Next: Discovery of new multi-sensory
Up: Past to Present: More
Previous: Addressing the role of
The ``self-supervised'' work makes two important contributions: It offers
a framework for thinking about the interaction between sensory
modalities and the role of feedback in learning, and it has the
potential to vastly improve machine learning algorithms, particularly opening
up the field to the use of unsupervised data. The major drawback with
traditional supervised machine learning algorithms is that they
require a lot of expensive hand-labeling of training patterns in order
to generalize well. Providing alternative ``self-supervised"
algorithms which supervise themselves through richer use of the input,
will allow collection of much more training data (for example through
the internet where information is abundant but unlabeled).
Virginia de Sa
2007-08-10