public void ResetSpeedTest() { int iter = 1000; mlpMN = new MultiLayerMathsNet(seed, null, shapes, 1, initialValueWeights); mlp = new MultiLayer(shapes, seed, 1, null); var watch = System.Diagnostics.Stopwatch.StartNew(); for (int i = 0; i < iter; i++) { mlpMN.Reset(true); } watch.Stop(); var elapsedMs = watch.ElapsedMilliseconds; Debug.Log("Reset Time MathNet: " + elapsedMs); watch = System.Diagnostics.Stopwatch.StartNew(); for (int i = 0; i < iter; i++) { mlp.Reset(1.0f, true); } watch.Stop(); elapsedMs = watch.ElapsedMilliseconds; Debug.Log("Reset Time Array: " + elapsedMs); }
public void TestMultipleLayersFromAbstractClass() { ICsConfigurationBuilder cb = tang.NewConfigurationBuilder(); cb.BindImplementation(GenericType <MultiLayer> .Class, GenericType <LowerLayer> .Class); MultiLayer o = tang.NewInjector(cb.Build()).GetInstance <MultiLayer>(); Assert.IsNotNull(o); }
public NeuralGenTrainTask() { ISingleLayer <double>[] layers = new ISingleLayer <double> [2]; layers[0] = new SingleLayer(6, 6, new Neuro.MLP.ActivateFunction.BipolarTreshhold(), new Random()); layers[1] = new SingleLayer(6, 1, new Neuro.MLP.ActivateFunction.BipolarTreshhold(), new Random()); MultiLayer mLayer = new MultiLayer(layers); DifferintiableLearningConfig config = new DifferintiableLearningConfig(new Neuro.MLP.ErrorFunction.HalfEuclid()); config.Step = 0.1; config.OneImageMinError = 0.01; config.MinError = 0.5; config.MinChangeError = 0.0000001; config.UseRandomShuffle = true; config.MaxEpoch = 10000; SimpleBackPropogation learn = new SimpleBackPropogation(config); network = new MultiLayerNeuralNetwork(mLayer, learn); }
public void SetUp() { mlpMN = new MultiLayerMathsNet(seed, null, shapes, 1, initialValueWeights); mlp = new MultiLayer(shapes, seed, 1, null); }