Package: metANN 0.1.0

metANN: Metaheuristic and Gradient-Based Optimization for Neural Network Training and Continuous Problems

Provides tools for general-purpose continuous optimization and feed-forward artificial neural network training using metaheuristic and gradient-based optimization algorithms. The package supports benchmark function optimization, regression, binary classification, and multi-class classification with multilayer perceptrons. The package implements several optimization methods, including particle swarm optimization Kennedy and Eberhart (1995) <doi:10.1109/ICNN.1995.488968>, differential evolution Storn and Price (1997) <doi:10.1023/A:1008202821328>, grey wolf optimizer Mirjalili et al. (2014) <doi:10.1016/j.advengsoft.2013.12.007>, secretary bird optimization Fu et al. (2024) <doi:10.1007/s10462-024-10729-y>, and Adam Kingma and Ba (2015) <doi:10.48550/arXiv.1412.6980>.

Authors:Burak Dilber [aut, cre, cph], A. Fırat Özdemir [aut, ths]

metANN_0.1.0.tar.gz
metANN_0.1.0.zip(r-4.7)metANN_0.1.0.zip(r-4.6)metANN_0.1.0.zip(r-4.5)
metANN_0.1.0.tgz(r-4.6-any)metANN_0.1.0.tgz(r-4.5-any)
metANN_0.1.0.tar.gz(r-4.7-any)metANN_0.1.0.tar.gz(r-4.6-any)
metANN_0.1.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
card.svg |card.png
metANN/json (API)

# Install 'metANN' in R:

install.packages('metANN', repos = c('https://burakdilber.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/burakdilber/metann/issues

On CRAN:

3.00 score 62 exports 0 dependencies

Last updated from:9fa689ff6e. Checks:9 OK. Indexed: yes.

Target	Result	Time
linux-devel-x86_64	OK	106
source / vignettes	OK	127
linux-release-x86_64	OK	102
macos-release-arm64	OK	153
macos-oldrel-arm64	OK	196
windows-devel	OK	138
windows-release	OK	65
windows-oldrel	OK	69
wasm-release	OK	86

Exports:activation_leaky_relu activation_linear activation_relu activation_sigmoid activation_softmax activation_tanh as_activation as_loss as_metric as_metrics as_optimizer available_activations available_gradient_optimizers available_losses available_metaheuristics available_metrics available_optimizers count_parameters decode_weights dense_layer evaluate forward_pass initialize_weights is_activation is_architecture is_dense_layer is_layer is_loss is_metric is_mlp_architecture is_optimizer loss_binary_crossentropy loss_crossentropy loss_huber loss_log_cosh loss_mae loss_mse met_mlp met_optimize metann metric_accuracy metric_f1 metric_mae metric_mse metric_precision metric_r2 metric_recall metric_rmse mlp_architecture optimizer_abc optimizer_adam optimizer_de optimizer_ga optimizer_gwo optimizer_hybrid optimizer_info optimizer_pso optimizer_sboa optimizer_sgd optimizer_tlbo optimizer_woa plot_network

Dependencies:

Help page	Topics
Leaky Rectified Linear Unit Activation Function	activation_leaky_relu
Linear Activation Function	activation_linear
Rectified Linear Unit Activation Function	activation_relu
Sigmoid Activation Function	activation_sigmoid
Softmax Activation Function	activation_softmax
Hyperbolic Tangent Activation Function	activation_tanh
Convert Character Input to an Activation Object	as_activation
Convert Character Input to a Loss Object	as_loss
Convert Character Input to a Metric Object	as_metric
Convert Multiple Inputs to Metric Objects	as_metrics
Convert Character Input to an Optimizer Object	as_optimizer
List Available Activation Functions	available_activations
List Available Gradient-Based Optimizers	available_gradient_optimizers
List Available Loss Functions	available_losses
List Available Metaheuristic Optimizers	available_metaheuristics
List Available Performance Metrics	available_metrics
List Available Optimizers	available_optimizers
Extract the Best Parameters from a metANN Optimization Result	coef.met_optimize_result
Extract Weights from a metANN Model	coef.metann
Count the Number of Trainable Parameters in an MLP Architecture	count_parameters
Decode an MLP Weight Vector	decode_weights
Create a Dense Layer	dense_layer
Evaluate a metANN Model	evaluate
Forward Pass for an MLP	forward_pass
Initialize MLP Weights	initialize_weights
Check Whether an Object is a metANN Activation	is_activation
Check Whether an Object is a metANN Architecture	is_architecture
Check Whether an Object is a Dense Layer	is_dense_layer
Check Whether an Object is a metANN Layer	is_layer
Check Whether an Object is a metANN Loss	is_loss
Check Whether an Object is a metANN Metric	is_metric
Check Whether an Object is an MLP Architecture	is_mlp_architecture
Check Whether an Object is a metANN Optimizer	is_optimizer
Binary Cross-Entropy Loss	loss_binary_crossentropy
Categorical Cross-Entropy Loss	loss_crossentropy
Huber Loss	loss_huber
Log-Cosh Loss	loss_log_cosh
Mean Absolute Error Loss	loss_mae
Mean Squared Error Loss	loss_mse
Train a Feed-Forward Multilayer Perceptron	met_mlp
General-Purpose Optimization	met_optimize
Train an Artificial Neural Network with metANN	metann
Accuracy Metric	metric_accuracy
F1 Score Metric	metric_f1
Mean Absolute Error Metric	metric_mae
Mean Squared Error Metric	metric_mse
Precision Metric	metric_precision
Coefficient of Determination Metric	metric_r2
Recall Metric	metric_recall
Root Mean Squared Error Metric	metric_rmse
Create an MLP Architecture	mlp_architecture
Artificial Bee Colony Optimizer	optimizer_abc
Adam Optimizer	optimizer_adam
Differential Evolution Optimizer	optimizer_de
Genetic Algorithm Optimizer	optimizer_ga
Grey Wolf Optimizer	optimizer_gwo
Hybrid Optimizer	optimizer_hybrid
Get Optimizer Information	optimizer_info
Particle Swarm Optimization Optimizer	optimizer_pso
Secretary Bird Optimization Algorithm Optimizer	optimizer_sboa
Stochastic Gradient Descent Optimizer	optimizer_sgd
Teaching-Learning-Based Optimization Optimizer	optimizer_tlbo
Whale Optimization Algorithm Optimizer	optimizer_woa
Plot Neural Network Architecture	plot_network
Plot Optimization Convergence	plot.met_optimize_result
Plot a metANN Model	plot.metann
Predict with a metANN Model	predict.metann
Print a Dense Layer	print.met_dense_layer
Print an MLP Architecture	print.met_mlp_architecture
Print a metANN Optimization Result	print.met_optimize_result
Print a metANN Optimizer	print.met_optimizer
Print Optimizer Information	print.met_optimizer_info
Print a metANN Model	print.metann
Print metANN Evaluation Results	print.metann_evaluation
Summarize a metANN Optimization Result	summary.met_optimize_result
Summarize a metANN Model	summary.metann

Package: metANN 0.1.0

metANN: Metaheuristic and Gradient-Based Optimization for Neural Network Training and Continuous Problems

Citation

Development and contributors

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)