Published January 1, 2006
| Version v1
Conference paper
Open
Applications of CNN with trapezoidal activation function
Creators
- 1. TUBITAK, MAM, Gebze, Kocaeli, Turkey
- 2. Dogus Univ, Dept Elect & Commun Engn, Istanbul, Turkey
- 3. Istanbul Univ, Dept Elect & Elect Engn, Istanbul, Turkey
Description
This paper presents some applications of cellular neural network (CNN) scheme employing a new nonlinear activation function, called trapezoidal activation function (TAF). The new CNN structure can classify linearly nonseparable data points and realize Boolean operations (including XOR) by using only a single-layer CNN.
Files
bib-a8862d7a-a203-44df-ad28-8b7be45c3846.txt
Files
(127 Bytes)
| Name | Size | Download all |
|---|---|---|
|
md5:d01678ad85ca15bcd61dcda5207e5752
|
127 Bytes | Preview Download |