BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//OneJoy//events//EN
BEGIN:VEVENT
UID:onejoy-event-80469@onejoy
DTSTAMP:20261023T090317Z
DTSTART:20261107T200000Z
DTEND:20261107T220000Z
SUMMARY:Probability and Machine Learning
LOCATION:
DESCRIPTION:Why do we train classifiers on cross-entropy?\n\nLast time we showed that MSE isn't an arbitrary rule. It falls out of assuming Gaussian noise on a continuous target. So what happens when the target isn't a number at all\, but a label: cat or dog\, spam or not\, one of ten digits?\nSame recipe\, new distribution. Once you ask "what distribution generates a label?"\, cross-entropy basically derives itself\, and so does the reason it has "entropy" in its name.\nIn this focused hour\, we'll trace exactly wher\nhttps://onejoy.io/event/80469
URL:https://onejoy.io/event/80469
END:VEVENT
END:VCALENDAR