Main Content

Tuning

Programmatically tune training options, resume training from a checkpoint, and investigate adversarial examples

To learn how to set options using the trainingOptions function, see Set Up Parameters and Train Convolutional Neural Network. After you identify some good starting options, you can automate sweeping of hyperparameters or try Bayesian optimization using Experiment Manager.

Investigate network robustness by generating adversarial examples. You can then use fast gradient sign method (FGSM) adversarial training to train a network robust to adversarial perturbations.

Apps

Deep Network DesignerDesign, visualize, and train deep learning networks

Objects

trainingProgressMonitorMonitor and plot training progress for deep learning custom training loops (Since R2022b)

Functions

trainingOptionsOptions for training deep learning neural network
trainNetworkTrain neural network
trainnetTrain deep learning neural network (Since R2023b)

Topics

Related Information