Suzana Ilić

@suzatweet

Minds and Machines. 🧠 Founder Visiting Scientist -Toyota Collaboration Center

日本 東京
Vrijeme pridruživanja: prosinac 2009.

Tweetovi

Blokirali ste korisnika/cu @suzatweet

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

  1. Prikvačeni tweet
    28. lis 2019.

    We are honored and humbled to receive the Technology & Innovation Silver Award 2019 for our work at . This award is for our team, our contributors and the community alike! :)

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet

    MIT's new CS class teaches you things that all the other classes don't teach you, like... 🖥️Shell tools and scripting 🖥️Vim 🖥️Data wrangling 🖥️Command-line environment 🖥️Version control Watch all 11 lectures for free here:

    Poništi
  3. prije 11 sati

    Thank you to for providing the Tinker Edge T board for the community to explore and experiment with! 🙌 it's capable of performing four tera-operations per second (TOPS) using 0.5 watts per unit of computation!! 🤯

    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
    3. velj

    PyTorch for research, C++ for production?

    Poništi
  6. proslijedio/la je Tweet
    Odgovor korisniku/ci

    welcome! hope we collaboratively change PyTorch to be flexible enough to capture and productively try boundary-pushing ideas. A continuous loop of your feedback and contributions will help us descend the gradient correctly.

    Poništi
  7. prije 17 sati

    Our ML Math Reading Sessions with , and many more are so. much. fun. and the discussions are incredibly valuable. I collected a few resources that cover fundamental concepts – feel free to add to the list and send a PR.

    Poništi
  8. proslijedio/la je Tweet
    2. velj

    Tesla will hold a super fun AI party/hackathon at my house with the Tesla AI/autopilot team in about four weeks. Invitations going out soon.

    Poništi
  9. proslijedio/la je Tweet
    2. velj

    Wow: Google's "Meena" chatbot was trained on a full TPUv3 pod (2048 TPU cores) for **30 full days** - That's more than $1,400,000 of compute time to train this chatbot model. (! 100+ petaflops of sustained compute !)

    Poništi
  10. 3. velj

    If you have advice, tutorials or repos you'd like to share please do!⬇️We're starting monthly working sessions w/ and appreciate to read about things that worked (or didn't work)! We'll also share some things we'll try! Btw, first 'Edge AI Lab' will be held on Feb 15.

    Prikaži ovu nit
    Poništi
  11. 3. velj

    今日は:Chapter 6: Probability and Distributions

    Poništi
  12. 1. velj

    Excited to be one of the panelists at Google's IWD event in Tokyo and can't wait to meet and connect with many amazing women in tech! Applications are open until Feb 7. See you there? 😊💙

    Poništi
  13. 1. velj
    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    30. sij

    Flash a smile! 😁 We built a smile-detecting, voice controlled photo booth using Lite and . 📸 See how we did it →

    Poništi
  15. proslijedio/la je Tweet
    31. sij

    A few years ago TensorFlow looked indomitable. Now it's on the verge of being overtaken by Pytorch. OpenAI just announced it's standardizing on Pytorch, joining the likes of Tesla, Nvidia, and FB. Google hoped TensorFlow would cement its lead in ML. It may soon be a liability.

    Poništi
  16. proslijedio/la je Tweet
    31. sij

    What unreleased FSD Autopilot sees. Straight from Tesla Autopilot recruiting website.

    Poništi
  17. 1. velj

    Google friend: What are you doing tomorrow? Me: We're working on a search engine. Google friend: Oh that's easy! Me:

    Poništi
  18. 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
  19. proslijedio/la je Tweet
    31. sij

    Why Random Forests can’t predict trends and how to overcome this problem. by

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

    Transformers 2.4.0 is out 🤗 - Training transformers from scratch is now supported - New models, including *FlauBERT*, Dutch BERT, *UmBERTo* - Revamped documentation - First multi-modal model, MMBT from , text & images Bye bye Python 2 🙃

    Prikaži ovu nit
    Poništi
  21. proslijedio/la je Tweet

    Best advice I ever received from one of my professors 5 years ago: “The output of your PhD is not your thesis. The output is YOU”

    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:

    ·