Abstract
This chapter introduces a few daily life problems, which lead to the concept of abstract neuron and neural network. They are all based on the process of adjusting a parameter such as a rate, a flow, or a current that feeds a given unit (tank, transistor, etc.), which triggers a certain activation function. The adjustable parameters are optimized to minimize a certain error function. At the end of the section we shall provide some conclusions, which will pave the path to the definition of the abstract neuron and neural networks.
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
Notes
- 1.
As we shall see in a future chapter, this type of activation function is known under the name of ReLU.
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). Introductory Problems. In: Deep Learning Architectures. Springer Series in the Data Sciences. Springer, Cham. https://doi.org/10.1007/978-3-030-36721-3_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-36721-3_1
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)