Description Usage Arguments Details Value
View source: R/ART_Update_Weights.r
Updates the weight matrix of an ART network.
1 | ART_Update_Weights(input, weight, categoryNumber, learningRate)
|
input |
Vector of size NumFeatures that contains the input signal into the network. |
weight |
Matrix of size NumFeatures-by-NumCategories which holds the weights of the network. |
learningRate |
Rate at which the network should learn new inputs. |
categoryNumer |
Number of the category that codes the current input. |
This function returns a new weight matrix that has "learned" the input in the given category, as well as a value correspoding to whether or not the weight matrix was changed (0 = no change; 1 = change).
The length of the INPUT vector must equal the number of rows in the WEIGHT matrix, the CATEGORYNUMBER must be in the range [1, NumCategories], and the LEARNINGRATE must be in the range [0, 1].
List containing the UPDATEDWEIGHT and WEIGHTCHANGE. The UPDATEDWEIGHT is a matrix of size NumFeatures-by-NumCategories that holds the new weights of the network after the input has been successfully learned. The WEIGHTCHANGE is a value (0 or 1) which relays whether or not the weight matrix was changed during this updating. Here, 0 represents no change and 1 represents a change.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.