Deep Learning Tuning and Visualization

Plot training progress, assess accuracy, make predictions, tune training options, and visualize features learned by a network

Monitor deep learning training progress using built-in plots of network accuracy and loss. To improve network performance, you can tune training options and use Bayesian optimization to search for optimal hyperparameters. To investigate trained networks, you can visualize features learned by a network and create deep dream visualizations. Test your trained network by making predictions using new data.

Apps

Deep Network Designer

Edit and build deep learning networks

Functions

expand all

Tuning Options and Plots

`analyzeNetwork`	Analyze deep learning network architecture
`plot`	Plot neural network layer graph
`trainingOptions`	Options for training deep learning neural network
`trainNetwork`	Train neural network for deep learning

Feature Visualization and Prediction

`activations`	Compute deep learning network layer activations
`predict`	Predict responses using a trained deep learning neural network
`classify`	Classify data using a trained deep learning neural network
`predictAndUpdateState`	Predict responses using a trained recurrent neural network and update the network state
`classifyAndUpdateState`	Classify data using a trained recurrent neural network and update the network state
`resetState`	Reset the state of a recurrent neural network
`deepDreamImage`	Visualize network features using deep dream
`occlusionSensitivity`	Determine how input data affects output activations by occluding input
`confusionchart`	Create confusion matrix chart for classification problem
ConfusionMatrixChart Properties	Confusion matrix chart appearance and behavior
`sortClasses`	Sort classes of confusion matrix chart

Topics

Tuning

Set Up Parameters and Train Convolutional Neural Network

Learn how to set up training parameters for a convolutional neural network

Resume Training from Checkpoint Network

Learn how to save checkpoint networks while training a convolutional neural network and resume training from a previously saved network

Deep Learning Using Bayesian Optimization

This example shows how to apply Bayesian optimization to deep learning and find optimal network hyperparameters and training options for convolutional neural networks.

Run Multiple Deep Learning Experiments

This example shows how to run multiple deep learning experiments on your local machine.

Train Network Using Custom Training Loop

This example shows how to train a network that classifies handwritten digits with a custom learning rate schedule.

Deep Learning Tips and Tricks

Learn how to improve the accuracy of deep learning networks.

Visualization

Classify Webcam Images Using Deep Learning

This example shows how to classify images from a webcam in real time using the pretrained deep convolutional neural network GoogLeNet.

Monitor Deep Learning Training Progress

When you train networks for deep learning, it is often useful to monitor the training progress.

Grad-CAM Reveals the Why Behind Deep Learning Decisions

Grad-CAM explains why a network makes a decision.

Understand Network Predictions Using Occlusion

This example shows how to use occlusion sensitivity maps to understand why a deep neural network makes a classification decision.

Investigate Network Predictions Using Class Activation Mapping

This example shows how to use class activation mapping (CAM) to investigate and explain the predictions of a deep convolutional neural network for image classification.

View Network Behavior Using tsne

This example shows how to use the tsne function to view activations in a trained network.

Visualize Activations of a Convolutional Neural Network

This example shows how to feed an image to a convolutional neural network and display the activations of different layers of the network.

Visualize Activations of LSTM Network

This example shows how to investigate and visualize the features learned by LSTM networks by extracting the activations.

Visualize Features of a Convolutional Neural Network

This example shows how to visualize the features learned by convolutional neural networks.

Featured Examples

Classify Webcam Images Using Deep Learning

Classify images from a webcam in real time using the pretrained deep convolutional neural network GoogLeNet.

Open Script

Deep Dream Images Using AlexNet

Generate images using deepDreamImage with the pretrained convolutional neural network AlexNet.

Open Live Script

Grad-CAM Reveals the Why Behind Deep Learning Decisions

Grad-CAM explains why a network makes a decision.

Open Live Script

Understand Network Predictions Using Occlusion

Use occlusion sensitivity maps to understand why a deep neural network makes a classification decision. Occlusion sensitivity is a simple technique for understanding which parts of an image are most important for a deep network's classification. You can measure a network's sensitivity to occlusion in different regions of the data using small pertubations of the data. Use occlusion sensitivity to gain a high-level understanding of what image features a network uses to make a particular classification, and to provide insight into the reasons why a network can missclassify an image.

Open Live Script