Package: neuralnetwork 0.1.0

neuralnetwork: Fast Compact Multilayer Perceptrons

A small multilayer perceptron implementation for 'R'. It supports regression and classification, multiple hidden layers, mini-batch training, Adam, SGD, momentum, Nesterov, RPROP, GRPROP and L-BFGS optimizers, dropout, L2 regularization, early stopping, convergence thresholds, gradient clipping, sample and class weights, callback hooks, target scaling and robust Huber loss for regression, 'Rcpp' forward-pass kernels, formula interfaces, model evaluation with balanced classification metrics, cross-validation, compact tuning, permutation importance, model persistence helpers, and 'S3' prediction methods. Methods follow Rumelhart, Hinton and Williams (1986) <doi:10.1038/323533a0>, with optimizers including Riedmiller and Braun (1993) <doi:10.1109/ICNN.1993.298623>, Nocedal (1980) <doi:10.1090/S0025-5718-1980-0572855-7>, and Kingma and Ba (2014) <doi:10.48550/arXiv.1412.6980>.

Authors:Feng Ji [aut, cre]