Repository owner: Modern Fortran (modern-fortran)

neural-fortran

Neural networks with dense and convolutional layers and gradient-based training.

Repository · Pinned source (b2073fa542c8) · Try in playground · Checked package example

GAMS classifications

About this package

Category: Machine learning
License: MIT

Topics: cnn, convolutional-networks, deep-learning, fortran, gradient-based-optimization, machine-learning, neural-network, neural-networks, parallel

Classification scope and review notes

G1 covers gradient-based network training. K remains broad because the package is not restricted to least-squares fitting.

Package dependencies

Resolved GitHub repositories used by the verified playground build, combining direct and indirect dependencies. This list does not describe internal module dependencies or native system libraries.

Required by this build

No additional GitHub package dependencies were recorded for this verified build.

Build record verified 2026-10-27.

Used by (0 selected packages)

No other selected build records this repository as a dependency. This is not a measure of usage outside the catalog.

Reviewed procedures

These mappings have pinned source evidence. A checked package example may exercise only some of them; source review is not a numerical benchmark.

network%train

Module: nf

G1b

G1b: verified

Derivatives / callbacks: internal backpropagation

Network-specific SGD with internal backpropagation, not a general scalar-objective callback solver. The checked driver calls network%train on one/two-input, two-output affine maps with full/stochastic batches; nonlinear networks and other optimizers remain unverified.

Pinned source: src/nf/nf_network.f90 · src/nf/nf_optimizers.f90 · src/nf/nf_network_submodule.f90

Author examples/tests: example/quadratic.f90

Load checked GAMS driver: gams-neural-affine-reference