Abstract
So far, neural networks were useful for two main types of important problems: regression and classification problems. While pursuing regression a neural network with a one-dimensional output has been used, which is having a linear activation function in the output layer. In the case of classification problems it is useful to employ a neural network with a multidimensional output, which is having a softmax activation function in the output layer.
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). Generative Models. In: Deep Learning Architectures. Springer Series in the Data Sciences. Springer, Cham. https://doi.org/10.1007/978-3-030-36721-3_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-36721-3_19
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)