EUVIMEDEUVIMED entdecken
Crossref

Analog Learning Neural Network using Two-Stage Mode by Multiple and Sample Hold Circuits

Masashi Kawaguchi, Naohiro Ishii, Takashi Jimbo

International Journal of Software Innovation · 2014

DOI: 10.4018/ijsi.2014010105 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Software Innovation, 2014. Verfasst von Masashi Kawaguchi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 16 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the neural network field, many application models have been proposed. A neuro chip and an artificial retina chip are developed to comprise the neural network model and simulate the biomedical vision system. Previous analog neural network models were composed of the operational amplifier and fixed resistance. It is difficult to change the connection coefficient. In this study, we used analog electronic multiple and sample hold circuits. The connecting weights describe the input voltage. It is easy to change the connection coefficient. This model works only on analog electronic circuits. It can finish the learning process in a very short time and this model will enable more flexible learning.

Zitieren

APA

Kawaguchi, M., Ishii, N., & Jimbo, T. (2014). Analog Learning Neural Network using Two-Stage Mode by Multiple and Sample Hold Circuits. International Journal of Software Innovation. https://doi.org/10.4018/ijsi.2014010105

Vancouver

Kawaguchi M, Ishii N, Jimbo T. Analog Learning Neural Network using Two-Stage Mode by Multiple and Sample Hold Circuits. International Journal of Software Innovation. 2014. doi:10.4018/ijsi.2014010105

BibTeX
@article{Kawaguchi2014,
  author = {Kawaguchi, Masashi and Ishii, Naohiro and Jimbo, Takashi},
  title = {Analog Learning Neural Network using Two-Stage Mode by Multiple and Sample Hold Circuits},
  journal = {International Journal of Software Innovation},
  year = {2014},
  doi = {10.4018/ijsi.2014010105}
}
Kostenlos starten →