Abstract
In classification problems a neural network has to be able to classify clusters, i.e., to assign a label with each cluster. These labels can be either natural numbers, points in the space or vectors, belonging to a label space. The classification procedure is equivalent to being able to learn a “cluster splitting function” or a decision map. The training set provides labels with each cluster. This assignment defines a decision map. The network will be able to classify the testing data by learning this decision map, i.e., to state to which cluster testing points belong to.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Calin, O. (2020). Classification. In: Deep Learning Architectures. Springer Series in the Data Sciences. Springer, Cham. https://doi.org/10.1007/978-3-030-36721-3_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-36721-3_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36720-6
Online ISBN: 978-3-030-36721-3
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)