제어로봇시스템학회:학술대회논문집
- 제어로봇시스템학회 2001년도 ICCAS
- /
- Pages.157.6-157
- /
- 2001
Simplified neuron functions for FPGA evaluations of engineering neuron on gate array and analogue circuit
- Saito, Masayuki (Miyazaki Univ.) ;
- Wang, Qianyi (Miyazaki Univ.) ;
- Aoyama, Tomoo (Miyazaki Univ.)
- 발행 : 2001.10.01
초록
We estimated various neuron functions to construct of engineering neurons, which are the combination of sigmoid, linear, sine, quadric, double/single bended, soft max/minimum functions. These combinations are estimated by the property on the potential surface between the learning points, calculation speed, and learning convergence; because the surface depends on the inference ability of a neuron system; and speed and convergence are depend on the efficiency on the points of engineering applications. After the evaluating discussions, we can select more appropriate combination than original sigmoid function´s, which is single bended function and linear one. The combination ...
키워드