Options
Minimizing execution time of artificial neural networks on resource-restricted devices
Citation Link: https://doi.org/10.15480/882.8668
Publikationstyp
Master Thesis
Date Issued
2019-12
Sprache
English
Author(s)
Title Granting Institution
Technische Universität Hamburg
Place of Title Granting Institution
Hamburg
Examination Date
2019-12
Institute
TORE-DOI
Artificial Neural Networks are a key technology in today’s area of machine learning. They
impact various parts in our lives and are therefore important in many ways. Compressing
Artificial Neural Networks, in particular the weight matrices, by slightly manipulating them,
while maintaining accuracy has been studied in recent research. One of the most promising
methods called Deep Compression achieved remarkable compression rates. The reduction in
size by Deep Compression should also be beneficial for the execution time. In this work, the
benefit was studied with the objective of reducing the execution time on resource-restricted
hardware. Furthermore, the benefit of simpler fixed-point arithmetic was investigated in this
context. Based on deeper insights and practical evaluations of Deep Compression, this work
gives an assessment and guidance towards a minimum execution time of Artificial Neural
Networks.
impact various parts in our lives and are therefore important in many ways. Compressing
Artificial Neural Networks, in particular the weight matrices, by slightly manipulating them,
while maintaining accuracy has been studied in recent research. One of the most promising
methods called Deep Compression achieved remarkable compression rates. The reduction in
size by Deep Compression should also be beneficial for the execution time. In this work, the
benefit was studied with the objective of reducing the execution time on resource-restricted
hardware. Furthermore, the benefit of simpler fixed-point arithmetic was investigated in this
context. Based on deeper insights and practical evaluations of Deep Compression, this work
gives an assessment and guidance towards a minimum execution time of Artificial Neural
Networks.
DDC Class
004: Computer Sciences
620: Engineering
Loading...
Name
thesis_with_Identifier_and_license.pdf
Size
1.84 MB
Format
Adobe PDF