Ronald Richman

@RichmanRonald

Avid actuary but prefers to Excel. Interested in the application of deep learning to actuarial issues.

Johannesburg, South Africa
Vrijeme pridruživanja: studeni 2013.

Tweetovi

Blokirali ste korisnika/cu @RichmanRonald

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

  1. proslijedio/la je Tweet

    No natural graph? No problem! In episode 3 of Neural Structured Learning, Software Engineer Arjun Gopalan goes over how graphs can be synthesized from raw input data and used to train neural networks. 📈Watch now →

    Neural Structured Learning thumbnail
    Poništi
  2. proslijedio/la je Tweet
    prije 8 sati
    Poništi
  3. proslijedio/la je Tweet
    prije 23 sata

    I had the privilege of teaching a two-day workshop, Modern Geospatial Data Analysis with R, at the conference with an amazing group of TAs and participants. I've made the slides available here: , , ,

    Poništi
  4. proslijedio/la je Tweet
    4. velj

    An interesting read is the AAE Commentary Paper “Application of Professional Judgment by Actuaries” on page 12.

    Poništi
  5. proslijedio/la je Tweet
    3. velj

    Just received the printer proof for the cover of the Cambridge book. Forthcoming March 2020. It can be pre-ordered through Amazon: I hope you like it!

    Poništi
  6. proslijedio/la je Tweet
    3. velj

    My new center offers an applied forecasting course, starting on Feb 12, taught by myself and colleagues, including Nassim Taleb who will lecture on fat tails For details see For more info contact at Assimenos.n@unic.ac.cy

    Poništi
  7. proslijedio/la je Tweet
    3. velj

    "The measure and mismeasure of fairness: a critical review of fair machine learning" Corbett-Davies & Goel, If we want fair machine learning models, then first we're going to need a working definition of 'fair'...

    Poništi
  8. proslijedio/la je Tweet
    2. velj

    An actuarial view from on the M4 forecasting competition from . The next competition is in March 2020

    Poništi
  9. 2. velj
    Poništi
  10. proslijedio/la je Tweet
    1. velj

    Nice article by Michael Wallace on behalf of the in communicating clearly about measurement error concepts, consequences and potential solutions

    Poništi
  11. proslijedio/la je Tweet
    2. velj

    Our forthcoming book dives deep into different tabular modeling approaches, with many experiments. But I'll save you from reading the whole thing, and just show you the conclusion.

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

    The cool kids may be moving to TabNet and NODE, mind you, although I don't have real-world experience of these yet.

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    8. sij

    Since 2018, there has been immense interest in using Transformers for ASR. In my new blog post, I look at the various challenges and the solutions people have proposed.

    Poništi
  14. proslijedio/la je Tweet
    31. sij

    Why Random Forests can’t predict trends and how to overcome this problem. by

    Prikaži ovu nit
    Poništi
  15. proslijedio/la je Tweet
    22. sij

    My blogpost on how & why we use convolutional neural networks as a model of the visual system is probably the most read thing I've ever written and it's now been expanded & updated into a proper review article, complete with 136 references & 5 new figures!

    Poništi
  16. proslijedio/la je Tweet
    31. sij

    the is maintaining a github repo of talks! Lots of outstanding content here!!

    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    31. sij

    It was so fun being a part of and share some things about and the 😁 my slides are available at

    Poništi
  18. proslijedio/la je Tweet
    30. sij

    "object of type 'closure' is not subsettable" 👆 is a talk I gave at on getting unstuck and debugging in Slides and other resources are here:

    Poništi
  19. proslijedio/la je Tweet
    29. sij

    This video explains 's amazing new Meena chatbot! An Evolved Transformer with 2.6B parameters on 341 GB / 40B words of conversation data to achieves remarkable chatbot performance! "Horses go to Hayvard!"

    Poništi
  20. proslijedio/la je Tweet
    30. sij

    My first paper is on the arXiv! The main results are 1. quantum ensembles contain Deutsch-Jozsa which has implications for the complexity of the algorithm and 2. a particular quantum ensemble may be dequantised and further studied.

    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:

    ·