Alexander Ecker

@alxecker

Neuroscience, Machine Learning, Computer Vision. Scientist and co-founder of and

Göttingen, Deutschland
Vrijeme pridruživanja: srpanj 2017.

Tweetovi

Blokirali ste korisnika/cu @alxecker

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

  1. proslijedio/la je Tweet
    16. sij

    Our new adversarial attack published @ NeurIPS 2019 is now available for Foolbox and CleverHans! The attack is SOTA in L0, L1, L2 & Linf, needs close to no hyperparameter tuning & is less susceptible to some types of gradient masking. Blog post @

    Prikaži ovu nit
    Poništi
  2. 14. pro 2019.

    If you’re at check out ‘s talk at 11:30 (East Ballroom A)

    Poništi
  3. proslijedio/la je Tweet
    12. pro 2019.

    Interested to build less artificial and more intelligent algorithms by learning from brains? Join our team! Our is hiring people at all levels with strong background in math and machine learning and with an entrepreneurial spirit interested in AI startups.

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    6. pro 2019.
    Poništi
  5. proslijedio/la je Tweet
    15. stu 2019.

    Check out our work on modeling the mouse visual system with pretrained networks trained on static object recognition. We find that equivalent random networks are just as useful! Come by if you’ll be at . Colab of

    Prikaži ovu nit
    Poništi
  6. 4. stu 2019.

    Check out our latest work with and : Optimal stimuli for mouse V1 are not Gabors. And Inception is not only a great movie ;-)

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

    you know and love ? the excellence cluster " - new perspectives for " is looking for a leader for its ML transfer center, helping to organize interactions with lots of scientific disciplines -

    Poništi
  8. 1. lis 2019.

    I meant! Should have double-checked.

    Prikaži ovu nit
    Poništi
  9. 1. lis 2019.

    Today I'm officially starting my new lab at focused on neural data science. Looking forward to new challenges and opportunities, but also a bit sad to leave a wonderful team at after >10 years.

    Prikaži ovu nit
    Poništi
  10. 18. ruj 2019.

    A comprehensive review and a very nice read!

    Poništi
  11. proslijedio/la je Tweet
    18. ruj 2019.

    Want to see how we bring interpretability to CNNs to predict V1 responses via end-to-end learning divisive normalization? Meet me at my poster W-56 With

    Poništi
  12. 16. ruj 2019.

    Heading to Berlin tomorrow for the and our workshop on Deep Learning in Neuroscience () co-organized with . Touch base if you want to meet.

    Poništi
  13. 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
  14. 11. ruj 2019.

    We’ll continue our tradition of workshops on Deep Learning in neuroscience at the in Berlin next week. Looking forward to cool talks!

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

    We are hiring!📣 Build exciting solutions with us & help shape a dynamic startup from its early days. If you know how to work with common deep learning frameworks & have an entrepreneurial mindset, join us as a Machine Learning Engineer.

    Poništi
  16. proslijedio/la je Tweet
    21. kol 2019.

    Our new manuscript w/ Katrin Franke, , and others is out on The temporal structure of the inner retina at a single glance, w/ axial 2PM scanning using an ETL and batch correction

    Poništi
  17. proslijedio/la je Tweet
    6. kol 2019.

    Happy to announce that our Robust Detection Benchmarking Toolkit is now part of the mmdetection toolbox! Benchmark:

    Poništi
  18. 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
  19. proslijedio/la je Tweet
    15. srp 2019.
    Poništi
  20. 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

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:

    ·