Neural Network Function Approximator--a Modular Network Approach
碩士 === 東海大學 === 工業工程研究所 === 83 === Theoretically, MLP is a universal function approximator. However, the performance is not always acceptable. Besides, the network with different activation function can yield different performance behavior...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
1995
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/78263324928649295166 |