Design and specification of analog artificial neural network
| Autor: | Hassan Jouni, Gilles Jacquemod, Adnan Harb, Yves Leduc |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Artificial neural network
Matlab simulink Computer science General Chemical Engineering Activation function General Engineering General Physics and Astronomy Control engineering Total error Multiplier (Fourier analysis) ComputingMethodologies_PATTERNRECOGNITION General Earth and Planetary Sciences General Materials Science Breast cancer classification General Environmental Science |
| Zdroj: | SN Applied Sciences. 1 |
| ISSN: | 2523-3971 2523-3963 |
| DOI: | 10.1007/s42452-019-1243-4 |
| Popis: | In this paper, we have implemented, using Matlab Simulink an analog artificial neural network for breast cancer classification. Simulated results with ideal building blocks exhibit a total error of classification of 2.6%. Thanks to this value, we have modified Simulink models of the building blocks (i.e. multiplier, activation function and its derivative) in order to take into account their non-idealities. This study allows to determine their influence on the classification quality and to extract some specifications of these building blocks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink