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>.
Versions across snapshots
| Version | Repository | File | Size |
|---|---|---|---|
0.1.0 |
rolling linux/jammy R-4.5 | neuralnetwork_0.1.0.tar.gz |
242.0 KiB |
0.1.0 |
rolling linux/noble R-4.5 | neuralnetwork_0.1.0.tar.gz |
243.4 KiB |
0.1.0 |
rolling source/ R- | neuralnetwork_0.1.0.tar.gz |
45.3 KiB |
0.1.0 |
latest linux/jammy R-4.5 | neuralnetwork_0.1.0.tar.gz |
242.0 KiB |
0.1.0 |
latest linux/noble R-4.5 | neuralnetwork_0.1.0.tar.gz |
243.4 KiB |
0.1.0 |
latest source/ R- | neuralnetwork_0.1.0.tar.gz |
45.3 KiB |
0.1.0 |
2026-04-23 source/ R- | neuralnetwork_0.1.0.tar.gz |
0 B |