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

---

Documentation for package ‘metANN’ version 0.1.0

• DESCRIPTION file
• Package README

Help Pages

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