Esta página es para la versión anterior. La página correspondiente en inglés ha sido eliminada en la versión actual.

Bucles de entrenamiento personalizados

Personalice bucles de entrenamiento y funciones de pérdida de deep learning para datos de secuencia y en tablas.

Si la función trainingOptions no proporciona las opciones de entrenamiento que necesita para la tarea o tiene una función de pérdida que la función trainnet no admite, puede definir un bucle de entrenamiento personalizado. Para los modelos que no se pueden especificar como redes de capas, puede definir el modelo como una función. Para obtener más información, consulte Define Custom Training Loops, Loss Functions, and Networks.

Funciones

expandir todo

Bucles de entrenamiento personalizados

`dlnetwork`	Redes neuronales de deep learning
`trainingProgressMonitor`	Monitor and plot training progress for deep learning custom training loops (Desde R2022b)
`minibatchqueue`	Create mini-batches for deep learning
`padsequences`	Pad or truncate sequence data to same length (Desde R2021a)
`dlarray`	Arreglo de deep learning para personalización
`dlgradient`	Compute gradients for custom training loops using automatic differentiation
`dljacobian`	Jacobian matrix deep learning operation (Desde R2024b)
`dldivergence`	Divergence of deep learning data (Desde R2024b)
`dllaplacian`	Laplacian of deep learning data (Desde R2024b)
`dlfeval`	Evaluar modelos de deep learning para bucles de entrenamiento personalizados

Operaciones de pérdida

`crossentropy`	Cross-entropy loss for classification tasks
`indexcrossentropy`	Index cross-entropy loss for classification tasks (Desde R2024b)
`l1loss`	L₁ loss for regression tasks (Desde R2021b)
`l2loss`	L₂ loss for regression tasks (Desde R2021b)
`huber`	Huber loss for regression tasks (Desde R2021a)
`ctc`	Connectionist temporal classification (CTC) loss for unaligned sequence classification (Desde R2021a)
`mse`	Error cuadrático medio dividido

Operaciones de deep learning

`dlconv`	Deep learning convolution
`dltranspconv`	Deep learning transposed convolution
`lstm`	Memoria de corto-largo plazo
`gru`	Gated recurrent unit
`attention`	Dot-product attention (Desde R2022b)
`embed`	Embed discrete data
`fullyconnect`	Sum all weighted input data and apply a bias
`dlode45`	Deep learning solution of nonstiff ordinary differential equation (ODE) (Desde R2021b)
`batchnorm`	Normalize data across all observations for each channel independently
`crosschannelnorm`	Cross channel square-normalize using local responses
`groupnorm`	Normalize data across grouped subsets of channels for each observation independently
`instancenorm`	Normalize across each channel for each observation independently (Desde R2021a)
`layernorm`	Normalize data across all channels for each observation independently (Desde R2021a)
`avgpool`	Pool data to average values over spatial dimensions
`maxpool`	Pool data to maximum value
`maxunpool`	Unpool the output of a maximum pooling operation

Activaciones

`relu`	Aplicar la activación de unidad lineal rectificada
`leakyrelu`	Apply leaky rectified linear unit activation
`gelu`	Apply Gaussian error linear unit (GELU) activation (Desde R2022b)
`softmax`	Apply softmax activation to channel dimension
`sigmoid`	Aplicar la activación sigmoide

Temas

Bucles de entrenamiento personalizados

Train Deep Learning Model in MATLAB
Learn how to training deep learning models in MATLAB^®.
Define Custom Training Loops, Loss Functions, and Networks
Learn how to define and customize deep learning training loops, loss functions, and models.
Train Sequence Classification Network Using Custom Training Loop
This example shows how to train a network that classifies sequences with a custom learning rate schedule.
Monitor Custom Training Loop Progress
Track and plot custom training loop progress.
Entrenar una red con varias salidas
Este ejemplo muestra cómo entrenar una red de deep learning con varias salidas que predicen tanto etiquetas como ángulos de rotación de dígitos manuscritos.
Train Neural ODE Network
This example shows how to train an augmented neural ordinary differential equation (ODE) network.
Resolver ecuaciones diferenciales ordinarias con redes neuronales
Este ejemplo muestra cómo resolver una ecuación diferencial ordinaria (EDO) usando una red neuronal.
Speed Up Deep Neural Network Training
Learn how to accelerate deep neural network training.

Diferenciación automática

Create Bidirectional LSTM (BiLSTM) Function
This example shows how to create a bidirectional long-short term memory (BiLSTM) function for custom deep learning functions. (Desde R2023b)
List of Functions with dlarray Support
View the list of functions that support dlarray objects.
Automatic Differentiation Background
Learn how automatic differentiation works.
Use Automatic Differentiation In Deep Learning Toolbox
How to use automatic differentiation in deep learning.

Ejemplos destacados

Solve PDE Using Physics-Informed Neural Network

Train a physics-informed neural network (PINN) to predict the solutions of an partial differential equation (PDE).

Abrir script en vivo

Train Latent ODE Network with Irregularly Sampled Time-Series Data

Train a latent ordinary differential equation (ODE) autoencoder with time-series data that is sampled at irregular time intervals.

Abrir script en vivo

Multivariate Time Series Anomaly Detection Using Graph Neural Network

Detect anomalies in multivariate time series data using a graph neural network (GNN).

Abrir script en vivo

Dynamical System Modeling Using Neural ODE

Train a neural network with neural ordinary differential equations (ODEs) to learn the dynamics of a physical system.

Abrir script en vivo

Sequence-to-Sequence Translation Using Attention

Convert decimal strings to Roman numerals using a recurrent sequence-to-sequence encoder-decoder model with attention.

Abrir script en vivo

Image Captioning Using Attention

Train a deep learning model for image captioning using attention.

Abrir script en vivo

Multilabel Text Classification Using Deep Learning

Classify text data that has multiple independent labels.

Abrir script en vivo