NN2SQL : Let SQL Think for Neural Networks

Faculty/Professorship: Data Engineering 
Author(s): Schüle, Maximilian  ; Kemper, Alfons; Neumann, Thomas
Title of the compilation: Lecture Notes in Informatics (LNI) : Proceedings ; P-331
Editors: König-Ries, Birgitta; Scherzinger, Stefanie; Lehner, Wolfgang; Vossen, Gottfried
Conference: BTW 2023 : 20th Conference on Database Systems for Business, Technology and Web, March 6 - 10, 2023, Dresden
Publisher Information: Bonn : Gesellschaft für Informatik e.V.
Year of publication: 2023
Pages: 183-194
ISBN: 978-3-88579-725-8
Language(s): English
DOI: 10.18420/BTW2023-09
Although database systems perform well in data access and manipulation, their relational model hinders data scientists from formulating machine learning algorithms in SQL. Nevertheless, we argue that modern database systems perform well for machine learning algorithms expressed in relational algebra. To overcome the barrier of the relational model, this paper shows how to transform data into a relational representation for training neural networks in SQL: We first describe building blocks for data transformation in SQL. Then, we compare an implementation for model training using array data types to the one using a relational representation in SQL-92 only. The evaluation proves the suitability of modern database systems for matrix algebra, although specialised array data types perform better than matrices in relational representation.
GND Keywords: SQL/92; Neuronales Netz; Automatische Differentiation
Keywords: SQL-92, Neural Networks, Automatic Differentiation
DDC Classification: 004 Computer science  
RVK Classification: ST 270   
Type: Conferenceobject
URI: https://fis.uni-bamberg.de/handle/uniba/58981
Release Date: 4. April 2023