> - A form of unsupervised learning where the data provides the supervision
> – In general, withhold some information about the data, and task the network with predicting it
> – The task defines a proxy loss, and the network is forced to learn what we really care about, e.g. a semantic representation, in order to solve it
> - A form of unsupervised learning where the data provides the supervision
> – In general, withhold some information about the data, and task the network with predicting it
> – The task defines a proxy loss, and the network is forced to learn what we really care about, e.g. a semantic representation, in order to solve it