La traducción de esta página aún no se ha actualizado a la versión más reciente. Haga clic aquí para ver la última versión en inglés.

Ajustar

Ajuste las opciones de entrenamiento de forma programática, reanude el entrenamiento desde un punto de control e investigue ejemplos adversarios

Para aprender a configurar las opciones con la función trainingOptions, consulte Set Up Parameters and Train Convolutional Neural Network. Una vez que haya identificado unas cuantas opciones de inicio válidas, podrá automatizar el barrido de hiperparámetros o probar la optimización bayesiana con Experiment Manager.

Investigue la solidez de la red generando ejemplos adversarios. Después, podrá usar el entrenamiento adversario con el método rápido de símbolo de gradiente (FGSM) para entrenar una red resistente a perturbaciones adversario.

Apps

Deep Network Designer

Diseñar, visualizar y entrenar redes de deep learning

Objetos

trainingProgressMonitor Monitor and plot training progress for deep learning custom training loops (desde R2022b)

Funciones

`trainingOptions`	Opciones para entrenar una red neuronal de deep learning
`trainNetwork`	Entrenar redes neuronales de deep learning

Temas

Set Up Parameters and Train Convolutional Neural Network
Learn how to set up training parameters for a convolutional neural network.
Deep learning usando la optimización bayesiana
En este ejemplo se muestra cómo aplicar la optimización bayesiana a deep learning y encontrar los hiperparámetros óptimos de la red, así como las opciones de entrenamiento para redes neuronales convolucionales.
Detect Issues During Deep Neural Network Training
This example shows how to automatically detect issues while training a deep neural network.
Train Deep Learning Networks in Parallel
This example shows how to run multiple deep learning experiments on your local machine.
Train Network Using Custom Training Loop
This example shows how to train a network that classifies handwritten digits with a custom learning rate schedule.
Compare Activation Layers
This example shows how to compare the accuracy of training networks with ReLU, leaky ReLU, ELU, and swish activation layers.
Generate Experiment Using Deep Network Designer
Use Experiment Manager to tune the hyperparameters of a network trained in Deep Network Designer.
Deep Learning Tips and Tricks
Learn how to improve the accuracy of deep learning networks.
Specify Custom Weight Initialization Function
This example shows how to create a custom He weight initialization function for convolution layers followed by leaky ReLU layers.
Compare Layer Weight Initializers
This example shows how to train deep learning networks with different weight initializers.
Customize Output During Deep Learning Network Training
This example shows how to define an output function that runs at each iteration during training of deep learning neural networks.

Información relacionada

App Experiment Manager

Ejemplos destacados

Resume Training from Checkpoint Network

Save checkpoint networks while training a deep learning network and resume training from a previously saved network.

Abrir script en vivo

Generate Untargeted and Targeted Adversarial Examples for Image Classification

Use the fast gradient sign method (FGSM) and the basic iterative method (BIM) to generate adversarial examples for a pretrained neural network.

Abrir script en vivo

Generate Adversarial Examples for Semantic Segmentation

Generate adversarial examples for a semantic segmentation network using the basic iterative method (BIM).

Abrir script en vivo

Train Image Classification Network Robust to Adversarial Examples

Train a neural network that is robust to adversarial examples using fast gradient sign method (FGSM) adversarial training.

Abrir script en vivo

Train Robust Deep Learning Network with Jacobian Regularization

Train a neural network that is robust to adversarial examples using a Jacobian regularization scheme.

Abrir script en vivo