이 예제에서는 생성적 적대 신경망을 훈련시켜서 영상을 생성하는 방법을 보여줍니다.

Train a network that classifies handwritten digits with a custom learning rate schedule.

Create and train a deep learning network by using functions rather than a layer graph or a dlnetwork. The advantage of using functions is the flexibility to describe a wide variety of networks. The disadvantage is that you must complete more steps and prepare your data carefully. This example uses images of handwritten digits, with the dual objectives of classifying the digits and determining the angle of each digit from the vertical.

Train a Siamese network to compare handwritten digits using dimensionality reduction.

Train a Siamese network to identify similar images of handwritten characters.

Train a deep learning model for image captioning using attention.

Classify text data that has multiple independent labels.

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

Classify each time step of sequence data using a generic temporal convolutional network (TCN).

Set up a custom training loop to train a network in parallel. In this example, parallel workers train on portions of the overall mini-batch. If you have a GPU, then training happens on the GPU. During training, a DataQueue object sends training progress information back to the MATLAB client.

이 예제에서는 MATLAB에서 변분 오토인코더(VAE)를 만들어 숫자 영상을 생성하는 방법을 보여줍니다. VAE는 MNIST 데이터 세트의 스타일로 손으로 그린 숫자를 생성합니다.

Train a network to classify images of objects using a cyclical learning rate schedule and snapshot ensembling for better test accuracy. In the example, you learn how to use a cosine function for the learning rate schedule, take snapshots of the network during training to create a model ensemble, and add L2-norm regularization (weight decay) to the training loss.