The proposed method is semi-supervised since it not only uses the supervised relevance feedback information but also exploits the unlabeled data.
During the supervised sessions feedback will be given regarding technique, exercise progression and modification, and management of injury/discomfort.
The proposed semi-supervised relevance feedback approach is also defined in terms of an iterative function f rf as following: A^{(t+1)} = f_{rf} left(A^{(t)},mathcal{R}^{(t)}, {I_{R}}^{(t)}, {I_{NR}}^{(t)}right). (2).
This type of training is known as predictive learning, supervised learning, or feedback learning (e.g., Garrison, Erdeniz, & Done, 2013; Van Hasselt, 2012).
Rank learning relies on supervised queries, relevance feedback or context information to achieve an adequate model to rank items like web pages, images, etc. Normally, rank aggregation is an unsupervised method that relies on multi-criteria ranks and tries to combine them to produce a consensus rank.
In supervised learning models, feedback fills the role of an external 'teacher', driving learning in a top-down manner [28].
Health workers felt that they were inadequately supervised, with no feedback on performance.
The research team was trained to administer assessments during an all-day class that included supervised practice and feedback.
The support tends to include simulated consultations, lots of feedback, supervised practice on the wards (also with immediate feedback from a member of staff)".
Participants stated that the method of logging procedures did not provide them with insights into whether or not the procedure was properly completed, nor if the procedure was supervised, nor if feedback was given.
