Matthias Kümmerer

@matthiaskue

Neuroscience, Machine Learning and Classical Music. Founding Member of .

Vrijeme pridruživanja: listopad 2013.

Tweetovi

Blokirali ste korisnika/cu @matthiaskue

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

  1. proslijedio/la je Tweet
    20. stu 2019.

    I am hiring a graduate student to join our group at the (full position, 4 years funding)! Please apply if you are interested in working on machine/deep learning and visual cognitive neuroscience. Details here: Please share/RT far and wide!

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    18. stu 2019.

    My 1st preprint! Can we measure semantic information in images? What’s its role in eye-movements control? Can meaning maps or help? With M. Kümmerer , T. Wallis , M. Bethge & Ch. Teufel. A thread [1/5]

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    3. stu 2019.

    VCD-Projekt "Wohnen leitet Mobilität": Quartiersgaragen statt Tiefgaragen machen Bauen und Wohnen billiger und können so bezahlbare Mieten sichern helfen.

    Poništi
  4. proslijedio/la je Tweet
    17. ruj 2019.

    Trying depth-mapping on abstract art. I don't know what you would call 'working properly' here, it's just fascinating to see a neural network try to interpret a Jackson Pollock painting as a 3D landscape. (Convergence, 1952)

    Prikaži ovu nit
    Poništi
  5. 14. ruj 2019.

    Looking forward to presenting my poster on "DeepGaze III: Using Deep Learning to Probe Interactions Between Scene Content and Scanpath History in Fixation Selection" today here at a fascinating (PS-1B.5)

    Poništi
  6. proslijedio/la je Tweet
    14. ruj 2019.

    Our manuscript on learning divisive normalization (DN) in V1 is out! Our interpretable, image-computable DN model learned orientation-specific normalization from natural stimuli and its accuracy came close to state-of-the-art deep neural networks.

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    11. ruj 2019.

    Want to learn about applying deep learning in a spectrum of comp. neuroscience questions? Join our speakers ( , , , , , T. Naselaris, J. Antolik) and us in our workshop () at .

    Prikaži ovu nit
    Poništi
  8. 14. ruj 2019.

    My colleague @MaxGuenthner talking about modelling V1 with divisive normalization at

    Poništi
  9. proslijedio/la je Tweet
    18. srp 2019.

    Can your object detector handle noise? What will your autonomous vehicle do when it's foggy? And more importantly: Is your D(rago)NN ready for Snow when Winter is Coming? Find out with our robust detection benchmark (Pascal, Coco & Cityscapes):

    Poništi
  10. proslijedio/la je Tweet
    17. srp 2019.

    'Pair Programming' with GPT-2 trained on 2 million GitHub files. Straightforward near-term practical use of deep learning. I wish they had better examples - for example, I bet if you name a variable Gryffindor it will suggest Hufflepuff for the next one!

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet

    Not how it works, I'm afraid.

    Poništi
  12. proslijedio/la je Tweet
    15. srp 2019.

    Why would anyone want to study topology? It's just--

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    12. srp 2019.

    Help me out twitterverse, which team chat/lab organisational tool do you use/recommend and why? Slack? Basecamp? Mattermost? Telegram? (please RT for visibility)

    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    11. srp 2019.

    Enjoying a ‘last dinner’ at this year’s with a brilliant group of people, including , , , Brian Cornell, Doris Braun, Karl Gegenfurtner, and Janis Kan. What a wonderful conference! Very much looking forward to the next one!! 🤓

    Poništi
  15. 11. srp 2019.

    It's great to be here at . Awesome talks on very diverse topics, great discussions and a very welcoming community

    Poništi
  16. proslijedio/la je Tweet
    10. srp 2019.

    We are delighted to announce that is expanding its involvement in ! A new Bosch campus is planned for , right next to the research facilities of the and . Bosch will invest around 35 million € and create jobs for 700 experts

    Poništi
  17. proslijedio/la je Tweet
    7. srp 2019.

    We developed gradient-based versions (L0, L1, L2 & Linf) of our Boundary adversarial attack that (1) resist gradient-masking, (2) perform better & are more query-efficient than SOTA (e.g. PGD or C&W) and (3) require virtually no hyperparameter tuning:

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    1. srp 2019.

    Article discussing our recent work investigating the properties of current state-of-the-art algorithms. Hope to see more in this line of research!

    Poništi
  19. proslijedio/la je Tweet
    26. lip 2019.

    This image contains 16 circles. They are in plain sight. But most likely your brain will interpret this picture in a way which makes them invisible.

    Poništi
  20. proslijedio/la je Tweet
    17. lip 2019.

    My lab is looking for postdocs! Experience in machine learning or 2P imaging is preferred! Please RT, and get in touch: mackenzie@post.harvard.edu

    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:

    ·