Arnaud Miribel

@arnaudmiribel

data scientist , previously , deep learning instructor , alum

Grenoble, France
Vrijeme pridruživanja: siječanj 2012.

Tweetovi

Blokirali ste korisnika/cu @arnaudmiribel

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

  1. Prikvačeni tweet
    29. sij

    Very happy that our paper got accepted at , introducing Broccoli: a new way to learn foreign languages! (hints: 🇫🇷🐱🐶) - Read more

    Poništi
  2. proslijedio/la je Tweet
    2. velj
    Poništi
  3. proslijedio/la je Tweet
    30. sij

    02/02/2020 is the only date in our lifetimes — and the 1st since 11/11/1111 — to be palindromic across the World, in whatever date format you choose.

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    31. sij

    On Tuesday, in my class, we have learnt that all a neural net does is stretching / contracting the space fabric. For example this 3-layer net (1 hidden layer of 100 positive neurons) gets its 5D logits (2D projections) linearly separable by the classifier hyperplanes (lines).

    Poništi
  5. 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
  6. proslijedio/la je Tweet
    27. ruj 2019.

    That feeling when you first discovered `document.designMode`

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    20. sij

    Interesting paper showing how dozens of studies have accidentally leaked large amounts of data from train->test dataset, by duplicating data items prior to doing a random split.

    Poništi
  8. proslijedio/la je Tweet
    13. sij

    Our mission is to provide the data and research to make progress against the world’s largest problems: What are the world’s largest problems? This week I thought I do a thread on all the global problems we research; starting with health. ↓↓

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

    i just read this excellent paper from 2018: "Relational inductive biases, deep learning, and graph networks". extremely well written, very clear, excellent graphics, and with code. highly recommended! paper: code: :

    Poništi
  10. proslijedio/la je Tweet
    18. sij

    Awesome interactive demos of different MCMC algorithms:

    Poništi
  11. proslijedio/la je Tweet
    17. sij

    After a year of dev, I am *extremely* excited to share this step-by-step tutorial Goal: to be the *easiest* intro to preserving, Deep Learning It's in I hope you enjoy it

    Poništi
  12. proslijedio/la je Tweet
    16. sij

    Getting into spaced repetition for memory thanks to and ’s work. It feels like unsupervised vs supervised learning Normal reading is unsupervised Spaced repetition provides labels you get tested on at successive epochs, to minimize memory loss

    Poništi
  13. proslijedio/la je Tweet
    16. sij

    The 1st paper of my PhD is out today in ! We show that word contexts can enhance letter representations in early visual cortex With , peter hagoort& Paper: TL;DR? Let me unpack it in a few (or so) tweets👇

    Prikaži ovu nit
    Poništi
  14. 14. sij

    Just when I thought I had discovered everything about ... `st.balloons()` 🙌

    Poništi
  15. proslijedio/la je Tweet
    12. sij
    Odgovor korisniku/ci

    has some fantastic ML explainers in this vein — this is my go to resource for teaching new analysts the core concepts for decision trees:

    Poništi
  16. proslijedio/la je Tweet

    Loving this trend of impressive new scientific sites. What else is in this vein? - : learn quantum computing - : learn ML - : interactive AI journal - : Medium for scientific publishing

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    12. sij
    Poništi
  18. proslijedio/la je Tweet
    11. sij

    Current image datasets are getting very large and pre-training on them is time consuming. We are releasing Neural Data Server (NDS), a search engine for transfer learning data! Webservice: Paper:

    Poništi
  19. proslijedio/la je Tweet
    11. sij

    A visual proof why 1+3+5+...+(2n-1)=n² ⚪⚫⚪⚫⚪⚫ ⚫⚫⚪⚫⚪⚫ ⚪⚪⚪⚫⚪⚫ ⚫⚫⚫⚫⚪⚫ ⚪⚪⚪⚪⚪⚫ ⚫⚫⚫⚫⚫⚫

    Poništi
  20. proslijedio/la je Tweet
    10. sij

    Very happy to share our latest work accepted at : we prove that a Self-Attention layer can express any CNN layer. 1/5 📄Paper: 🍿Interactive website : 🖥Code: 📝Blog:

    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:

    ·