> For the complete documentation index, see [llms.txt](https://ncxlib.gitbook.io/ncxlib/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ncxlib.gitbook.io/ncxlib/getting-started/api-documentation/overview.md). # Overview ## Module: ncxlib.neuralnetwork.neuralnet ### Classes [`NeuralNetwork(...)`](/ncxlib/getting-started/api-documentation/overview/neural-network.md) : Builds a Neural Network Class ### Functions [`Compile(...)`](/ncxlib/getting-started/api-documentation/overview/neural-network/_compile.md): Returns None. Compiles the Neural Network. [`add_layer(...)`](/ncxlib/getting-started/api-documentation/overview/neural-network/add_layer.md) : Adds a layer to the Neural Network [`forward_propagate_all(...)`](/ncxlib/getting-started/api-documentation/overview/neural-network/forward_propagate_all.md) : Forward Propagates all layers in layers list [`forward_propagate_all_no_save(...)`](/ncxlib/getting-started/api-documentation/overview/neural-network/forward_propagate_all_no_save.md) : Forward propagates all layers without saving layer information [`back_propagation(...)`](/ncxlib/getting-started/api-documentation/overview/neural-network/back_propagation.md) : Performs the back propagation on all layers starting from the output layer [`train(...)`](/ncxlib/getting-started/api-documentation/overview/neural-network/train.md) : Trains the model based on number of epochs, learning rate, input and labels [`predict(...)`](/ncxlib/getting-started/api-documentation/overview/neural-network/predict.md) : Predicts the output of the model [`evaluate(...)`](/ncxlib/getting-started/api-documentation/overview/neural-network/evaluate.md) : Provides an accuracy score across the model [`save_model(...)`](/ncxlib/getting-started/api-documentation/overview/neural-network/save_model.md) : Saves the model as an .h5 into desired file path [`load_model(...)`](/ncxlib/getting-started/api-documentation/overview/neural-network/load_model.md) : Loads the model back from the desired filepath. Must be an .h5 ## Module: ncxlib.neuralnetwork.activations ### Classes [`Activation(...)`](/ncxlib/getting-started/api-documentation/overview/activation.md) Abstract Base Class for all Activation classes [`ReLU(...)`](/ncxlib/getting-started/api-documentation/overview/activation/relu.md) : ReLU activation function class [`LeakyReLU(...)`](/ncxlib/getting-started/api-documentation/overview/activation/leakyrelu.md) : LeakyReLU activation function class [`Sigmoid(...)`](/ncxlib/getting-started/api-documentation/overview/activation/sigmoid.md) : Sigmoid Activation function class [`Softmax(...)`](/ncxlib/getting-started/api-documentation/overview/activation/softmax.md) : Softmax Activation function class [`Tanh(...)`](/ncxlib/getting-started/api-documentation/overview/activation/tanh.md) : Tanh Activation function class ## Module: ncxlib.neuralnetwork.layers ### Classes [`Layer(...)`](/ncxlib/getting-started/api-documentation/overview/layer.md) : Abstract Base Class for the Layer family [`InputLayer(...)`](/ncxlib/getting-started/api-documentation/overview/layer/inputlayer.md) Input Layer Class to the Neural Network [`FullyConnectedLayer(...)`](/ncxlib/getting-started/api-documentation/overview/layer/fullyconnectedlayer.md) : FullyConnectedLayer (hidden layers) within the Neural Network [`OutputLayer(...)`](/ncxlib/getting-started/api-documentation/overview/layer/outputlayer.md) : Output Layer of the Neural Network ## Module: ncxlib.neuralnetwork.losses ### Classes [`LossFunction(...)`](/ncxlib/getting-started/api-documentation/overview/lossfunction.md) : Abstract Base Class for all loss functions [`MeanSquaredError(...)`](/ncxlib/getting-started/api-documentation/overview/lossfunction/meansquarederror.md) : Mean Squared Error loss function [`BinaryCrossEntropy(...)`](/ncxlib/getting-started/api-documentation/overview/lossfunction/binarycrossentropy.md) : Binary Cross Entropy loss function [`CategoricalCrossEntropy(...)`](/ncxlib/getting-started/api-documentation/overview/lossfunction/categoricalcrossentropy.md) : Categorical Cross Entropy loss function\\ ## Module: ncxlib.neuralnetwork.optimizers ### Classes [`Optimizer(...)`](/ncxlib/getting-started/api-documentation/overview/optimizer.md) : Abstract Base Class for all optimizers [`SGD(...)`](/ncxlib/getting-started/api-documentation/overview/optimizer/sgd.md) : Stochastic Gradient Descent Optimizer [`SGDMomentum(...)`](/ncxlib/getting-started/api-documentation/overview/optimizer/sgdmomentum.md) : Stochastic Gradient Descent with Momentum Optimizer [`RMSProp(...)`](/ncxlib/getting-started/api-documentation/overview/optimizer/rmsprop.md) : RMS Prop Optimizer [`Adam(...)`](/ncxlib/getting-started/api-documentation/overview/optimizer/adam.md) : Adam Optimizer ## Module: ncxlib.neuralnetwork.initializers ### Classes [`Initializer(...)`](/ncxlib/getting-started/api-documentation/overview/initializer.md) : Abstract Base Class for all Initializers [`HeNormal(...)`](/ncxlib/getting-started/api-documentation/overview/initializer/henormal.md) : He Normal Initializer [`Zero(...)`](/ncxlib/getting-started/api-documentation/overview/initializer/zero.md) : Zero Initializer ## Module: ncxlib.preprocessing ### Classes [`PreProcessor(...)`](/ncxlib/getting-started/api-documentation/overview/preprocessor.md) : Abstract Base Class for all Preprocessors [`OneHotEncoder(...)`](/ncxlib/getting-started/api-documentation/overview/preprocessor/onehotencoder.md) : One Hot Encoding Preprocessors [`ImageRescaler(...)`](/ncxlib/getting-started/api-documentation/overview/preprocessor/imagerescaler.md) : Image Rescaler Preprocessor [`ImageGrayscaler(...)`](/ncxlib/getting-started/api-documentation/overview/preprocessor/imagegrayscaler.md) : Image Grayscaler Preprocessor [`Scaler(...)`](/ncxlib/getting-started/api-documentation/overview/preprocessor/scaler.md) : Abstract Base Class for Scalers [`MinMaxScaler(...)`](/ncxlib/getting-started/api-documentation/overview/preprocessor/minmaxscaler.md) : Min-Max-Scaler Preprocessor ## Module: ncxlib.dataloaders ### Classes [`DataLoader(...)`](/ncxlib/getting-started/api-documentation/overview/dataloader.md) : Abstract Base Class for all Dataloaders [`CSVDataLoader(...)`](/ncxlib/getting-started/api-documentation/overview/dataloader/csvdataloader.md) : CSV Data Loader [`ImageDataLoader(...)`](/ncxlib/getting-started/api-documentation/overview/dataloader/imagedataloader.md) : Image DataLoader ## Module: ncxlib.generators ### Functions [`random_array(...)`](/ncxlib/getting-started/api-documentation/overview/generators/random_array.md) : Returns random uniform array of data [`integer_array(...)`](/ncxlib/getting-started/api-documentation/overview/generators/integer_array.md) : Returns random integer array [`generate_training_data(...)`](/ncxlib/getting-started/api-documentation/overview/generators/generate_training_data.md) : Generates random training data with num of samples, features, labels, etc. ## Module: ncxlib.utils ### Function [`train_test_split(...)`](https://ncxlib.gitbook.io/ncxlib/getting-started/api-documentation/overview/utils/train_test_split) : splits the data into x\_train, x\_test, y\_train, y\_test [`k_fold_cross_validation(...)`](https://ncxlib.gitbook.io/ncxlib/getting-started/api-documentation/overview/utils/k_fold_cross_validation) : splits the data into k-folds for x\_train, x\_test, y\_train, y\_test and returns scores per fold