encog-java-core
encog-java-core copied to clipboard
jeffheaton
Hi! description: Referring to the API document of ''org.junit.Test'' , the correct API of ''AssertEquals'' is ''assertEquals(Object expected, Object actual)''. However, we detect that some assertions in your test code...
The function `Train.getLastGradient()` will return an array containing only zeros, if it is called after `Train.iteration()`. This is still true even if `Train.calculateGradients()` is called right before. Also, inside the...
https://github.com/jeffheaton/encog-java-core/blob/06bed745403a1a670675b606b6ae483fbf7a6b97/src/main/java/org/encog/neural/freeform/training/FreeformPropagationTraining.java#L160 should this be: fromNeuron.addTempTraining(0, layerDelta); since the existing stored value is not always zero (from previous iterations of the same training). unit tests still pass after this change.
EncogUtility.convertCSV2Binary does not use the header parameter. False is hard coded in the logic. ``` public static void convertCSV2Binary(final File csvFile, final File binFile, final int inputCount, final int outputCount,...
Hey, I have created a Network like this: `nn = new BasicNetwork(); nn.addLayer(new BasicLayer(null, true, 21)); nn.addLayer(new BasicLayer(new ActivationSigmoid(), true, 200)); nn.addLayer(new BasicLayer(new ActivationSigmoid(), true, 200)); nn.addLayer(new BasicLayer(new ActivationSigmoid(), true,...
There seems to be no problem when training my network because it converges and falls below 0.01 error. However when I load my trained network, and introduce the evaluation set,...
In Ken Stanley's original NEAT paper, the following is specified: "Species then reproduce by first eliminating the lowest performing members from the population. The entire population is then replaced by...
I forked the code because I noticed a few places that mistakenly use Double.MIN_VALUE for comparison. But Double.MIN_VALUE is not the lowest negative value for double. Double.NEGATIVE_INFINITY is. I say...
First of all, encog is wonderful! When running the HyperNEAT example, `gradle runNEATBoxes`, from the encog-java-examples, I kept getting a NullException error. But in the .NET version, it works fine....
Hello, I tried to use the CrossValidateSunspot example with LevenbergMarquardtTraining, which caused an java.lang.IndexOutOfBoundsException: Exception in thread "main" java.lang.IndexOutOfBoundsException: Index: 249, Size: 249 at java.util.ArrayList.rangeCheck(ArrayList.java:635) at java.util.ArrayList.get(ArrayList.java:411) at org.encog.ml.data.basic.BasicMLDataSet.getRecord(BasicMLDataSet.java:253) at...
