From my (limited) experience the OEIS titles lean strongly to the descriptive side too. But maybe also to avoid ambiguity regarding to which one is it from his sequences?
Hofstadter introduces several sequences in GEB, [0] may be an interesting submission on its own but I was especially captivated by this self-referencing one. Plus a title including both Hofstadter's sequence and a description is too long for HN and I preferred the descriptive one
Really neat visualization! And thanks for the tip on MCC.
Out of curiosity I plugged it to the same visualization (performance vs. class weight when optimized with BCE) and it behaves similar to F1, i.e. best without weighting.
Yeah it gets tricky. I think eventually it has to be about tradeoffs - no ML system can be 100% correct. I do think there's a "right" decision (up to a point) in the context of the product or business.
A fully connected layer has different weights for each feature (or position in input in your formulation). So the word "hello" would be treated completely differently if it were to appear in position 15 vs. 16, for example.
Attention, by contrast, would treat those two occurrences similarly, with the only difference depending on positional encoding - so you can learn generalized patterns more easily.
If the questions were pre-determined, which they're usually not. Reminds me of Huffman coding and the reason that compression challenges measure submissions looking at artifacts required to run them in addition to compressed size. I tend to agree with OP that this doesn't pass the smell test
Preparing my PyCon IL workshop, a competitive platform where you write code to solve simple games (think snake, pong etc.). Here are some screenshots: https://imgur.com/a/VDKfmjO
After it's done I hope to add a demo to my blog.
Cheers for all the interesting work going on here!
I can imagine it's a bit like if gravity suddenly changed to 0.9g. Everything(?) is easier but a lot of people would probably stumble around a bit before muscle memory, coordination etc. get used to the change.