Neural Networks

Clemens Heitzinger ()
Additional contact information
Clemens Heitzinger: Technische Universität Wien, Center for Artificial Intelligence and Machine Learning (CAIML) and Department of Mathematics and Geoinformation

Chapter Chapter 13 in Algorithms with JULIA, 2022, pp 365-396 from Springer

Abstract: Abstract Artificial neural networks were first conceived decades ago and have been an important part of machine learning and artificial intelligence ever since. The basic idea behind neural networks is to combine linear combinations and nonlinear functions into layers such that they can approximate arbitrary functions. Neural networks have been used to great effect for example in image classification and recognition once the computational power and suitable algorithms to train large neural networks had become available. In this chapter, we implement a neural network and train it using backpropagation in a fully selfcontained program. Using tens of thousands of scanned images, we train the neural network to recognize handwritten digits and discuss important aspects of training neural networks.

Date: 2022
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:978-3-031-16560-3_13

Ordering information: This item can be ordered from
http://www.springer.com/9783031165603

DOI: 10.1007/978-3-031-16560-3_13

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 ().