Detail publikace

TypeCNN: CNN Development Framework With Flexible Data Types

REK, P. SEKANINA, L.

Originální název

TypeCNN: CNN Development Framework With Flexible Data Types

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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. 

Klíčová slova

convolutional neural network, software library, data type, deep learning

Autoři

REK, P.; SEKANINA, L.

Vydáno

26. 3. 2019

Nakladatel

European Design and Automation Association

Místo

Florence

ISBN

978-3-9819263-2-3

Kniha

Design, Automation and Test in Europe Conference

Strany od

292

Strany do

295

Strany počet

4

URL

https://www.fit.vut.cz/research/publication/11854/

BibTex

@inproceedings{BUT156845,
  author="Petr {Rek} and Lukáš {Sekanina}",
  title="TypeCNN: CNN Development Framework With Flexible Data Types",
  booktitle="Design, Automation and Test in Europe Conference",
  year="2019",
  pages="292--295",
  publisher="European Design and Automation Association",
  address="Florence",
  doi="10.23919/DATE.2019.8714855",
  isbn="978-3-9819263-2-3",
  url="https://www.fit.vut.cz/research/publication/11854/"
}