César de Pablo

@zdepablo

Data Scientist @ BBVA Data & Analytics. Crunching numbers and letters

Mad City
Vrijeme pridruživanja: lipanj 2010.

Tweetovi

Blokirali ste korisnika/cu @zdepablo

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

  1. Prikvačeni tweet
    13. ožu 2019.

    : Interested in for datasets? Have a look to the Financial Entity Identification

    Poništi
  2. proslijedio/la je Tweet
    3. velj
    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet

    how to mess with your coworkers

    Poništi
  4. proslijedio/la je Tweet
    31. sij

    We are releasing HiPlot, a lightweight interactive visualization tool to help AI researchers discover correlations and patterns in high-dimensional data.

    Poništi
  5. proslijedio/la je Tweet
    2. velj
    Poništi
  6. proslijedio/la je Tweet
    1. velj
    Poništi
  7. proslijedio/la je Tweet
    31. sij

    Ya ha finalizado el proceso de elección del logo que representa al CEIP Lope de Vega. Ahora toca votar cual será el ganador de los 6 países. Este logo representará el proyecto Erasmus +: "músic to all" durante estos dos cursos. Ya sabéis tenéis que votar.

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    30. sij

    Our Question Answering model for English based on AlBERT and fine tuned on SQuAD 2.0 seems to be useful. Great job !

    Poništi
  9. proslijedio/la je Tweet
    28. sij
    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    28. sij

    We launch today Oraf. Strategy & vision,narrative,data products, art, applied AI, digital and non digital. There is no such thing as a data or digital strategy. There is only strategy. Relationships matter. We operate across boundaries to understand them.

    Poništi
  11. proslijedio/la je Tweet
    28. sij
    Poništi
  12. proslijedio/la je Tweet
    25. sij

    Our unsupervised MT paper mentioned "Important AI & Machine Learning Trends for 2020"

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

    Una lectura que no os dejará indiferentes. O, al menos, no debería...: La secreta que podría poner fin a la tal como la conocemos by

    , , i još njih 7
    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    23. sij

    Hello, world! This is the official account for NumPy, the fundamental package for scientific computing with Python. Follow us for news, info and content related to NumPy!

    Poništi
  15. proslijedio/la je Tweet
    24. sij

    Natural Language Generation has been dominated by left-to-right autoregressive models like GPT-2. However it is not the only way to do it and lots of exciting work been done over last ~2 years on alternative approaches with their own pros&cons. Here is my attempt on grouping them

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    24. sij

    The cover looks very familiar. I hope the translators fixed all our errors. Oh, BTW, we just commissioned a Spanish translation.

    Poništi
  17. proslijedio/la je Tweet
    19. sij

    "(...) intentando que los que saben del dominio a mejorar sean capaces de usar IA en vez de ser reemplazados por modelos creados por gente que no tiene ni zorra de lo que está modelando." Amén Santana.

    Poništi
  18. proslijedio/la je Tweet
    13. sij

    2020 edition of CMU CS11-747 "Neural Networks for NLP", is starting tomorrow! We (co-teacher and 6 wonderful TAs) restructured it a bit to be more focused on "core concepts" used across a wide variety of applications. 1/2

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    10. sij

    Missed this great article on the Clever Hans effect in NLP Many SOTA results we get with Bert-like models are due to these models "breaking" our datasets –in a bad sense– by exploiting their weaknesses 's piece has nice overview & advice Also follow on this

    Poništi
  20. proslijedio/la je Tweet
    10. sij

    This is an incredible blog post talking about how to build a search engine with open-source search and ML technologies: Elasticsearch and BERT. by link: github:

    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:

    ·