Train Deep Neural Networks

Train networks using built-in training functions or custom training loops

After defining the network architecture, you can define training parameters using the trainingOptions function. You can then train the network using the trainnet function. Use the trained network to predict class labels or numeric responses.

You can train a neural network on a CPU, a GPU, multiple CPUs or GPUs, or in parallel on a cluster or in the cloud. Training on a GPU or in parallel requires Parallel Computing Toolbox™. Using a GPU requires a supported GPU device (for information on supported devices, see GPU Computing Requirements (Parallel Computing Toolbox)). Specify the execution environment using the trainingOptions function.

If the trainingOptions function does not provide the training options that you need for your task, or custom output layers do not support the loss functions that you need, then you can define a custom training loop. For models that cannot be specified as networks of layers, you can define the model as a function. To learn more, see Define Custom Training Loops, Loss Functions, and Networks.

Featured Examples

Prepare Network for Transfer Learning Using Deep Network Designer

Interactively fine-tune a pretrained deep learning network to learn a new image classification task.

Open Live Script

Time Series Forecasting Using Deep Learning

Forecast time series data using a long short-term memory (LSTM) network.

Open Live Script

Train Residual Network for Image Classification

Create a deep learning neural network with residual connections and train it on CIFAR-10 data. Residual connections are a popular element in convolutional neural network architectures. Using residual connections improves gradient flow through the network and enables training of deeper networks.