thesehands

This is very much what dspy aims to address. Learning the incantations necessary to prompt well can be replaced by an algorithmic loop and example labelled cases.

systems also need noisy labels..

Transformers suffer from a quadratic bottleneck when calculating attention. Much work has been done investigating where memory can be saved by being more explicit on which attentions to calculate. This repo implements transformers with noted improvements

ha! no way - I just cited your paper in the comments without noticing you already had.

You can train programmers because there is time and there aren’t often lives at stake. Nurses have to hit the ground running in specialist areas where there is (I’d assume) often little time to acquire all necessary skills in order to perform at the required level

Is this not a timeseries classification, which they do implement?

At this point, the UK is very much in the same state as the US.

This is what the mypersonality dataset collected on Facebook was. The 5 axes of OCEAN - Openness, Conscientiousness, Extroversion, Agreeableness and Neuroticism for all those who took the test.

The T-Sne view for papers is a killer feature. Loved it for ICLR, glad more will be able to use it. Thank You!