[HN Gopher] Transformers for software engineers
___________________________________________________________________
Transformers for software engineers
Author : datkinson
Score : 57 points
Date : 2022-04-01 21:43 UTC (1 days ago)
(HTM) web link (blog.nelhage.com)
(TXT) w3m dump (blog.nelhage.com)
| blueflow wrote:
| I hoped this would be an explanation of electricity, magnetism,
| the Lorentz force and induction.
| sthatipamala wrote:
| Thanks for this writeup! Software engineers should definitely
| learn about Transformers. They are a significant step-change in
| the advancement of deep learning. They've proven useful in
| multiple domains outside of natural language, including computer
| vision and audio.
|
| This opens up the world of multi-modal models which represent
| concepts by considering multiple types of input. The most popular
| one has been OpenAI's CLIP [0]
|
| If anyone's interested, I run a podcast and did an episode on
| Transformer models and their implications [1]. Check it out!
|
| [0] https://openai.com/blog/clip/ [1]
| https://www.youtube.com/watch?v=Kb0II5DuDE0
| dontreact wrote:
| Just a fun technical note:
|
| CLIP would be possible with any language and vision encoder.
|
| It turns out that transformers were the most efficient encoder
| choices available at the time but most likely the approach
| would have given interesting results with a resnet and some
| sort of convolutional language encoder. In fact the paper has a
| resnet as one model for the vision side.
| chaosprint wrote:
| Very good content! It's interesting that you use Rust here.
| f311a wrote:
| I think it's better to use other languages for pseudo code.
| Rust is not the easiest language to read and understand for
| people who never used it.
| nelhage wrote:
| (author here)
|
| I actually did a v0 writeup in Go, but I wanted a language that
| had a bit more powerful type system and more support for a
| fluent/functional style in some of the expressions. I was
| optimizing for what I know and felt was highly expressive; I've
| since gotten a bunch of feedback from people who are interested
| in the content but not comfortable reading Rust, so perhaps it
| wasn't the best choice.
___________________________________________________________________
(page generated 2022-04-02 23:00 UTC)