Ann: Difference between revisions
Jump to navigation
Jump to search
imported>Donal No edit summary |
imported>Donal No edit summary |
||
| Line 23: | Line 23: | ||
* '''nhid1''' : [{2}] Number of nodes in first hidden layer. | * '''nhid1''' : [{2}] Number of nodes in first hidden layer. | ||
* '''nhid2''' : [{2}] Number of nodes in second hidden layer. | * '''nhid2''' : [{2}] Number of nodes in second hidden layer. | ||
* '''maxseconds''' : [{ | * '''maxseconds''' : [{20}] Maximum duration of ANN training (seconds). | ||
* '''terminalrmse''' : [0. | * '''terminalrmse''' : [0.05] Termination RMSE value for ANN iterations (RMSE of scaled y). | ||
* '''terminalrmserate''' : [1.e- | * '''terminalrmserate''' : [1.e-9] Termination rate of change of RMSE per 100 iterations. | ||
* '''preprocessing''': {[] []} preprocessing structures for x and y blocks (see PREPROCESS). | * '''preprocessing''': {[] []} preprocessing structures for x and y blocks (see PREPROCESS). | ||
* '''compression''': [{'none'}| 'pca' | 'pls' ] type of data compression to perform on the x-block prior to calculaing or applying the SVM model. 'pca' uses a simple PCA model to compress the information. 'pls' uses either a pls or plsda model (depending on the svmtype). Compression can make the SVM more stable and less prone to overfitting. | * '''compression''': [{'none'}| 'pca' | 'pls' ] type of data compression to perform on the x-block prior to calculaing or applying the SVM model. 'pca' uses a simple PCA model to compress the information. 'pls' uses either a pls or plsda model (depending on the svmtype). Compression can make the SVM more stable and less prone to overfitting. | ||
Revision as of 15:29, 18 November 2013
Purpose
Predictions based on Artificial Neural Network (ANN) regression models.
Synopsis
- [model] = ann(x,y,options);
- [ypred] = ann(x,model,options);
- [ypred] = ann(x,y,model,options);
- [ypred] = ann(x,y, xt,yt, options);
Description
Build an ANN model from input X and Y block data using the specified number of layers and layer nodes. Alternatively, if a model is passed in ANN makes a Y prediction for an input test X block. The ANN model contains quantities (weights etc) calculated from the calibration data. If a model structure is passed in then these do not have to be re-calculated. The ANN is a Feedforward ANN with Resilient Backpropagation training. See [1] for further details. ANN is implemented using the Encog package [2] provided by Heaton Research, Inc, under the Apache 2.0 license.
Options
options = a structure array with the following fields:
- display : [ 'off' |{'on'}] Governs display
- plots: [ {'none'} | 'final' ] governs plotting of results, and
- waitbar : [ 'off' |{'auto'}| 'on' ] governs use of waitbar during analysis. 'auto' shows waitbar if delay will likely be longer than a reasonable waiting period.
- anntype : [{1} | 2] Number of hidden layers.
- nhid1 : [{2}] Number of nodes in first hidden layer.
- nhid2 : [{2}] Number of nodes in second hidden layer.
- maxseconds : [{20}] Maximum duration of ANN training (seconds).
- terminalrmse : [0.05] Termination RMSE value for ANN iterations (RMSE of scaled y).
- terminalrmserate : [1.e-9] Termination rate of change of RMSE per 100 iterations.
- preprocessing: {[] []} preprocessing structures for x and y blocks (see PREPROCESS).
- compression: [{'none'}| 'pca' | 'pls' ] type of data compression to perform on the x-block prior to calculaing or applying the SVM model. 'pca' uses a simple PCA model to compress the information. 'pls' uses either a pls or plsda model (depending on the svmtype). Compression can make the SVM more stable and less prone to overfitting.
- compressncomp: [1] Number of latent variables (or principal components to include in the compression model.
- blockdetails: [ {'standard'} | 'all' ], extent of predictions and residuals included in model, 'standard' = only y-block, 'all' x- and y-blocks.