Detail publikace

Mapping trained neural networks to FPNNs

Originální název

Mapping trained neural networks to FPNNs

Anglický název

Mapping trained neural networks to FPNNs

Jazyk

en

Originální abstrakt

This paper introduces a set of methods for mapping the trained neural networks into the lighted grid structured Field Programmable Neural Networks without the use of a training data set. These methods use information obtained from original neural networks such as a network structure, connection weights and biases. The principles of these mapping methods are described and the used grid FPNNs are explained. The results of experiments are presented and summarized.

Anglický abstrakt

This paper introduces a set of methods for mapping the trained neural networks into the lighted grid structured Field Programmable Neural Networks without the use of a training data set. These methods use information obtained from original neural networks such as a network structure, connection weights and biases. The principles of these mapping methods are described and the used grid FPNNs are explained. The results of experiments are presented and summarized.

BibTex


@inproceedings{BUT119876,
  author="Martin {Krčma} and Jan {Kaštil} and Zdeněk {Kotásek}",
  title="Mapping trained neural networks to FPNNs",
  annote="This paper introduces a set of methods for mapping
the trained neural networks into the lighted grid structured
Field Programmable Neural Networks without the use of a
training data set. These methods use information obtained from
original neural networks such as a network structure, connection
weights and biases. The principles of these mapping methods are
described and the used grid FPNNs are explained. The results of
experiments are presented and summarized.",
  address="IEEE Computer Society",
  booktitle="IEEE 18th International Symposium on Design and Diagnostics of Electronic Circuits and Systems",
  chapter="119876",
  doi="10.1109/DDECS.2015.50",
  edition="NEUVEDEN",
  howpublished="print",
  institution="IEEE Computer Society",
  year="2015",
  month="april",
  pages="157--160",
  publisher="IEEE Computer Society",
  type="conference paper"
}