John Prothero

@johnnyprothero

Machine Learning Software Engineer

Ashburn, VA
github.com/jprothero
Vrijeme pridruživanja: rujan 2017.
0 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @johnnyprothero

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

  1. proslijedio/la je Tweet
    3. velj

    Added ImageNet validation results for 164 pretrained models on several datasets, incl ImageNet-A, ImageNetV2, and Imagenet-Sketch. No surprise, models with exposure to more data do quite well. Without extra, EfficientNets are holding their own.

    156 proslijeđenih tweetova 678 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    31. sij

    CausalNex – Python library to infer causation rather than observing correlation By ( , @ntsaouthe) Github: Medium:

    24 proslijeđena tweeta 56 korisnika označava da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    29. sij

    New blog post: Contrastive Self-Supervised Learning. Contrastive methods learn representations by encoding what makes two things similar or different. I find them very promising and go over some recent works such as DIM, CPC, AMDIM, CMC, MoCo etc.

    8 replies 99 proslijeđenih tweetova 452 korisnika označavaju da im se sviđa
    Poništi
  4. proslijedio/la je Tweet
    22. sij

    Have you ever wondered what will be the ML frameworks of the '20s? In this essay, I examine the directions AI research might take and the requirements they impose, concluding with an overview of what I believe to be two strong candidates: JAX and S4TF.

    13 replies 128 proslijeđenih tweetova 521 korisnik označava da mu se sviđa
    Poništi
  5. proslijedio/la je Tweet
    19. sij

    I built my first python package: jupyterplot! Plot real-time results in Jupyter notebooks. It is founded on 's excellent python-lrcurve library. Effortless development and publishing with by and .

    7 replies 106 proslijeđenih tweetova 446 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    19. sij

    Help me Twitter. Best (reasonably technical) math/science podcasts?

    41 reply 48 proslijeđenih tweetova 362 korisnika označavaju da im se sviđa
    Poništi
  7. proslijedio/la je Tweet
    16. sij

    I did a deep-dive into Pages, and found it's possible to create a *really* easy way to host your own blog: no code, no terminal, no template syntax. I made "fast_template" to pull this together, & a guide showing beginners how to get blogging

    401 proslijeđeni tweet 1.665 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    14. sij

    How To Train Interpretable Neural Networks That Accurately Extrapolate From Small Data. Today we released a new paper that showcases how to do just that using Scientific Machine Learning () techniques to encode non-data scientific information.

    5 replies 81 proslijeđeni tweet 231 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  9. proslijedio/la je Tweet
    11. sij

    In our forthcoming book & course, you'll learn how to build a real deep learning web app from scratch, including downloading images using Bing's API. You'll also learn what can go wrong! (h/t )

    130 proslijeđenih tweetova 799 korisnika označava da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    6. sij

    I am extremely excited to announce (1) I've joined OpenAI to lead a large-scale effort into AI-generating Algorithms research, & (2) I'll be an Associate CS Professor at U. British Columbia in 2021, where I will continue to lead the OpenAI project. Both are dreams come true! 1/2

    89 replies 120 proslijeđenih tweetova 2.085 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    18. pro 2019.

    A Harvard undergrad used OpenAI’s GPT-2 to generate deepfake text comments for a political campaign. The results are astounding; some bot comments fooled 100% of the judges: This is exactly the dystopian use of GPT2 thatOpenAI was concerned about.

    19 replies 466 proslijeđenih tweetova 869 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    18. pro 2019.

    Introducing Generative Teaching Networks, which generate entirely synthetic data that is up to 9x faster to train on than real data!, enabling state-of-the-art Neural Architecture Search Led by w ,, & 1/

    8 replies 117 proslijeđenih tweetova 473 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    13. pro 2019.

    Want a sneak peak for what's next with Neural ODEs? I will be talking about Higher Order Autodiff in JAX. Work with , , and ! Program Transformations: Sat. 14, Room West 114 Poster: 12-14:00 Talk: 17:00-17:20

    6 replies 64 proslijeđena tweeta 320 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    6. pro 2019.

    Excited to share a recent collaboration with and . In this paper we were able to show Quality Diversity (QD) algorithms, such as MAP-Elites, can be greatly improved by leveraging ideas from the modern derivative-free optimizer CMA-ES.

    7 proslijeđenih tweetova 56 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    13. pro 2019.

    We're releasing "Dota 2 with Large Scale Deep Reinforcement Learning", a scientific paper analyzing our findings from our 3-year Dota project: One highlight — we trained a new agent, Rerun, which has a 98% win rate vs the version that beat .

    608 proslijeđenih tweetova 1.776 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    12. pro 2019.

    Slides available for my NeurIPS talk tomorrow (Friday. 9:30am, meta-learning workshop) "How Meta-Learning Could Help Us Accomplish Our Grandest AI Ambitions, and Early, Exotic Steps in that Direction." @neurips2019

    16 proslijeđenih tweetova 40 korisnika označava da im se sviđa
    Poništi
  17. proslijedio/la je Tweet
    2. pro 2019.

    I've been working with for a long time to create something that combines the best of Notebooks with the best of traditional software development approaches. It's called nbdev. We're releasing it today as open source. 1/

    522 proslijeđena tweeta 1.602 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    6. stu 2019.

    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:

    75 replies 1.255 proslijeđenih tweetova 3.666 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    6. stu 2019.

    Nice new article on novelty search, QD, open-ended algos, and AI-generating algorithms, including connections to Go-Explore, AlphaStar, IT&E, & more. Thanks for writing it and to , , & for nice comments.

    54 proslijeđena tweeta 145 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    5. stu 2019.

    Spleeter is an amazing open-source project from Deezer (the French Spotify) that uses Deep Learning to do source separation on musical tracks. Built with Keras and TensorFlow. It runs out-of-the-box on CPU! Blog post: Code:

    16 replies 379 proslijeđenih tweetova 1.379 korisnika označava da im se sviđa
    Poništi

@johnnyprothero 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:

    ·