical random projections with unknown operators" Sidharth Gupta Ivan Dokmanić

    Poništi
  16. 10. pro 2019.

    Physicists have been studying machine learning with random data for 40 years: it is time to be more realistic! With , & we derive ODEs predicting the learning dynamics of nns for data generated by GANS or random features:

    Poništi
  17. 9. pro 2019.

    I do not how who wrote the scenario for but they need to get a rise. This is the best TV show I have seen since...

    Poništi
  18. 6. pro 2019.

    What is the link between the theoretical work on neural nets in physics in the 90s, Statistical learning theories in the 80s and over-parametrization the 2010s? Find out in our new paper "Rademacher complexity and Spin Glasses"

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

    Did you know that the Rademacher complexity is just the ground state energy of the perceptron model? If you want to know more check out our new paper: with

    Poništi
  20. proslijedio/la je Tweet

    New paper published : wavefront shaping meets photonic quantum information processing. A big congrats to our PhD student and our collaborators et al.

    Poništi
  21. proslijedio/la je Tweet

    A l’occasion des 80 ans du , la question du financement de la recherche française est posée par et 4 témoignages.

    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:

    ·