MATLAB & Simulink

DATA ANALYSIS AND MACHINE LEARNING

Deep Learning with MATLAB

Course Highlights

This two-day course provides a comprehensive introduction to practical deep learning using MATLAB®. Attendees will learn how to create, train, and evaluate different kinds of deep neural networks . The instructor-led training uses NVIDIA GPUs to accelerate network training

Topics include:

• Importing image and sequence data

• Using convolutional neural networks for image classification, regression, and other image appplications

• Using long short-term memory networks for sequence classification and forecasting

• Modifying common network architectures to solve custom problems

• Improving performance of a network by modifying training options

Who Should Attend

Engineers, professionals, researchers who are involved in machine learning design for image processing.

Techsource Systems is
Mathworks Sole and Authorised Distributor and Training Partner

Course Prerequisite

MATLAB Fundamentals 

Course Benefits

Upon the completion of the course, the participants will be able to

- perform image classification, regression and object detection

- perform sequence classification and forecasting

- modify common network architecture to solve custom problems - improve performance of a network. 
 

Course Outline

Day 1 of 2

​

Transfer Learning for Image Classification

Objective: Perform image classification using pretrained networks. Use transfer learning to train customized classification networks.

• Pretrained networks

• Image datastores

• Transfer learning

• Network evaluation

Interpreting Network Behavior

Objective: Gain insight into how a network is operating by visualizing image data as it passes through the network. Apply this technique to different kinds of images.

• Activations

• Feature extraction for machine learning

Creating Networks

Objective: Build convolutional networks from scratch. Understand how information is passed between network layers and how different types of layers work.

• Training from scratch

• Neural networks

• Convolution layers and filters

Training a Network

Objective: Understand how training algorithms work. Set training options to monitor and control training.

• Network training

• Training progress plots

• Validation

Day 2 of 2

​

Improving Network Performance

Objective: Choose and implement modifications to training algorithm options, network architecture, or training data to improve network performance.

• Training options

• Directed acyclic graphs

• Augmented datastores

Performing Image Regression

Objective: Create convolutional networks that can predict continuous numeric responses.

• Transfer learning for regression

• Evaluation metrics for regression networks

Using Deep Learning for Computer Vision

Objective: Train networks to locate and label specific objects within images.

• Image application workflow

• Object detection

Classifying Sequence Data

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

• Long short-term memory networks

• Sequence classification

• Sequence preprocessing

• Categorical sequences

Generating Sequences of Output

Objective: Use recurrent networks to create sequences of predictions.

• Sequence to sequence classification

• Sequence forecasting