Hao Tan

@HaoTan5

NLP @ UNC Chapel Hill

Chapel Hill, NC
cs.unc.edu/~airsplay/
Vrijeme pridruživanja: listopad 2016.
17 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @HaoTan5

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @HaoTan5

  1. proslijedio/la je Tweet
    20. sij

    "Controlling complexity is the essence of computer programming." - Brian Kernighan

    221 proslijeđeni tweet 635 korisnika označava da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    22. pro 2019.

    This mind-bending timelapse with the Milky Way stabilized shows the Earth is spinning through space. Credit:

    14.485 proslijeđenih tweetova 42.565 korisnika označava da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    2. pro 2019.

    What's hidden in an overparameterized neural network with random weights? If the distribution is properly scaled (e.g. Kaiming Normal), then it contains a subnetwork which achieves high accuracy without ever modifying the values of the weights... (/n)

    241 proslijeđeni tweet 844 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    30. stu 2019.

    Neurons spike back The Invention of Inductive Machines and the Artificial Intelligence Controversy Dominique Cardon, Jean-Philippe Cointet and Antoine Mazières : H / T : Carlos E. Perez

    4 proslijeđena tweeta 5 korisnika označava da im se sviđa
    Poništi
  5. proslijedio/la je Tweet
    30. stu 2019.

    I really like blog posts which try to teach the reader old ideas. This one is about ways to visualise concepts in information theory, mentioned (cautiously) in solution 8.8 in Mackay's book (remember, positive areas can be negative quantities!) By

    1 reply 132 proslijeđena tweeta 573 korisnika označavaju da im se sviđa
    Poništi
  6. 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.
    550 proslijeđenih tweetova 1.933 korisnika označavaju da im se sviđa
    Poništi
  7. proslijedio/la je Tweet
    25. stu 2019.

    New BAIR blog post on RoboNet! A dataset of multi-robot interactions that we hope will make pretraining the norm, and training your robot from scratch a thing of the past.

    1 reply 43 proslijeđena tweeta 159 korisnika označava da im se sviđa
    Poništi
  8. proslijedio/la je Tweet
    25. stu 2019.

    This has been 2 years and 3 papers in the making: direct mapping of natural language instructions and first-person observations to continuous velocity control. Yep, we learn the entire pipeline with a single interpretable neural model! ❤️

    34 proslijeđena tweeta 179 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    19. stu 2019.

    "Trained on 147M conversation-like exchanges, DialoGPT extends the transformer to attain a performance close to human both in terms of automatic and human evaluation in single-turn dialogue settings"

    1 reply 47 proslijeđenih tweetova 194 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    19. stu 2019.

    So I've made a new multimodal ML coding exercise & I'm so excited about it that I want to blog/share it w. everyone... but I can't because then it won't be a hiring test anymore 😭 🙃 ... please apply to join so I can share it with you! End-result of the ML test 👇

    138 proslijeđenih tweetova 825 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    19. stu 2019.

    The PRIOR team is considering intern applications for various research problems including robot navigation, commonsense reasoning, multi-agent coordination, vision & language planning, efficient neural networks, few shot reasoning and many more.

    10 proslijeđenih tweetova 45 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    19. stu 2019.

    Sam Bowman is giving an invited talk at ! Check out the live video at

    10 proslijeđenih tweetova 33 korisnika označavaju da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    17. stu 2019.

    Compose sklearn objects the way you compose layers in Keras. Neat.

    192 proslijeđena tweeta 808 korisnika označava da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    12. stu 2019.

    I'm starting a professorship in the CS department at UNC in fall 2020 (!!) and am hiring students! If you're interested in doing a PhD please get in touch. More info here:

    80 replies 154 proslijeđena tweeta 906 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    8. stu 2019.

    slides from my keynote talk at

    91 proslijeđeni tweet 366 korisnika označava da im se sviđa
    Poništi
  16. 4. stu 2019.

    Generated examples.

    1 proslijeđeni tweet 3 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. 4. stu 2019.

    Model: CNN -> Joint encoder -> comparative encoder -> attentive decoder.

    1 reply 4 proslijeđena tweeta 3 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. 4. stu 2019.

    Examples and statistics of the dataset.

    1 reply 1 proslijeđeni tweet 1 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. 4. stu 2019.

    Paper link: . Data available at: .

    1 reply
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  20. 4. stu 2019.

    . is now presenting their work on their paper about fine-grained image captioning. A dataset (i.e., Birds-to-Words) and a neural model (i.e., Neural Naturalist) are introduced.

    1 reply 1 proslijeđeni tweet
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi

@HaoTan5 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:

    ·