A simple NumPy feedforward neural networks builder
model = FNN(lossFunction = Loss.CE, inputs = 4)
model.normalize(x = True, y = False)
model.addLayer(activation = Activation.RELU, neurons = 4)
model.addLayer(activation = Activation.SIGMOID, neurons = 3)
model.addLayer(activation = Activation.SOFTMAX, neurons = 3)
model.train(x_train, y_train, epochs = 10000, rate = .01, batch_size = 5)
model.predict(x_test)
model.test(y_test)
y_train, y_test :
pandas.core.series.Series
x_train, x_test :pandas.core.frame.DataFrame
Usage | Features | Requirements | Notebook
- Sigmoïd
Activation.SIGMOID
- ReLU
Activation.RELU
- Softmax
Activation.SOFTMAX
- Categorical Cross Entropy
Loss.CE
- Mean Squared Error
Loss.MSE
- Rescaling (min-max normalization)
- Stochastic Gradient Descent :
batch_size = 1
- Mini-batch :
batch_size = n
- Batch :
batch_size = len(x_train.index)
- numpy
- pandas
- matplotlib