encog-java-core
encog-java-core copied to clipboard
jeffheaton
I'm looking at this Kaggle competition: http://www.kaggle.com/c/titanic-gettingStarted/data This is the training file: http://www.kaggle.com/c/titanic-gettingStarted/download/train.csv (CSV) I tried to use this simple code (mostly taken from the NormalizeFile example): ``` public class...
Hey, I am unable to persist a HyperNeatNetwork and load it. .... once i try to load it... it thinks it's just a NEAT network.
Trying large numbers to see how big of a network I can set up. Trying to set up a nn with 50K inputs, one hidden layer with 50K neurons, and...
The architecture of Encog is really well designed with nice separations between the different parts of the networks and the training algorithms. It seems to be built to be very...
PNN trains to a low error rate, but overfitting seems to result, as the results on untrained data are not very good. This was discovered with Issue #78. PNN's do...
Consider reformulating the formuation, and coding, including threshold functions, using matrix expressions, instead of all the low level loops. Then the output error function can be more general, depending on...
Hello Jeff, while checking in the PNN source code from the Analyst, I saw, that there is an interface, to use unsupervised machine learning method available, but no interface to...
Code should be updated in C# and Java. See discussion here: http://www.heatonresearch.com/node/3577
randomize() method does not take a seed nor class provides an ability to supply Randomizer for testing
The problem is in the SimpleIntensityDownsample class. I modified TestImageDataSet test class I see (afther downsampling) the same result for different images also with non changes in image resolution (please...
