Transformers, explained: Under…
Use the Google Fonts in your t… Previous post Use the Google Fonts in your t…
Dynamic elements Axure widget … Next post Dynamic elements Axure widget …

47 thoughts on “Transformers, explained: Under…

  1. From 5:28, shouldn't it be the following:
    "when the model outputs the word “économique,” it’s attending heavily to both the input words “European” and “Economic.” "?

    For européenne, I see that it is attending only to European. Please let me know if I am missing something here. Thanks for the great video.

  2. I’m very confused. You clearly state here that this system is not just a chatbot, yet now that one of your employees have claimed the system is sentient you have reverted to just calling it a “chatbot”. I’m very concerned 😦 Please don’t delete my comment. Just help us understand what you’ve created. Your company does many wonderful things and the fact you’ve even been able to build this system is remarkable

  3. I'll jump on where others are doing the same – would love advice for someone who understands half the concepts that are alluded to as complex naturally and the innovation feels obvious I'm unsure how to break into the space without some guidance or connection between having exactly that great natural grasp but wildly anxious that language and logic are strengths and math is a mental turn off. For someone needing that type of translation/guide where my approach is language usage & finer cues what is the key terms to get to that understanding? Hate being fascinated and all the tools to play in this space and being unable to start because how I approach topics so welcome any advice.

  4. The invention of transformers seems to have jump-started a revolutionary acceleration in machine learning! Between the models you mentioned here, plus the way transformers are combined with other network architectures in DALL-E 2, OpenAI Jukebox, PaLM, Chinchilla/Flamingo, Gato — it seems like adding a transformer to any model produces bleeding-edge, state-of-the-art-or-better performance on basically any tasks.

    Barring any major architecture innovations in the future, I wonder if transformers end up being the key we need to reach human levels of broad-range performance after all 🤔

Leave a Reply

Your email address will not be published. Required fields are marked *


The reCAPTCHA verification period has expired. Please reload the page.

error: Content is protected !!