Reiichiro Nakano

@reiinakano

i like building awesome things with awesome people 🇵🇭 🇯🇵 fellows program

San Francisco
Vrijeme pridruživanja: kolovoz 2009.

Tweetovi

Blokirali ste korisnika/cu @reiinakano

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

  1. Prikvačeni tweet
    8. tra 2019.

    Style transfer without a specific style image. I minimize only the content loss from neural style transfer and directly optimize brushstrokes via backpropagation. In this case, "style" is an intrinsic property defined entirely by the artistic medium.

    Prikaži ovu nit
    Poništi
  2. prije 8 sati

    I wish all papers came with a video for each equation I don't understand

    Poništi
  3. proslijedio/la je Tweet
    26. sij

    Continuing to move the game forward . Much respect my brother 💪🏾 #33644

    Poništi
  4. 22. sij

    Is trax/flax/stax the new tf.layers/tf.contrib.layers/tf.contrib.slim?

    Poništi
  5. proslijedio/la je Tweet
    20. sij

    How to get into machine learning without a degree, alternatives to traditional education, building a portfolio, applying for ML jobs, interviews, getting into research, and indie research ideas. I had an ace chat with at . Enjoy!

    Poništi
  6. 14. sij

    Some personal news: I moved to San Francisco and joined the OpenAI Fellows Program! Super excited to learn from all the amazing people here. It's a dream come true to be able to do machine learning full-time!

    Poništi
  7. proslijedio/la je Tweet
    8. sij

    One of my wonderful PhD students, Ghanimat Azdahri, was on the plane that crashed in Tehran this morning. Ghanimat was on her way back to after visiting her family and traditional Indigenous territories in Iran over the December break. The students and I are in so much pain

    Prikaži ovu nit
    Poništi
  8. 29. pro 2019.

    I concur with this blog post. Independent research is not a good experience. The psychological toll failures take on you (rejection, failed expts, getting scooped) are magnified N times without other people to share it with.

    Poništi
  9. proslijedio/la je Tweet
    22. pro 2019.
    Odgovor korisnicima

    Four examples of recent papers that make me believe the community as a whole could hugely benefit from following Joelle's suggestions:

    Poništi
  10. 17. pro 2019.

    At , talking to a guy from DeepMind about how I can't reproduce their results because it's so resource intensive. "It's not too bad actually, we only use 16 GPUs, it's not like we use a cluster of TPUs or anything."

    Poništi
  11. 15. pro 2019.

    Vancouver was beautiful.

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

    Neural Painter by addresses the fact that human painters use brushstrokes, not pixels. What can we create (and learn!) if we impose these constraints? Lots of great examples on his website ()

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    14. pro 2019.

    PyTorch implementation of Neural Painters Cool talk by at ML for creativity workshop. He released a new library and notebooks for others to easily play around with neural painter algorithms!

    Poništi
  14. proslijedio/la je Tweet

    . combines concepts from SPIRAL and World Models to create a sample-efficient way to train a neural network via VAE or GAN approaches to simulate painting programs

    Poništi
  15. 13. pro 2019.

    . explaining why GANs are a special case of his 1990 work on unsupervised minimax

    Poništi
  16. 10. pro 2019.

    At the end he smiled and said "You guys have worn me out. It was great talking to all of you. It's nice to get a perspective of where the field is at." (from the person who basically invented the field) Then we took this selfie.

    Prikaži ovu nit
    Poništi
  17. 10. pro 2019.

    His top 5 most important problems in RL 1. Improving core RL algorithms. They should learn better. 2. State construction 3. Planning He couldn't remember the other two 😁

    Prikaži ovu nit
    Poništi
  18. 10. pro 2019.

    On evolution as a way to intelligence: "Evolution is evolution. Learning is learning. They're separate things. We don't need to go through evolution again to build a learning system"

    Prikaži ovu nit
    Poništi
  19. 10. pro 2019.

    On causality: "I don't know what they're talking about. I don't understand it. All I know are MDPs. The world is an MDP."

    Prikaži ovu nit
    Poništi
  20. 10. pro 2019.

    On theoretical guarantees: "I don't care about theoretical guarantees. Show me the empirical results. Throw the chicken into the engine" Presumably referencing the chicken gun used to fire chickens to test a jet engine's robustness

    Prikaži ovu nit
    Poništi
  21. 10. pro 2019.

    Today I had the opportunity to listen to Rich Sutton as he spoke to a few of us at the RL Social. He was incredibly nice and humble, patiently listening to all questions and responding thoughtfully. Very short thread of his insights (sadly I arrived quite late)

    Prikaži ovu nit
    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:

    ·