Introduction to Representation Learning

Nada Lavrač, Vid Podpečan and Marko Robnik-Šikonja
Additional contact information
Nada Lavrač: Jožef Stefan Institute, Department of Knowledge Technologies
Vid Podpečan: Jožef Stefan Institute, Department of Knowledge Technologies
Marko Robnik-Šikonja: University of Ljubljana, Faculty of Computer and Information Science

Chapter Chapter 1 in Representation Learning, 2021, pp 1-16 from Springer

Abstract: Abstract Data scientists are faced with large quantities of data in different forms and sizes. Modern data processing techniques enable data fusion from different formats into a tabular data representation, where instances are represented as vectors. This form is expected by standard machine learning techniques such as rule learning, support vector machines, random forests, or deep neural networks. The key element of the success of modern representation learning methods, which transform data instances into a vector space, is that similarities of the original data instances and their relations are expressed as distances and directions in the target vector space, allowing for similar instances to be grouped based on these properties.

Date: 2021
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:978-3-030-68817-2_1

Ordering information: This item can be ordered from
http://www.springer.com/9783030688172

DOI: 10.1007/978-3-030-68817-2_1

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 ().