MIT 6.S191: Uncertainty in Deep Learning

[@ajit60w]

O.O.D means x was not even in the training set. P_test(y.x) n.eq P_train (y.x) may also mean wrong classification or open set i.e. not seen during training(feature vector not within bounds of vectors in the training set)

[@vimukthirandika872]

Thank you MIT

[@zigzag4273]

Hey Alex. Hope you're well. Is the 2023 course going to be free too? If yes, when does it go live?

[@AAmini]

Thanks! We are actually announcing the premiere today! The first release will be March 10 and a new lecture will be released every Friday at 10am ET.

[@TheEightSixEight]

Please post the slides as indicated in the URL descriptor. Thank you.

[@gulsenaaltntas5398]

You can find the slides from the NeurIPS tutorial here: docs.google.com/presentation/d/1savivnNqKtYgPzxrqQU8w_sObx1t0Ahq76gZFNTo960

[@QuantAI-kp8xt]

Very well done. Thank you.

[@vyacheslavli9254]

In the deep ensemble method the uncertainty corresponds to which particular classifier? Is it an assumption that the resulting uncertainty corresponds to the arcitecture with a near to optimal hyperparameters? It rationally should but overall sounds very handwavy. On top of that it is an uncertainty of the classifier evaluated on a training domain. How does it change on the OOD dataset?

[@thatapuguy2768]

Can someone answer my basic question? The speaker defines confidence as predicted probability of correctness. I am guessing this is NOT the same as yprob, which is predicted probability of postive class that a trained model returns for every test instance. So, how does one get an estimate the confidence?

[@anvarkurmukov2438]

If you are referring to 13:30, then for a binary classification confidence is exactly what you are saying, p(y=1|x).

[@SunilKalmady]

​@anvarkurmukov2438 Thanks for answering. I guess it is a bit about terminology. In this notion of confidence, overfitted models will confidently make wrong predictions. I was referring to uncertainity in those predictions aka confidence bounds of predicted scores. I have since figured out how to estimate those by bootstrapping.

[@nikteshy9131]

Спасибо )) MIT ))))))

[@drxplorer778]

This tutorial saved my ass

[@user-wr4yl7tx3w]

he is really sloppy in his explanation. not really trying to be clear.