Specifically, a deep convolutional network is introduced to learn discriminative feature representations, which are directly used to generate hash codes and predict labels of images.
A critical problem is how to use the network structure and other extra information to build better classifiers to predict labels for the unlabeled nodes.
Fig. 2 Illustration of OHTWC adapted from [19] showing the use of offline and online classifiers to predict labels for an online task.
According to the idea of learning with label proportions [9 11], we can learn a model to predict labels of the individual samples by grouping the training samples and providing proportions of the labels in each group.
We apply LR to predict labels for each instance.
The classification function should be able to correctly predict labels of new samples.
As described above, such homogenous systems predict labeling patterns where the diameter of patches has a direct linear relationship with the size of an injection uptake zone.
Two uncertainty measures based on the base classifier predictions and the inconsistency of a predicted label set, respectively, were defined to select the most informative examples.
I put it into a linear machine learning-classifier, and I then, for a new test point, will get out a predicted label.
