Training a Restricted Boltzmann Machine for Classification by Labeling Model Samples.
- Publication type:
- Journal article
- Metadata:
-
- Autoren
- Malte Probst
- Franz Rothlauf
- Zeitschrift
- CoRR
- Datum der Veröffentlichung
- 2015
- Titel
- Training a Restricted Boltzmann Machine for Classification by Labeling Model Samples.
- Ausgabe der Zeitschrift
- abs/1509.01053
Data source: DBLP
- Other metadata sources:
-
- Abstract
- 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.
- Autoren
- Malte Probst
- Franz Rothlauf
- Autoren-URL
- http://arxiv.org/abs/1509.01053v1
- Schlüsselwörter
- cs.LG
- cs.LG
- Datum der Veröffentlichung
- 2015
- Datum der Datenerfassung
- 2015
- Datum, an dem der Datensatz öffentlich gemacht wurde
- 2015
- Titel
- Training a Restricted Boltzmann Machine for Classification by Labeling Model Samples
Files
1509.01053v1.pdf
Data source: arXiv
- Beziehungen:
- Property of