Implement common deep learning workflows in MATLABĀ® using real-world image and sequence data. Dive into some of the ideas behind deep learning algorithms and standard network architectures.

Get an overview of the course. Perform image classification using pretrained networks. Use transfer learning to train customized classification networks.

Lessons:

- Course Overview

- Deep Learning Basics

Understand how information is passed between network layers and how different types of layers work.

Lessons:

- Understanding Neural Networks

- Convolutional Layers

- Viewing Filters

- Viewing the Activations of Different Layers

- Review - Understanding Convolutional Neural Networks

Train networks from scratch. Understand how training algorithms work. Set training options to monitor and control training.

Lessons:

- Training from Scratch

- Creating Network Architectures

- Understanding Network Training

- Monitoring Training Progress

- Validation

- Review - Creating and Training Networks

Choose and implement modifications to training algorithm options and training data to improve network performance.

Lessons:

- Troubleshooting Methods

- Visualizing Network Predictions

- Augmented Datastores

- Training Options

- Experiment Manager

- Review - Improving Performance

Bring together image classification concepts that you have learned with a project.

Lessons:

- Project - Classify Fashion Images

Create convolutional networks that can predict continuous numeric responses.

Lessons:

- What is Regression

- Transfer Learning for Regression

- Evaluating a Regression Network

- Review - Performing Regression

Train networks to locate and label specific objects within images.

Lessons:

- Computer Vision Applications

- Ground Truth

- YOLO Object Detectors

- Evaluating Object Detectors

- Review - Deep Learning for Computer Vision

Build and train networks to perform classification on ordered sequences of data, such as time series or sensor data.

Lessons:

- Course Example - Classify Flooding Level

- Managing Collections of Signal Data

- Long Short-Term Memory Networks

- Sequence Classification

- Improving LSTM Performance

- Review - Classifying Sequence Data with Recurrent Networks

Use recurrent networks to create sequences of predictions.

Lessons:

- Course Example - Classify Regions of Flooding Levels

- Labeling Regions of Interest

- Sequence-to-Sequence Classification

- Review - Classifying Sequences of Output

Bring together signal classification concepts that you have learned with a project.

Lessons:

- Project - Robot Navigation

Learn next steps and give feedback on the course.

Lessons:

- Summary

- Additional Resources

- Survey

Format:Self-paced

Language:English

- Hands-on exercises with automated feedback
- Access to MATLAB through your web browser
- Shareable progress report and course certificate

Learn core MATLAB functionality for data analysis, modeling, and programming.

Get started quickly using deep learning methods to perform image recognition.

Explore data and build predictive models.

Get started quickly with the basics of MATLAB.

Learn core MATLAB functionality for data analysis, modeling, and programming.

Get started quickly using deep learning methods to perform image recognition.