Abstract
This chapter covers the basics of neural networks, a.k.a. deep learning. We discuss various foundational topics as follows: gradient-based optimization of input and parameters of the function (Section 5.1), linear models (Section 5.2), deep and dense neural network (Section 5.3), activation functions (Section 5.4), loss functions (Section 5.5), and optimization (Section 5.6) and regularization (Section 5.7) techniques. Finally, we summarize the chapter in Section 5.8.
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
Rights and permissions
Copyright information
© 2021 Rahul Bhalley
About this chapter
Cite this chapter
Bhalley, R. (2021). Neural Networks. In: Deep Learning with Swift for TensorFlow. Apress, Berkeley, CA. https://doi.org/10.1007/978-1-4842-6330-3_5
Download citation
DOI: https://doi.org/10.1007/978-1-4842-6330-3_5
Published:
Publisher Name: Apress, Berkeley, CA
Print ISBN: 978-1-4842-6329-7
Online ISBN: 978-1-4842-6330-3
eBook Packages: Professional and Applied ComputingProfessional and Applied Computing (R0)Apress Access Books