Lecture 1 | Machine Learning (Stanford)
StanfordYouTube ↗
Further reading 4
What can images teach without labels? →Unsupervised learning looks for structure in observations. Learning features from image patches shows what that structure can look like before labels enter the task.Where does the learning signal come from? →Finding patterns in unlabeled data and choosing actions from rewards both dispense with a teacher giving the right answer. Only the latter must account for the consequences of a decision.Where does AlphaGo get experience? →Describe the task, experience and performance measure before examining the algorithm. AlphaGo provides distinct examples of experience from human games and self-play.Why can’t a policy classify each move in isolation? →An action changes the next situation and thus the choices and rewards still available. The dependence is temporal even when the delay is short.
Caption notes
Ng contrasts learning from labeled examples, discovering structure in unlabeled data and learning sequential decisions from rewards.
Original passages · 5
should you spending more time collecting more data or is it the case that you already have enough datathis actually turned out to be a mix of supervised and unsupervised learningthe consequence of trashing it may not happen until much latera computer program is set to learn from an experienceI'm not going to tell you what the right answer is