Machine Learning

Omar Hijab
Additional contact information
Omar Hijab: Temple University, Department of Mathematics

Chapter Chapter 7 in Math for Data Science, 2025, pp 391-474 from Springer

Abstract: Abstract In this chapter, we go over the structure of neural networks, in enough detail to write weight gradient code. Here the neural networks need not be layered, they are allowed any topology. Then we study gradient descent methods, and use them to train neural networks. We also analyze stochastic gradient descent, and gradient descent with momentum.

Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-031-89707-8_7

Ordering information: This item can be ordered from
http://www.springer.com/9783031897078

DOI: 10.1007/978-3-031-89707-8_7

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().