Diese Seite ist für die vorige Version. Die entsprechende englische Seite wurde in der aktuellen Version entfernt.

Benutzerdefinierte Trainingsschleifen

Anpassen von Deep-Learning-Trainingsschleifen und Verlustfunktionen für Sequenz- und Tabellendaten

Wenn die Funktion trainingOptions nicht die Trainingsoptionen bietet, die Sie für Ihre Aufgabe benötigen, oder Sie eine Verlustfunktion haben, die von der trainnet-Funktion nicht unterstützt wird, können Sie eine eigene Trainingsschleife definieren. Für Modelle, die nicht als Netz von Schichten angegeben werden können, können Sie das Modell als Funktion definieren. Weitere Informationen finden Sie unter Define Custom Training Loops, Loss Functions, and Networks.

Funktionen

alle erweitern

Benutzerdefinierte Trainingsschleifen

`dlnetwork`	Deep learning neural network
`trainingProgressMonitor`	Monitor and plot training progress for deep learning custom training loops (Seit R2022b)
`minibatchqueue`	Create mini-batches for deep learning
`padsequences`	Pad or truncate sequence data to same length (Seit R2021a)
`dlarray`	Deep learning array for customization
`dlgradient`	Compute gradients for custom training loops using automatic differentiation
`dljacobian`	Jacobian matrix deep learning operation (Seit R2024b)
`dldivergence`	Divergence of deep learning data (Seit R2024b)
`dllaplacian`	Laplacian of deep learning data (Seit R2024b)
`dlfeval`	Evaluate deep learning model for custom training loops

Verlustoperationen

`crossentropy`	Cross-entropy loss for classification tasks
`indexcrossentropy`	Index cross-entropy loss for classification tasks (Seit R2024b)
`l1loss`	L₁ loss for regression tasks (Seit R2021b)
`l2loss`	L₂ loss for regression tasks (Seit R2021b)
`huber`	Huber loss for regression tasks (Seit R2021a)
`ctc`	Connectionist temporal classification (CTC) loss for unaligned sequence classification (Seit R2021a)
`mse`	Half mean squared error

Deep-Learning-Operationen

`dlconv`	Deep learning convolution
`dltranspconv`	Deep learning transposed convolution
`lstm`	Long short-term memory
`gru`	Gated recurrent unit
`attention`	Dot-product attention (Seit 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) (Seit 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 (Seit R2021a)
`layernorm`	Normalize data across all channels for each observation independently (Seit 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

Aktivierungen

`relu`	Anwenden einer Rectified Linear Unit-Aktivierung
`leakyrelu`	Apply leaky rectified linear unit activation
`gelu`	Apply Gaussian error linear unit (GELU) activation (Seit R2022b)
`softmax`	Apply softmax activation to channel dimension
`sigmoid`	Anwenden der Sigmoid-Aktivierung

Themen

Benutzerdefinierte Trainingsschleifen

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.
Train Network with Multiple Outputs
This example shows how to train a deep learning network with multiple outputs that predict both labels and angles of rotations of handwritten digits.
Train Neural ODE Network
This example shows how to train an augmented neural ordinary differential equation (ODE) network.
Solve ODE Using Physics-Informed Neural Network
This example shows how to train a physics-informed neural network (PINN) to predict the solutions of an ordinary differential equation (ODE).
Speed Up Deep Neural Network Training
Learn how to accelerate deep neural network training.

Automatische Differenzierung

Create Bidirectional LSTM (BiLSTM) Function
This example shows how to create a bidirectional long-short term memory (BiLSTM) function for custom deep learning functions. (Seit 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.

Enthaltene Beispiele

Solve PDE Using Physics-Informed Neural Network

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

Live Script öffnen

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.

Live Script öffnen

Multivariate Time Series Anomaly Detection Using Graph Neural Network

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

Live Script öffnen

Dynamical System Modeling Using Neural ODE

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

Live Script öffnen

Sequence-to-Sequence Translation Using Attention

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

Live Script öffnen

Image Captioning Using Attention

Train a deep learning model for image captioning using attention.

Live Script öffnen

Multilabel Text Classification Using Deep Learning

Classify text data that has multiple independent labels.

Live Script öffnen