Sebastian Raschka

@rasbt

Asst. Prof. of Statistics . Machine Learning & Deep Learning researcher. Author of 'Python Machine Learning' & open source contributor.

Madison, Wisconsin
sebastianraschka.com
Vrijeme pridruživanja: listopad 2012.
95 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @rasbt

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

  1. Prikvačeni tweet
    5. lip 2019.

    Just reorganized and uploaded all the TensorFlow and PyTorch models and methods I implemented for teaching in a fresh GitHub repo -- 80 Jupyter notebooks in total :)

    31 reply 782 proslijeđena tweeta 2.822 korisnika označavaju da im se sviđa
    Poništi
  2. prije 8 sati

    An amazing animation by (as always ;) )

    1:00
    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).
    1 reply 1 proslijeđeni tweet 14 korisnika označava da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    prije 15 sati

    I made an illustration for my class of why you need separate validation and training sets and I'm quite happy with it. Has anyone illustrated this similarly before?

    14 replies 68 proslijeđenih tweetova 482 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    3. velj
    Odgovor korisniku/ci

    is another option

    7 proslijeđenih tweetova 18 korisnika označava da im se sviđa
    Poništi
  5. 3. velj

    Given that data loading can be a major bottleneck in many DL projects, this sounds like an interesting project to check out: "Accelerating Pytorch with Nvidia DALI" --> "on small models it's ~4X faster than the Pytorch dataloader"

    1 reply 36 proslijeđenih tweetova 186 korisnika označava da im se sviđa
    Poništi
  6. proslijedio/la je Tweet
    1. velj

    Even for science and medical applications, I am becoming weary of fine statistical modeling efforts, and believe that we should standardize on a handful of powerful and robust methods. An opinionated thread to give context for 1/8

    Odgovor korisnicima @bradpwyble @talyarkoni i sljedećem broju korisnika: 2
    I'm totally with you. We should just tell people to stop worrying and use Gradient-Boosted Decision Trees. With enough data, they just work. Almost not kidding
    35 proslijeđenih tweetova 135 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    28. sij

    Introducing the new Thinc, a refreshing functional take on deep learning! 🔮 Static type checking 🔥 Mix , & ⛓️ Integrated config system 🧮 Extensible backends incl. JAX (experimental) 🧬 Variable-length sequences & more

    18 replies 230 proslijeđenih tweetova 731 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    21. pro 2019.

    Building ML library for quants... Thanks for a new brick in the wall! 👍

    7 proslijeđenih tweetova 37 korisnika označava da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    28. sij

    💥 Starting the 2020 edition of 's Deep Learning class with ~200 students! 🤩 This year we *will* end up with annotated ✏️ video recordings 🎥 and publishable lecture notes 📖, as we're putting the extra effort to renew 🌟 and reorganise 🧐 the material. – mjesto: NYU Courant Institute of Mathematical Sciences

    Korisnici , i
    19 replies 196 proslijeđenih tweetova 1.081 korisnik označava da mu se sviđa
    Poništi
  10. 28. sij

    2/2 totally agree with this. At the same I do think that systems/architectures like this are useful though. Maybe not for sequence-to-sequence modeling but goode olde classification -- automating mundane tasks like document categorization etc.

    1 proslijeđeni tweet 8 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  11. 28. sij

    "GPT-2 and the Nature of Intelligence" via : "[...]upon careful inspection, it becomes apparent the system has no idea what it is talking about: it cannot follow simple sequence of events nor reliably have any idea what might happen next." 1/2

    1 reply 4 proslijeđena tweeta 29 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    25. sij

    AMA Announcement: Inviting any/all questions for Sebastian Raschka, . Sebastian was kind enough to allow questions from AMA for an upcoming ep. on the Chai Time Data Science Show. Please send them as replies to this tweet. Thanks in advance! 🍵

    6 replies 10 proslijeđenih tweetova 46 korisnika označava da im se sviđa
    Poništi
  13. 25. sij

    Generative Adversarial Networks are a pretty active appl. and research field, and I am really glad that there are the occasional reviews that summarize recent developments: "A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications"

    105 proslijeđenih tweetova 439 korisnika označava da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    25. sij

    2/2 If you have received a copy like that and 's customer support is unable to help, please let know. If you already bought the book on Amazon, we would also really welcome reviews about the book itself (in addition to feedback about Amazon)

    5 replies 1 proslijeđeni tweet 2 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    25. sij

    Seeing the reviews on , I am really disappointed to see that (who prints Packt titles on demand) also seemed to have shipped copies with the font upside down. Hope these are only a few exceptions. 1/2

    1 reply 2 proslijeđena tweeta
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  16. 25. sij

    2/2 If you have received a copy like that and 's customer support is unable to help, please let know. If you already bought the book on Amazon, we would also really welcome reviews about the book itself (in addition to feedback about Amazon)

    5 replies 1 proslijeđeni tweet 2 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. 25. sij

    Seeing the reviews on , I am really disappointed to see that (who prints Packt titles on demand) also seemed to have shipped copies with the font upside down. Hope these are only a few exceptions. 1/2

    1 reply 2 proslijeđena tweeta
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. 25. sij

    Great deal if you are interested in the 3rd Ed :). Btw if you are interested in the print copy, & I recommend ordering that from Packt directly as well -- seems to have poor quality control & shipped books with water dmg etc, as it can be seen in the reviews :(

    The latest edition of ' Machine Learning' from & brings your skills in this crucial area of modern development up to date.
    9 replies 4 proslijeđena tweeta 56 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. 24. sij

    The Most Complete Brain Map Ever Is Here: A Fly's 'Connectome' -- "It took 12 years and at least $40 million to chart a region about 250 micrometers across—about the thickness of two strands of hair."

    18 proslijeđenih tweetova 82 korisnika označavaju da im se sviđa
    Poništi
  20. 23. sij

    After the 1st lecture this semester, (for the first time) a student asked the question: "But isn't deep learning bad for climate change?"--coincidentally, the following article was upl shortly after :) "AI Can Do Great Things—if It Doesn't Burn the Planet"

    5 replies 17 proslijeđenih tweetova 66 korisnika označava da im se sviđa
    Poništi
  21. proslijedio/la je Tweet
    22. sij

    Survey of machine-learning experimental methods at and Results of a poll and I ran, with some analysis and discussion of statistical power and reproducibility.

    24 proslijeđena tweeta 69 korisnika označava da im se sviđa
    Poništi

@rasbt još nije objavio nijedan Tweet.

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:

    ·