연산
대부분의 작업에서 내장 계층을 사용할 수 있습니다. 작업에 필요한 내장 계층이 없는 경우 자신만의 고유한 사용자 지정 계층을 정의할 수 있습니다. 학습 가능한 파라미터와 상태 파라미터를 포함하는 사용자 지정 계층을 정의할 수 있습니다. 사용자 지정 계층을 정의한 후에는 이 계층이 유효하고, GPU와 호환되며, 올바르게 정의된 기울기를 출력하는지 확인할 수 있습니다. 자세한 내용은 사용자 지정 딥러닝 계층 정의하기 항목을 참조하십시오. 지원되는 계층 목록은 딥러닝 계층 목록 항목을 참조하십시오.
딥러닝 연산을 사용하여 사용자 지정 계층, 훈련 루프 및 모델 함수에 대한 MATLAB® 코드를 개발합니다.
함수
도움말 항목
자동 미분
- Automatic Differentiation Background
Learn how automatic differentiation works. - Use Automatic Differentiation In Deep Learning Toolbox
How to use automatic differentiation in deep learning. - List of Functions with dlarray Support
View the list of functions that supportdlarrayobjects. - Define Custom Deep Learning Operations
Learn how to define custom deep learning operation. - Specify Custom Operation Backward Function
This example shows how to define the SReLU operation as a differentiable function and specify a custom backward function. - Train Model Using Custom Backward Function
This example shows how to train a deep learning model that contains an operation with a custom backward function. - Create Bidirectional LSTM (BiLSTM) Function
This example shows how to create a bidirectional long-short term memory (BiLSTM) function for custom deep learning functions. (R2023b 이후)
모델 함수
- Train Network Using Model Function
This example shows how to create and train a deep learning network by using functions rather than a layer graph or adlnetwork. - Update Batch Normalization Statistics Using Model Function
This example shows how to update the network state in a network defined as a function. - Make Predictions Using Model Function
This example shows how to make predictions using a model function by splitting data into mini-batches. - Initialize Learnable Parameters for Model Function
Learn how to initialize learnable parameters for custom training loops using a model function.
딥러닝 함수 가속
- Deep Learning Function Acceleration for Custom Training Loops
Accelerate model functions and model loss functions for custom training loops by caching and reusing traces. - Accelerate Custom Training Loop Functions
This example shows how to accelerate deep learning custom training loop and prediction functions. - 가속화된 딥러닝 함수의 출력값 검사하기
이 예제에서는 가속화된 함수의 출력값이 기본 함수의 출력값과 일치하는지 검사하는 방법을 보여줍니다. - Evaluate Performance of Accelerated Deep Learning Function
This example shows how to evaluate the performance gains of using an accelerated function.
추천 예제
Train a Twin Network for Dimensionality Reduction
Train a twin neural network with shared weights to compare handwritten digits using dimensionality reduction.
Train a Twin Neural Network to Compare Images
Train a twin neural network with shared weights to identify similar images of handwritten characters.
Image Captioning Using Attention
Train a deep learning model for image captioning using attention.
Sequence-to-Sequence Translation Using Attention
Convert decimal strings to Roman numerals using a recurrent sequence-to-sequence encoder-decoder model with attention.
물리정보 신경망을 사용하여 PDE 해 구하기
이 예제에서는 편미분 방정식(PDE)의 해를 예측하는 물리정보 신경망(PINN)을 훈련시키는 방법을 보여줍니다.
Dynamical System Modeling Using Neural ODE
Train a neural network with neural ordinary differential equations (ODEs) to learn the dynamics of a physical system.
Node Classification Using Graph Convolutional Network
Classify nodes in a graph using a graph convolutional network (GCN).
Multilabel Graph Classification Using Graph Attention Networks
Classify graphs that have multiple independent labels using graph attention networks (GATs).
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.
Multivariate Time Series Anomaly Detection Using Graph Neural Network
Detect anomalies in multivariate time series data using a graph neural network (GNN).
