Status message

There are no scheduled classes for this course. If you are interested in purchasing this course, please click on the "Express Interest" button, fill in your contact information, and submit a request for the course.
  • Course Length:
  • 3 days

Deep Learning has taken the concepts of Machine Learning and extended them to support more complex data analysis and predictions. This course provides a hands-on introduction to the basic concepts of Deep Learning from a telecom perspective. Deep Learning is explored from a definition and underlying technology perspective. It starts with an introduction to Deep Learning models. The course then moves to an exploration of the data selection and analysis. The course then moves into the details of building a number of Deep Learning models based on telecom specific data. The key concepts are presented using hands on activities that include analyzing data, using a Deep Learning model in python and using a GUI based tool.

For personnel involved in product management, marketing, planning, design, engineering, and operating wireless (4G, 5G) and wireline access networks who need a technical introduction to AI

After completing this course, the student will be able to:
■ List key types of neural networks and compare them
■ Define key Data Selection processes like Eigen decomposition
■ Prepare Data for training a Deep Learning Model
■ Describe a Convolutional Neural Network model and its uses
■ Build a CNN model
■ Describe a Recurrent Neural Network model and its uses
■ Build a RNN model
■ Analyze an Unsupervised Learning Model and describe the steps involved

1. Overview of Deep Learning Models
1.1 Convolutional Neural Networks
1.2 Recurrent Neural Networks
1.3 Auto Encoder
1.4 Generative adversarial networks
1.5 Model Training vs. Model Deployment
Exercise: Use a number of Deep Learning models

2. Data Selection
2.1 Data Selection and Analysis
2.2 Intuitive description of n-dimensional vector space
2.3 Eigen decomposition
2.4 Eigen values, eigen vectors
2.5 Decomposition
2.6 Principle Component Analysis
Exercise: Prepare Data for a Deep Learning Model

3. Convolutional Neural Network (CNN) Lab
3.1 Basic CNN Example
3.2 CNN Model Details
3.3 CNN Model Use Cases
Exercise: Build a CNN Model

4. Recurrent Neural Network (RNN) Lab
4.1 Basic RNN Example
4.2 RNN Model Design
4.3 RNN Model Use Cases
Exercise: Build a RNN Model

5. Unsupervised Learning Lab
5.1 Basic Unsupervised Learning Example
5.2 Specific Unsupervised Learning Models
5.3 Unsupervised Learning Data Analysis
Exercise: Build an Unsupervised Learning Model