Deep Learning: Principles and Training Algorithms

Charu Aggarwal
Additional contact information
Charu Aggarwal: International Business Machines, IBM T. J. Watson Research Center

Chapter Chapter 4 in Neural Networks and Deep Learning, 2023, pp 119-163 from Springer

Abstract: Abstract The great power of deep learning models comes with computational challenges. One key point is that the backpropagation algorithm is rather unstable to minor changes in the algorithmic setting, such as the initialization point used by the approach. This instability is particularly significant when one is working with very deep networks.

Date: 2023
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:978-3-031-29642-0_4

Ordering information: This item can be ordered from
http://www.springer.com/9783031296420

DOI: 10.1007/978-3-031-29642-0_4

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 ().