Self-Taught Learning
From Ufldl
(→Learning features) |
(→Overview) |
||
| Line 49: | Line 49: | ||
a large collection of random images downloaded off the internet. This latter | a large collection of random images downloaded off the internet. This latter | ||
setting, in which the unlabeled data (random internet images) may be drawn from | setting, in which the unlabeled data (random internet images) may be drawn from | ||
| - | a different distribution than the labeled data, is called the | + | a different distribution than the labeled data, is called the '''self-taught |
| - | learning | + | learning''' setting. In the self-taught learning setting, it is far easier to |
obtain large amounts of unlabeled data, and thus leverage the potential of | obtain large amounts of unlabeled data, and thus leverage the potential of | ||
| - | learning from massive amounts of data. | + | learning from massive amounts of data. |
| - | + | ||
== Learning features == | == Learning features == | ||
