TypeCNN: CNN Development Framework With Flexible Data Types
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F19%3APU132056" target="_blank" >RIV/00216305:26230/19:PU132056 - isvavai.cz</a>
Result on the web
<a href="https://www.fit.vut.cz/research/publication/11854/" target="_blank" >https://www.fit.vut.cz/research/publication/11854/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.23919/DATE.2019.8714855" target="_blank" >10.23919/DATE.2019.8714855</a>
Alternative languages
Result language
angličtina
Original language name
TypeCNN: CNN Development Framework With Flexible Data Types
Original language description
The rapid progress in artificial intelligence technologies based on deep and convolutional neural networks (CNN) has led to an enormous interest in efficient implementations of neural networks in embedded devices and hardware. We present a new software framework for the development of (approximate) convolutional neural networks in which the user can define and use various data types for forward (inference) procedure, backward (training) procedure and weights. Moreover, non-standard arithmetic operations such as approximate multipliers can easily be integrated into the CNN under design. This flexibility enables to analyze the impact of chosen data types and non-standard arithmetic operations on CNN training and inference efficiency. The framework was implemented in C++ and evaluated using several case studies.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/GA19-10137S" target="_blank" >GA19-10137S: Designing and exploiting libraries of approximate circuits</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Design, Automation and Test in Europe Conference
ISBN
978-3-9819263-2-3
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
292-295
Publisher name
European Design and Automation Association
Place of publication
Florence
Event location
Florencie
Event date
Mar 25, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000470666100053