Bayes7

The popular information is always a great read for non-experts! https://www.nobelprize.org/prizes/chemistry/2026/popular-inf...

>"The first species of Paulinella was discovered on Dec. 24, 1894, in the sediments of a backwater of the Rhine River by the German biologist Robert Lauterborn. He named the genus after his stepmother, Pauline."

How can they say this without providing more background?

| „[…] was a friend telling me his LaTeX thesis took 90 seconds to compile towards the end“

Sure, but in order to iterate you won’t have to compile the whole document but can just keep the chapter you are working on by structuring it with \includes

Its a thing: https://www.nature.com/articles/s41377-024-01590-3

Would you mind sharing how it turned out useful?

thanks!

Is there any good article/paper that describes how it actually works or is implemented not just in high-level and hand-waving terms?

great project!

Check out sioyek, it’s great and can open epubs like normal pdfs:

https://sioyek.info/ https://github.com/ahrm/sioyek

This was a great read, thanks a lot! One a side note, any one has a good guess what tool/software they used to create the visualisations for matrix multiplications or memory outline?

Summarised by https://xkcd.com/2494

Okay, I see that for inference. But for training it shouldn't matter because I need to hold on to all my activations for my backwards pass anyways? But yeah, fair point!

"[...] modern neural network (NN) architectures have complex designs with many components [...]"

I find the Transformer architecture actually very simple compared to previous models like LSTMs or other recurrent models. You could argue that their vision counterparts like ViT are conceptually maybe even simpler than ConvNets?

Also, can someone explain why they are so keen to remove the skip connections? At least when it comes to coding, nothing is simpler than adding a skip connection and computationally the effect should be marginal?

ah I see, cool thanks!

hey, off topic but can you explain or link a post which explains what the benefits of the alias -> function definition are over just defining the function directly? Thanks!

Very cool! However, I often feel like the process of generating the question/answer necessary for the Anki card is an important part of the learning process because it forces you do deeply think about the material and reflect on it. So I think there is a trade-off involved

Robert Sapolsky's Human Behavioural Biology [0] It's like a (good) netflix series you can binge watch!

[0] - https://www.youtube.com/watch?v=NNnIGh9g6fA&list=PL150326949...