English: Diagram which explains the motivation and use of feature learning. In the paradigm, implicit feature representations are learned through various methods by inputting either raw data such as text, or an initial (usually sparse) feature set. The result is a richer, often lower dimensionality feature representation which can boost performance when used as the input for more specific learning tasks. Common tasks include classification and regression which generally require supervised learning and therefore labels to tune the models predictions.
to share – to copy, distribute and transmit the work
to remix – to adapt the work
Under the following conditions:
attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
share alike – If you remix, transform, or build upon the material, you must distribute your contributions under the same or compatible license as the original.