The MLP training algorithm to use
Namespace: OpenCvSharp.CPlusPlus
Assembly: OpenCvSharp.CPlusPlus (in OpenCvSharp.CPlusPlus.dll) Version: 1.0.0.0 (1.0.0.0)
Syntax
Members
| Member name | Value | Description | |
|---|---|---|---|
| Zero | 0 | No flags [0] | |
| UpdateWeights | 1 | 1 - algorithm updates the network weights, rather than computes them from scratch (in the latter case the weights are initialized using Nguyen-Widrow algorithm). [CvANN_MLP::UPDATE_WEIGHTS] | |
| NoInputScale | 2 | algorithm does not normalize the input vectors. If this flag is not set, the training algorithm normalizes each input feature independently, shifting its mean value to 0 and making the standard deviation =1. If the network is assumed to be updated frequently, the new training data could be much different from original one. In this case user should take care of proper normalization. [CvANN_MLP::NO_INPUT_SCALE] | |
| NoOutputScale | 4 | algorithm does not normalize the output vectors. If the flag is not set, the training algorithm normalizes each output features independently, by transforming it to the certain range depending on the activation function used. [CvANN_MLP::NO_OUTPUT_SCALE] |
See Also