'Less Than One'-Shot Learning: Learning N Classes From M

'Less Than One'-Shot Learning: Learning N Classes From M
Sat, 24 Oct 2020 10:00:41 GMT

'Less Than One'-Shot Learning: Learning N Classes from M
2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

'Less Than One'-Shot Learning: Learning N Classes From M
Sun, 18 Oct 2020 20:12:12 GMT

Direct link to paper: https://arxiv.org/pdf/2009.08449.pdf Interesting paper, although the headline is of course sensational. The crux of the paper is that by using "soft labels" (for example a probability distribution rather than one-hot), it's possible to create a decision boundary that encodes more classes than you have examples. In fact, only two examples can be used to encode any finite number of classes. This is interesting because it means that, in theory, ML models should be able to learn decision spaces that are far more complex than the input data has traditionally been thought to…
Paper and discussion history. A mention is not an endorsement.