NNTRAIN

Description

Use NNTRAIN to train a back-propagation neural network for pattern recognition. The neural-network functions, NNCREAT, NNTRAIN, and NNCLASS implement the process of supervised classification of multispectral imagery using training sites.

Parameters

Name	Type	Length	Value range
InputNN: Input neural-network segment *	Raster port	1 - 1
BitmapNN: Input training sites to sample data *	Bitmap port	1 - 1
NNLayer: Neural-network layer to train *	BIN port	1 - 1
OutputNN: One or more layers used to train the neural network *	Bitmap port	1 - 1
OutBitNN: Training sites used to train the neural network *	Bitmap port	1 - 1
NNTrained: Trained neural-network layer *	BIN port	1 - 1
Momentum Rate for Neural Network	Float	0 - 1	0 - 1.0 Default: 0.9
Learning Rate for Neural Network	Float	0 - 1	0.0 - 1.0 Default: 0.1
Maximum Total Error	Float	0 - 1	0.0 - Default: 0.01
Maximum Individual Error	Float	0 - 1	0.0 - Default: 0.001
Maximum Number of Iterations	Integer	0 - 1	1 - Default: 1000
Listing Type	String	0 - 1	BRIEF | SHORT | FULL Default: SHORT
Report	String	0 - 192	See parameter description

* Required parameter

Parameter descriptions

InputNN: Input neural-network segment

The neural-network segment (type 180) from which to read the input neural-network data and that will receive the trained neural network.

BitmapNN: Input training sites to sample data

One or more input-bitmap layers that make up the training-site mask or masks.

NNLayer: Neural-network layer to train

The neural-network segment (type 180) from which to read the input neural-network data. The segment must be created with NNCREAT.

OutputNN: One or more layers used to train the neural network

On completion, this parameter contains one or more of the image layers used to create the trained neural-network layer.

OutBitNN: Training sites used to train the neural network

On completion, this parameter contains the training sites (type 181) used to create the trained neural-network layer.

NNTrained: Trained neural-network layer

On completion, this parameter contains the output layer (type 180) that receives the trained neural-network layer. The neural-network layer must be created by NNCREAT.

Momentum Rate for Neural Network

The momentum rate (between 0.0 and 1.0) for neural-network training. If no value is specified, a rate of 0.9 is applied by default. A high momentum rate allows for the specification of a higher learning rate without the risk of oscillation or non-convergence. The specified momentum rate is saved in the neural-network segment for future report generation.

This parameter is optional.

Learning Rate for Neural Network

The learning rate (between 0.0 and 1.0) for neural-network training. If no value is specified, a learning rate of 0.1 is applied by default. A higher learning rate speeds up the training, but increases the risk of oscillation or non-convergence of the training result. The specified learning rate is saved in the neural-network segment for future report generation.

Maximum Total Error

The maximum normalized total error to allow. If no value is specified, a maximum total error of 0.01 is applied by default. If this error occurs below the value specified, the neural-network processing stops and the NNTRAIN run terminates.

This parameter is optional.

Maximum Individual Error

The maximum individual error to allow for all samples. If no value is specified, a maximum individual error of 0.001 is applied by default. If this error occurs below the value specified for all samples, the neural-network processing stops and the NNTRAIN run terminates.

This parameter is optional.

Maximum Number of Iterations

The maximum number of iterations to run on the neural network. If no value is specified, a maximum number of iterations of 1000 is applied by default. If the number of iterations exceeds the value specified, the neural-network processing stops and the NNTRAIN run terminates.

This parameter is optional.

Listing Type

The report listing type.

This parameter is optional.

Report

Specifies where to direct the generated report.

Available options are:

• LOG: generates a report on the terminal (default)
• <modulename.RPT>: appends a report to the module's RPT file
• DISK: generates a report on file "IMPRPT.LST"

Details

NNTRAIN trains an existing neural-network segment created with NNCREAT for back-propagation neural-network processing using sample data from training sites. When the neural-network training reaches a specified maximum acceptable error or the maximum number of iterations, training terminates. NNCLASS uses the trained neural network to classify imagery.

The momentum rate (MOMEN) and learning rate (LEARN) for building the neural network can be specified. For more information, see Training later in this topic.

Typically, the neural network is trained when NNTRAIN completes when either of the first two conditions have been met. If NNTRAIN completes because it exceeds the maximum allowable number of iterations, NNTRAIN may need to be run again if the total normalized error is still too large.

LTYP (Listing Type) specifies whether to print a BRIEF report, where only the error plot is reported; a SHORT report, where the first 10 samples per class are reported; or a FULL report, where all samples are reported. A FULL report should be produced only if there are a few samples.

Training

Back-propagation neural networks need to be trained to learn the input patterns of interest. When the neural-network segment is first created by NNCREAT, the weights for the inter-unit connections are initialized to random values in the range of -0.5 to +0.5. If a classification is performed with NNCLASS before training the neural network, the classification results are completely random. (NNCLASS checks the number of training iterations and will not run if the neural network is untrained.)

Typically, back-propagation neural networks require a number of iterations (100 to 10000) before the interconnection weights stabilize enough to recognize the input patterns. If NNTRAIN terminates when the specified number of iterations (MAXIT) is reached and the specified individual error (MAXTERR or MAXIERR) has not been met, the network may need to be trained again with NNTRAIN. If it still does not converge, you may need to redefine the neural network (using different input channels, more accurate bitmaps, more input and hidden units, or more samples).

The learning and momentum rates affect how quickly the neural network stabilizes. A high learning rate (0.9) converges quickly, but may exit prematurely. A low learning rate (0.1) takes more iterations to train, but has less of a tendency to exit prematurely. The risk of using a high learning rate is that the modeling may oscillate and not stabilize. You can observe how different learning rates converge by examining the error plot in the output report.

The momentum rate can be used to speed up learning. A high momentum rate (0.9) trains with larger steps than a lower rate (0.1). Using a momentum term helps reduce oscillation between iterations and allows a higher learning rate to be specified without the risk of non-convergence.

Before running NNTRAIN, NNCREAT should be run to completion with the parameters defined as described in the corresponding NNCREAT Help topic.

References

The code for NNTRAIN was adapted from a program written by M. S. Klassen and Y. H. Pao (1989) and modified by A. Zhang (1993).