Examples with NeuralNetworkError org.encog.neural.NeuralNetworkError used on opensource projects

Example 1 with NeuralNetworkError

use of org.encog.neural.NeuralNetworkError in project shifu by ShifuML.

the class FloatNeuralStructure method finalizeStruct.

/**
 * Build the synapse and layer structure. This method should be called afteryou are done adding layers to a network,
 * or change the network's logic property.
 */
public void finalizeStruct() {
    if (this.getLayers().size() < 2) {
        throw new NeuralNetworkError("There must be at least two layers before the structure is finalized.");
    }
    final FlatLayer[] flatLayers = new FlatLayer[this.getLayers().size()];
    for (int i = 0; i < this.getLayers().size(); i++) {
        final BasicLayer layer = (BasicLayer) this.getLayers().get(i);
        if (layer.getActivation() == null) {
            layer.setActivation(new ActivationLinear());
        }
        flatLayers[i] = layer;
    }
    this.setFlat(new FloatFlatNetwork(flatLayers, true));
    finalizeLimit();
    this.getLayers().clear();
    enforceLimit();
}

Example 2 with NeuralNetworkError

use of org.encog.neural.NeuralNetworkError in project shifu by ShifuML.

the class CacheBasicFloatNetwork method compute.

/**
 * Compute network score (forward computing). If cacheInputOutput is true, to cache first layer output in this
 * class. Then if cacheInputOutput is false, read value from cache and then use sum-current item to save CPU
 * computation.
 *
 * @param input
 *            input value array
 * @param cacheInputOutput
 *            if it is to cache first layer output or to use first layer output cache.
 * @param resetInputIndex
 *            if cacheInputOutput is false, resetInputIndex is which item should be removed.
 * @return output value as score.
 */
public final MLData compute(final MLData input, boolean cacheInputOutput, int resetInputIndex) {
    try {
        final MLData result = new BasicMLData(this.network.getStructure().getFlat().getOutputCount());
        compute(input.getData(), result.getData(), cacheInputOutput, resetInputIndex);
        return result;
    } catch (final ArrayIndexOutOfBoundsException ex) {
        throw new NeuralNetworkError("Index exception: there was likely a mismatch between layer sizes, or the size of the input presented to the network.", ex);
    }
}