Caused by: java.lang.ArrayIndexOutOfBoundsException
at java.lang.System.arraycopy(Native Method) ~[?:1.8.0_121]
at org.encog.util.EngineArray.arrayCopy(EngineArray.java:107) ~[?:?]
at org.encog.neural.flat.FlatNetwork.compute(FlatNetwork.java:364) ~[?:?]
at org.encog.neural.networks.training.propagation.GradientWorker.process(GradientWorker.java:203) ~[?:?]
at org.encog.neural.networks.training.propagation.GradientWorker.run(GradientWorker.java:272) ~[?:?]
at org.encog.util.concurrency.PoolItem.run(PoolItem.java:59) ~[?:?]
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source) ~[?:1.8.0_121]
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source) ~[?:1.8.0_121]
... 1 more
This happens when i use the following code:
MLDataSet set = new BasicMLDataSet(doubles, MachineACCore.get().getPreferred());
Train train = new ResilientPropagation(MachineACCore.get().getNetwork(), set);
int epoch = 1;
do {
train.iteration();
System.out.println("Epoch #" + epoch + " Error: " + train.getError());
} while (train.getError() > 0.01);
For some reason, this exception is being thrown:
This happens when i use the following code:
The prefferred multidimensional array contains the following data: https://gist.githubusercontent.com/erosemberg/2aba103d1255b6dd162f7cec26b8c8f5/raw/772a81a4a7db6bbd8a8250cc05b48b93c4a6a22d/data%2520preferred
And the data being fed to it at that time was the following: https://gist.githubusercontent.com/erosemberg/e81aa9b094812605506a0c2674903a20/raw/5238fb57654dd3dede8f2041b2a827af8fe85ad8/data%2520one%2520time
The network being used looks like the following:
network being a BasicNetwork.
Could this be an issue with the network not having enough neurons assigned to it?