Package: neuralnetwork
Title: Fast Compact Multilayer Perceptrons
Version: 0.1.4
Authors@R: c(
    person(given = "Feng", family = "Ji",
           role = c("aut", "cre"), email = "f.ji@utoronto.ca")
    )
Description: A small multilayer perceptron implementation for 'R'. It
        supports regression and classification, multiple hidden layers,
        mini-batch training, adaptive moment estimation, stochastic
        gradient descent, momentum, Nesterov acceleration, resilient
        backpropagation and limited-memory quasi-Newton optimization,
        dropout, squared-weight 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 standard 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>.
License: MIT + file LICENSE
Encoding: UTF-8
Language: en-US
Depends: R (>= 4.1.0)
Imports: Rcpp
LinkingTo: Rcpp
Suggests: knitr, rmarkdown
VignetteBuilder: knitr
NeedsCompilation: yes
Packaged: 2026-10-13 13:48:28 UTC; root
Author: Feng Ji [aut, cre]
Maintainer: Feng Ji <f.ji@utoronto.ca>
Repository: https://trtfj.r-universe.dev
Date/Publication: 2026-10-10 18:43:14 UTC
RemoteUrl: https://github.com/cran/neuralnetwork
RemoteRef: HEAD
RemoteSha: 8fdb15c9f2a2e962a1884cace730f7d10c564b2a