Paper accepted at Neurocomputing!
Extending the learning using privileged information paradigm to logistic regression is accepted at Neurocomputing
Have you ever discarded variables simply because they were not available at evaluation time?
These variables, known as privileged information, were first introduced in the learning process by Vapnik with Support Vector Machines (SVMs). Privileged variables are available as additional information at training time but they are not available at evaluation time. In our latest publication, the learning using privileged information (LUPI) paradigm is extended to logistic regression, one of the most widely used models in the clinical field. Furthermore, a real-world case study related to COVID-19 is included.
