Tweetovi

Blokirali ste korisnika/cu @iamknighton

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

  1. proslijedio/la je Tweet
    2. velj

    I've posted a Tutorial on using Runtime Compiled C++ with Dear ImGui and DirectX11 on Comes with full source code on Github, with branches for each stage of the tutorial along with videos.

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    3. velj

    Given that data loading can be a major bottleneck in many DL projects, this sounds like an interesting project to check out: "Accelerating Pytorch with Nvidia DALI" --> "on small models it's ~4X faster than the Pytorch dataloader"

    Poništi
  3. proslijedio/la je Tweet
    31. sij

    An Opinionated Guide to ML Research: “To make breakthroughs with idea-driven research, you need to develop an exceptionally deep understanding of your subject, and a perspective that diverges from the rest of the community—some can do it, but it’s hard.”

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    30. sij

    Towards Open-Set Semantic Segmentation of Aerial Images.

    Poništi
  5. proslijedio/la je Tweet
    29. sij

    After 2+ years in stealth, we’re excited to launch today! Thank you to our team, customers, partners and investors, we couldn’t have done it w/o your support and trust. Exciting milestone, even more exciting journey ahead!

    Poništi
  6. proslijedio/la je Tweet
    29. sij

    "Bringing Stories Alive: Generating Interactive Fiction Worlds” made a text-adventure game world generator. The online demo is live! Paper: Code: Demo:

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

    What if we see level generation as a game, where each action changes the level in some way? Well, we could use RL to learn to "play" level generation! We introduce Procedural Content Generation via Reinforcement Learning (PCGRL), a new paradigm for PCG.

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    Odgovor korisnicima

    We tie 6 strongly simplified RNN layers in a CPU-optimized transformer hybrid with very little quality loss. Been doing that for two years now in production, wrote about it only now :)

    Poništi
  9. proslijedio/la je Tweet
    28. sij

    Introducing , a 2.6B-param open-domain chatbot with near-human quality. Remarkably, we show strong correlation between perplexity & humanlikeness! Paper: Sample conversations:

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    27. sij

    Wow, more than 200 NLP datasets – this is gold. Made by Seen:

    Poništi
  11. proslijedio/la je Tweet
    26. sij

    This looks pretty interesting Neurons in Visual Cortex are Driven by Feedback Projections when their Feedforward Sensory Input is Missing

    Poništi
  12. proslijedio/la je Tweet
    26. sij

    A Large Scale Event-based Detection Dataset for Automotive.

    Poništi
  13. proslijedio/la je Tweet
    26. sij

    PyHessian from is a new scalable framework that enables fast computation of Hessian information for deep neural networks: "by computing finer-scale Hessian-based statistics, we show that in some cases conventional understanding ... is not correct"

    Poništi
  14. proslijedio/la je Tweet
    25. sij

    Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning by Jianyu Chen et al.

    Poništi
  15. proslijedio/la je Tweet
    25. sij

    Fascinating. I'm really surprised Google is using depthwise convs so much in their research, when it performs so badly on their TPUs.

    Poništi
  16. proslijedio/la je Tweet
    25. sij

    StyleGAN2 Ultimate Edition: ✅Conditional training ✅FP16 ✅Non-square and compressed TFRecord images ✅Colab Examples ✅Beta TPU/Swarm training ✅And More!

    Poništi
  17. proslijedio/la je Tweet
    24. sij

    We just released a large public dataset of >10k echocardiogram videos with clinical annotations . Great resource for the medical ML community!

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    23. sij

    I am teaching Applied Computational Genomics (geared towards early stage graduate students) again this semester. I am slowly updating the slides and posting recordings to youtube.

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

    Check out the new release of NumPyro . This includes an implementation of 's Block Neural Autoregressive Flow in JAX and its usage in MCMC. Also, let us know what you think about the new Sample Adaptive MCMC sampler.

    Poništi
  20. proslijedio/la je Tweet
    23. sij

    Do dendrites compute partial derivatives? Three options: (1) They do. (2) They don’t because it is too complex for dendrites. (3) Evolution found another way which violates everything we know about physics. I am in favour of (1) and very skeptical of (2) and (3).

    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:

    ·