Aproximación y regresión no lineal de funciones
Cree una red neuronal para generalizar relaciones no lineales entre entradas y salidas de ejemplo
Apps
Neural Net Fitting | Resolver un problema de ajuste utilizando redes prealimentadas de dos capas |
Funciones
fitnet | Red neuronal de ajuste de funciones |
feedforwardnet | Generar una red neuronal prealimentada |
cascadeforwardnet | Generar una red neuronal prealimentada en cascada |
train | Entrenar una red neuronal superficial |
trainlm | Retropropagación Levenberg-Marquardt |
trainbr | Retropropagación de regularización bayesiana |
trainscg | Retropropagación de gradiente conjugado escalado |
trainrp | Resilient backpropagation |
mse | Función de rendimiento normalizada de error cuadrático medio |
regression | (No recomendado) Realizar una regresión lineal de las salidas de redes superficiales en los objetivos |
ploterrhist | Representar un histograma de error |
plotfit | Representar el ajuste de una función |
plotperform | Representar el rendimiento de la red |
plotregression | Representar una regresión lineal |
plottrainstate | Representar valores de estado de entrenamiento |
genFunction | Generate MATLAB function for simulating shallow neural network |
Ejemplos y procedimientos
Diseño básico
- Fit Data with a Shallow Neural Network
Train a shallow neural network to fit a data set. - Create, Configure, and Initialize Multilayer Shallow Neural Networks
Prepare a multilayer shallow neural network. - Body Fat Estimation
This example illustrates how a function fitting neural network can estimate body fat percentage based on anatomical measurements. - Train and Apply Multilayer Shallow Neural Networks
Train and use a multilayer shallow network for function approximation or pattern recognition. - Analyze Shallow Neural Network Performance After Training
Analyze network performance and adjust training process, network architecture, or data. - Deploy Shallow Neural Network Functions
Simulate and deploy trained shallow neural networks using MATLAB® tools. - Deploy Training of Shallow Neural Networks
Learn how to deploy training of shallow neural networks.
Escalabilidad y eficiencia del entrenamiento
- Shallow Neural Networks with Parallel and GPU Computing
Use parallel and distributed computing to speed up neural network training and simulation and handle large data. - Automatically Save Checkpoints During Neural Network Training
Save intermediate results to protect the value of long training runs. - Optimize Neural Network Training Speed and Memory
Make neural network training more efficient.
Soluciones óptimas
- Choose Neural Network Input-Output Processing Functions
Preprocess inputs and targets for more efficient training. - Configure Shallow Neural Network Inputs and Outputs
Learn how to manually configure the network before training using theconfigure
function. - Divide Data for Optimal Neural Network Training
Use functions to divide the data into training, validation, and test sets. - Choose a Multilayer Neural Network Training Function
Comparison of training algorithms on different problem types. - Improve Shallow Neural Network Generalization and Avoid Overfitting
Learn methods to improve generalization and prevent overfitting. - Train Neural Networks with Error Weights
Learn how to use error weighting when training neural networks. - Normalize Errors of Multiple Outputs
Learn how to fit output elements with different ranges of values.
Conceptos
- Flujo de trabajo para el diseño de redes neuronales
Aprenda los principales pasos del proceso de diseño de una red neuronal.
- Four Levels of Neural Network Design
Learn the different levels of using neural network functionality.
- Redes neuronales superficiales multicapa y entrenamiento de retropropagación
Flujo de trabajo para diseñar una red neuronal prealimentada superficial multicapa para el ajuste de funciones y el reconocimiento de patrones.
- Multilayer Shallow Neural Network Architecture
Learn the architecture of a multilayer shallow neural network.
- Understanding Shallow Network Data Structures
Learn how the format of input data structures affects the simulation of networks.
- Conjuntos de datos de muestra para redes neuronales superficiales
Lista de conjuntos de datos de muestra que se pueden utilizar al experimentar con redes neuronales superficiales.
- Neural Network Object Properties
Learn properties that define the basic features of a network.
- Neural Network Subobject Properties
Learn properties that define network details such as inputs, layers, outputs, targets, biases, and weights.