Emil Wallner

@EmilWallner

internet-educated, independent ML researcher, and in residency . OOT

42 Paris | Google Paris ( )
Vrijeme pridruživanja: srpanj 2010.

Tweetovi

Blokirali ste korisnika/cu @EmilWallner

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

  1. Prikvačeni tweet
    10. sij 2018.

    I’m thrilled to share my latest deep learning project: Turning a design mockup into code. 💻 🤖 1) Give the trained neural network a design image 2) The network converts the image into HTML markup and renders it ↴ Article: Code:

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

    My Interview with The Creator of DeOldify, Jason Antic is live: We talk all about , NoGANs, ML and Software Engineering along with Jason's journey with DeOldify. Audio: Video:

    Poništi
  3. proslijedio/la je Tweet
    25. sij

    Emil’s Story as a Self-Taught AI Researcher An interview with with useful tips on structuring a curriculum, creating a portfolio, getting involved in research, and finding a job. 💯

    Poništi
  4. proslijedio/la je Tweet
    21. sij

    “At large companies, less than a few hires are self-taught in ML. Of those, most don’t come through the classic hiring channels. Due to the volume of applicants a large company faces, it’s hard for them to adjust to portfolio-centric hiring.”

    Poništi
  5. 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. proslijedio/la je Tweet
    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
    29. pro 2019.

    After getting published in ICLR as an Independent Researcher, I have received nearly 100 messages from others who are looking to do the same. So I wrote a blog post on why I decided to do it and my advice to others.

    Prikaži ovu nit
    Poništi
  8. 13. stu 2019.

    "I’m going to work on artificial general intelligence (AGI) ... For the time being at least, I am going to be going about it “Victorian Gentleman Scientist” style, pursuing my inquiries from home, and drafting my son into the work."

    Poništi
  9. 11. stu 2019.

    'The Measure of Intelligence' contradicts the compute-is-all-we-need narrative, adds historical context, and is accessible to a broad audience. Hats off to for creating clear and actionable suggestions to advance AGI. It's a must-read!

    Prikaži ovu nit
    Poništi
  10. 11. stu 2019.

    The ARC dataset has 400 training tasks and 600 evaluation tasks. Key features: - Only novel tasks in the evaluation set - Highly abstract - Similar to human IQ tests - 3 demonstrations per task - Fixed/limited training data - An explicit set of priors

    Prikaži ovu nit
    Poništi
  11. 11. stu 2019.

    Chollet created a dataset according to the best practice he outlined, the ARC. The dataset mimics the abstraction and reasoning portion in an IQ test (fluid intelligence). Examples:

    Prikaži ovu nit
    Poništi
  12. 11. stu 2019.

    To avoid local-generalization systems that artificially "buy" performance on a specific task, Chollet restricts priors to 'Core Knowledge' found in developmental science theory: such as elementary physics, arithmetic, geometry and a basic understanding of intentions.

    Prikaži ovu nit
    Poništi
  13. 11. stu 2019.

    Chollet uses Algorithmic Information Theory to quantify the programs and interactions, expressed below. 'The intelligence is the rate at which a learner turns its experience and priors into new skills at valuable tasks that involve uncertainty and adaptation.'

    Prikaži ovu nit
    Poništi
  14. 11. stu 2019.

    Below is an overview of skill-acquisition efficiency. A task could be chess, the situation is a board position, and the skill program is a frozen chess engine. Think of the intelligent system as a program synthesis engine for different tasks.

    Prikaži ovu nit
    Poništi
  15. 11. stu 2019.

    In section II.2, Chollet formalizes his central idea: "The intelligence of a system is a measure of its skill-acquisition efficiency over a scope of tasks, with respect to priors, experience, and generalization difficulty."

    Prikaži ovu nit
    Poništi
  16. 11. stu 2019.

    When humans are tested in different cognitive tests the results correlate with each other. This indicates that we an underlying meta-skill to learn skills, the g-factor. These are the abilities Chollet want to measure in the context of AI, starting with Broad Generalization.

    Prikaži ovu nit
    Poništi
  17. 11. stu 2019.

    Chollet thinks our task-centric idea of intelligence is a bottleneck to advance AGI. Instead, we should adopt Hernandez-Orallo take: “AI is the science and engineering of making machines do tasks they have never seen and have not been prepared for beforehand”.

    Prikaži ovu nit
    Poništi
  18. 11. stu 2019.

    Similarly, Chollet argues that AlphaZero, DeepMind's program synthesis engine for board games, is not flexible and general. He compares it to a hashtable that uses a locality-sensitive hash function. With unlimited simulation, you can map board positions with actions.

    Prikaži ovu nit
    Poništi
  19. 11. stu 2019.

    IBM's DeepBlue is not intelligent, but we consider humans who master chess intelligent. It's because we associate chess with a meta-skill, an aptitude for logical tasks such as math and reasoning. We often anthropomorphize AI systems in a similar way: task mastery = AGI.

    Prikaži ovu nit
    Poništi
  20. 11. stu 2019.

    In the 1970s, many thought that chess reflected the entire scope of rational human thought. Solving chess with computers would lead to major leaps in cognitive understanding. But after IBM's DeepBlue, they realized they didn't have a better understanding of human thinking.

    Prikaži ovu nit
    Poništi
  21. 11. stu 2019.

    François Chollet’s core point: We can't measure an AI system's adaptability and flexibility by measuring a specific skill. With unlimited data, models memorize decisions. To advance AGI we need to quantify and measure ***skill-acquisition efficiency***. Let’s dig in👇

    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:

    ·