Deep Learning with MATLAB

Who Should Attend?

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

}
Duration: 2 Days

This 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.

Topics include:

  • Import image and sequence data
  • Use convolutional neural networks for image classification, regression, and object detection
  • Use long short-term memory networks for sequence classification and forecasting
  • Modify common network architectures to solve custom problems
  • Improve performance of a network by modifying training options

The aim of this training is to provide participants with comprehensive introduction on deep learning with Neural Network toolbox for image processing applications.

Classifying Images with Convolution Networks

Objectives: Get an overview of the course. 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

Objectives: 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
  • Images from signal data
  • Feature extraction for machine learning

Creating Networks

Objectives: 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 Networks

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

  • Network training
  • Training progress plots
  • Validation

Improving Performance

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

  • Training options
  • Augmented datastores
  • Directed acyclic graphs

Performing Regression

Objectives: Create convolutional networks that can predict continuous numeric responses.Training options

  • Transfer learning for regression
  • Evaluation metrics for regression networks

Detecting Objects in Images

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

  • Object detection

Classifying Sequence Data with Recurrent Networks

Objectives: 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

Classifying Categorical Sequences

Objectives: Use recurrent networks to classify sequences of categorical data, such as text.

  • Categorical sequences
  • Text classification

Generating Sequences of Output

Objectives: Use recurrent networks to create sequences of predictions.

  • Sequence to sequence classification
  • Sequence forecasting

Register Now

Drop us your entry if you are interested to join this course.