Training a Restricted Boltzmann Machine for Classification by Labeling Model Samples
This approach addresses labeling efficiency in classification tasks by leveraging model samples to increase labeled examples and automate the identification of hard cases, though it is incremental as it builds on existing unsupervised and semi-supervised techniques.
The paper tackles the problem of training classification models by proposing a method that first trains a Restricted Boltzmann Machine unsupervised on unlabeled MNIST data, then manually labels model samples via a GUI, achieving performance competitive with semi-supervised learning.
We propose an alternative method for training a classification model. Using the MNIST set of handwritten digits and Restricted Boltzmann Machines, it is possible to reach a classification performance competitive to semi-supervised learning if we first train a model in an unsupervised fashion on unlabeled data only, and then manually add labels to model samples instead of training data samples with the help of a GUI. This approach can benefit from the fact that model samples can be presented to the human labeler in a video-like fashion, resulting in a higher number of labeled examples. Also, after some initial training, hard-to-classify examples can be distinguished from easy ones automatically, saving manual work.