Tweetovi

Blokirali ste korisnika/cu @CezarSas

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

  1. proslijedio/la je Tweet
    30. sij

    I have now seen several classification tasks where a logistic regression model with bag-of-character n-grams tied or even beat neural (MTL, LSTM, CNN+attention) models. Any similar observations?

    Poništi
  2. proslijedio/la je Tweet
    28. sij

    Check out Meena, a new state-of-the-art open-domain conversational agent, released along with a new evaluation metric, the Sensibleness and Specificity Average, which captures basic, but important attributes for normal conversation. Learn more below!

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    24. sij

    When I see someone succeed, it inspires me, it makes me happy, it makes me proud to be human. Envy, derision are human inclinations too, but in the long-run they are counter-productive. Enjoying the success of others is the easiest way to be happy, second only to Baby Yoda pics.

    Poništi
  4. proslijedio/la je Tweet
    23. sij

    Google Dataset Search is now officially out of beta. "Dataset Search has indexed almost 25 million of these datasets, giving you a single place to search for datasets & find links to where the data is." Nice work, Natasha Noy and everyone else involved!

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    21. sij

    NLP community: Interpreting text models with Captum – an open source, extensible library for model interpretability built on PyTorch. Sentiment Analysis and interpreting BERT Models in the tutorials.

    Poništi
  6. proslijedio/la je Tweet
    15. sij

    v1.4: customizable mobile builds, Distributed Model Parallelism via experimental RPC API, Java Bindings, Chaining LRSchedulers Summary: Release Notes: Last release for Python 2 (bye bye!)

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

    I often meet research scientists interested in open-sourcing their code/research and asking for advice. Here is a thread for you. First: why should you open-source models along with your paper? Because science is a virtuous circle of knowledge sharing not a zero-sum competition

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet

    I believe the goal of a research field should be to stop being primarily a research field, and instead move into the real world. Become an industry. Deep learning has achieved just that: academic research now represents less than 10-15% of users of deep learning.

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    20. pro 2019.
    Poništi
  10. proslijedio/la je Tweet
    13. pro 2019.

    What ngrams most predict outcome Y controlling for confounds C? Blog post & python package. for text via feature selection & adversarial learning. Predict Y from C then predict Y from Y_hat + text. Pull features from trained model weights.

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    5. pro 2019.

    I've been thinking about the software stack for machine learning. Tools I'd love to see. 1. Pip for pretrained models. 2. Version control for datasets. 3. GPU-friendly CI. Travis CI, Circe CI don't support GPUs. Jenkins is a pain. 4. Fast dataframes. Why is Pandas so slow?

    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:

    ·