Artificial Neural Networks for Anomaly Detection
Rcpp module exposing C++ class ANN
Train an Autoencoding Neural Network
Compression plot
Decoding step
Encoding step
Train a Neural Network
Plot training and validation loss
Make predictions for new data
Print ANN
Read ANN object from file
Reconstruct data using trained ANN object of type autoencoder
Reconstruction plot
Check user input related to activation functions
Check the input data
Check user input related to loss function
Sets list with meta info, to be used in other checks
Check user input related to network structure
Check user input related to optimizer
Check user input related to training
Continue training of a Neural Network
Write ANN object to file
Training of neural networks for classification and regression tasks using mini-batch gradient descent. Special features include a function for training autoencoders, which can be used to detect anomalies, and some related plotting functions. Multiple activation functions are supported, including tanh, relu, step and ramp. For the use of the step and ramp activation functions in detecting anomalies using autoencoders, see Hawkins et al. (2002) <doi:10.1007/3-540-46145-0_17>. Furthermore, several loss functions are supported, including robust ones such as Huber and pseudo-Huber loss, as well as L1 and L2 regularization. The possible options for optimization algorithms are RMSprop, Adam and SGD with momentum. The package contains a vectorized C++ implementation that facilitates fast training through mini-batch learning.