Tweetovi

Blokirali ste korisnika/cu @suraj_donthi

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

  1. proslijedio/la je Tweet
    2. velj

    📏Founders: here's a handy chart of metrics VCs care about.

    Poništi
  2. proslijedio/la je Tweet
    23. sij

    Q-learning is difficult to apply when the number of available actions is large. We show that a simple extension based on amortized stochastic search allows Q-learning to scale to high-dimensional discrete, continuous or hybrid action spaces:

    Poništi
  3. proslijedio/la je Tweet
    8. sij

    Wasn't there a 'Black Mirror' episode about this?

    Poništi
  4. proslijedio/la je Tweet

    Do you use a VPN for privacy? Here's what you should know: –There's no way you or anyone else can tell if the VPN provider is selling your data. –If a VPN provider _doesn't_ sell your data, it will be outcompeted by those that do, and go out of business. It's a market for lemons.

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet

    A big reason why the gaming industry makes more 💰 than Hollywood: The model (for the most lucrative games) prices for elastic demand. LTV scales with consumer engagement as whales spend $100’s on Fortnite. In comparison, everyone pays the same monthly fee for Netflix.

    Poništi
  6. proslijedio/la je Tweet

    Thank you all for coming to the Deepfake Detection Challenge launch event at . Register today to download the full data set and participate in the challenge:

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

    Machine Learning in a company is 10% Data Science & 90% other challenges It's VERY hard. Everything in this guide is ON POINT, and it's stuff you won't learn in an ML book "Best Practices of ML Engineering" This is a lifesaver project

    Poništi
  8. proslijedio/la je Tweet
    10. pro 2019.

    'The India Watch' report by is 🤯. Gives a new perspective on internet and consumption by Bharat. Here are my 2 cents from the report.

    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    6. pro 2019.

    People are biased. Data is biased, in part because people are biased. Algorithms trained on biased data are biased. But learning algorithms themselves are not biased. Bias in data can be fixed. Bias in people is harder to fix.

    Poništi
  10. proslijedio/la je Tweet

    Finding the perfect gift for the entrepreneur in your life just became a little bit easier.

    Poništi
  11. proslijedio/la je Tweet

    Speeding justice: China’s judiciary embraces artificial intelligence cyber-courts, blockchain, cloud computing & verdicts delivered on chat- apps. WeChat has already handled more than 3 Mln legal cases. Hangzhou Internet Court has litigants arguing by Video-chat to AI judges.

    Poništi
  12. proslijedio/la je Tweet

    1/ HOW TO ASK FOR HELP AS AN ENTREPRENEUR -- Every week entrepreneurs reach out to me cold on LinkedIn, Twitter, and email asking for help. I love helping if I can! Unfortunately most people are terrible at asking for help. Here is how to do it properly.

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

    Introducing the SHA-RNN :) - Read alternative history as a research genre - Learn of the terrifying tokenization attack that leaves language models perplexed - Get near SotA results on enwik8 in hours on a lone GPU No Sesame Street or Transformers allowed.

    The SHA-RNN is composed of an RNN, pointer based attention, and a “Boom” feed-forward with a sprinkling of layer normalization. The persistent state is the RNN’s hidden state h as well as the memory M concatenated from previous memories. Bake at 200◦F for 16 to 20 hours in a desktop sized oven.
    The attention mechanism within the SHA-RNN is highly computationally efficient. The only matrix multiplication acts on the query. The A block represents scaled dot product attention, a vector-vector operation. The operators {qs, ks, vs} are vectorvector multiplications and thus have minimal overhead. We use a sigmoid to produce {qs, ks}. For vs see Section 6.4.
    Bits Per Character (BPC) onenwik8. The single attention SHA-LSTM has an attention head on the second last layer and hadbatch size 16 due to lower memory use. Directly comparing the head count for LSTM models and Transformer models obviously doesn’tmake sense but neither does comparing zero-headed LSTMs against bajillion headed models and then declaring an entire species dead.
    Poništi
  14. proslijedio/la je Tweet

    BodyPix 2.0 has been released, including multi-person segmentation support and a new live demo! To learn more, read the post by , , , , , , . Details here →

    Poništi
  15. proslijedio/la je Tweet
    15. stu 2019.

    When I published my PyTorch vs TensorFlow article, some people raised questions about whether it applied to non-NLP conferences. With NeurIPS posting all their papers, the answer is clear! Pytorch: 68 -> 166 papers Tensorflow: 91 -> 74 papers

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

    numpy has an `isin` function, but it doesn't let you pass a set to it, and as a result it's >1000 times slower than a list comprehension. This seems... odd. Am I missing something?

    Poništi
  17. proslijedio/la je Tweet
    9. stu 2019.

    XLM-RoBERTa: Amazing results on XLU and GLUE benchmarks from Facebook AI: large transformer network trained on 2.5TB of text from 100 languages. - ArXiv paper:...

    Poništi
  18. proslijedio/la je Tweet

    I've just released a fairly lengthy paper on defining & measuring intelligence, as well as a new AI evaluation dataset, the "Abstraction and Reasoning Corpus". I've been working on this for the past 2 years, on & off. Paper: ARC:

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

    Really excited to be sharing out latest and final report on GPT-2, which is being published alongside the 1.5B model and an improved detection baseline. Some brief reflections on the GPT-2 journey this year (thread):

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    29. lis 2019.
    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:

    ·