Deep Learning with Keras and Tensorflow

Deep Learning with Keras and Tensorflow

This course is part of multiple programs.

Instructors: Samaya Madhavan

What you'll learn

Create custom layers and models in Keras and integrate Keras with TensorFlow 2.x
Develop advanced convolutional neural networks (CNNs) using Keras
Develop Transformer models for sequential data and time series prediction
Explain key concepts of Unsupervised learning in Keras, Deep Q-networks (DQNs), and reinforcement learning

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

18 assignments

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

Build your subject-matter expertise

This course is available as part of

When you enroll in this course, you'll also be asked to select a specific program.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate from IBM

Earn a career certificate

Add this credential to your LinkedIn profile, resume, or CV

Share it on social media and in your performance review

There are 7 modules in this course

Deep learning is revolutionizing many fields, including computer vision, natural language processing, and robotics. In addition, Keras, a high-level neural networks API written in Python, has become an essential part of TensorFlow, making deep learning accessible and straightforward. Mastering these techniques will open many opportunities in research and industry.

You will learn to create custom layers and models in Keras and integrate Keras with TensorFlow 2.x for enhanced functionality. You will develop advanced convolutional neural networks (CNNs) using Keras. You will also build transformer models for sequential data and time series using TensorFlow with Keras. The course also covers the principles of unsupervised learning in Keras and TensorFlow for model optimization and custom training loops. Finally, you will develop and train deep Q-networks (DQNs) with Keras for reinforcement learning tasks (an overview of Generative Modeling and Reinforcement Learning is provided). You will be able to practice the concepts learned using hands-on labs in each lesson. A culminating final project in the last module will provide you an opportunity to apply your knowledge to build a Classification Model using transfer learning. This course is suitable for all aspiring AI engineers who want to learn TensorFlow and Keras. It requires a working knowledge of Python programming and basic mathematical concepts such as gradients and matrices, as well as fundamentals of Deep Learning using Keras.

This module provides an overview of Keras advanced features. It will cover Keras functional API for complex model creation. It also includes the creation of custom layers and models in Keras. Then the module describes the integration of Keras with TensorFlow 2.x for enhanced functionality. You will apply your learnings in labs and test your concepts in quizzes.

What's included

5 videos2 readings3 assignments2 app items1 discussion prompt2 plugins

5 videosTotal 21 minutes

Course Introduction2 minutesPreview module
Introduction to Advanced Keras 3 minutes
Keras Functional API and Subclassing API6 minutes
Creating Custom Layers in Keras 3 minutes
Overview of TensorFlow 2.x 5 minutes

2 readingsTotal 9 minutes

Course Overview4 minutes
Summary and Highlights: Advanced Keras Functionalities 5 minutes

3 assignmentsTotal 50 minutes

Graded Quiz: Advanced Keras Functionalities 30 minutes
Practice Quiz: Advanced Keras Functional API 10 minutes
Practice Quiz: Custom Layers with Keras10 minutes

2 app itemsTotal 60 minutes

Lab: Implementing the Functional API in Keras30 minutes
Lab: Creating Custom Layers and Models30 minutes

1 discussion promptTotal 10 minutes

[Optional] Meet and Greet 10 minutes

2 pluginsTotal 16 minutes

Helpful Tips for Course Completion1 minute
Glossary: Advanced Keras Functionalities 15 minutes

In this module, you will learn to develop advanced convolutional neural networks (CNNs) using Keras. You will learn data augmentation techniques with Keras. In addition, you will implement transfer learning with Keras and leverage pre-trained models. Finally, you will learn how to use TensorFlow for enhancing image processing capabilities. You will apply your learnings in labs and test your concepts in quizzes.

What's included

6 videos1 reading4 assignments3 app items1 discussion prompt2 plugins

6 videosTotal 26 minutes

Advanced CNNs in Keras 4 minutesPreview module
Data Augmentation Techniques 3 minutes
Transfer Learning in Keras 7 minutes
Using Pre-trained Models 5 minutes
TensorFlow for Image Processing 2 minutes
Introducing Transpose Convolution 3 minutes

1 readingTotal 1 minute

Summary and Highlights: Advanced CNNs in Keras 1 minute

4 assignmentsTotal 60 minutes

Graded Quiz: Advanced CNNs in Keras30 minutes
Practice Quiz: Advanced CNNs and Data Augmentation10 minutes
Practice Quiz: Transfer Learning on Pre-trained Models and Image Processing10 minutes
Practice Quiz: Introducing Transpose Convolution 10 minutes

3 app itemsTotal 120 minutes

Advanced Data Augmentation with Keras30 minutes
Lab: Transfer Learning Implementation30 minutes
Lab: Practical Application of Transpose Convolution60 minutes

1 discussion promptTotal 10 minutes

[Optional] Discussion Prompt: Data Augmentation and Transfer Learning10 minutes

2 pluginsTotal 20 minutes

Reading: Tips for Transfer Learning Implementation5 minutes
Glossary: Advanced CNNs in Keras 15 minutes

This module covers building and training advanced Transformers using Keras. You will further develop Transformer models for sequential data and time series using TensorFlow with Keras. In addition, you will learn to implement advanced Transformer techniques for text generation. You will apply your learnings in labs and test your concepts in quizzes.

What's included

5 videos1 reading3 assignments2 app items1 discussion prompt1 plugin

5 videosTotal 20 minutes

Introduction to Transformers in Keras 4 minutesPreview module
Building Transformers for Sequential Data 3 minutes
Advanced Transformer Applications 4 minutes
Transformers for Time Series Prediction 4 minutes
TensorFlow for Sequential Data 4 minutes

1 readingTotal 3 minutes

Summary and Highlights: Transformers in Keras 3 minutes

3 assignmentsTotal 50 minutes

Graded Quiz: Transformers in Keras 30 minutes
Practice Quiz: Transformers in Keras 10 minutes
Practice Quiz: Advanced Transformers and Sequential Data using TensorFlow10 minutes

2 app itemsTotal 90 minutes

Lab: Building Advanced Transformers60 minutes
Lab: Implementing Transformers for Text Generation30 minutes

1 discussion promptTotal 10 minutes

[Optional] Discussion Prompt: Transforming Sequential Data with Transformers10 minutes

1 pluginTotal 15 minutes

Glossary: Transformers in Keras 15 minutes

In this module, you will learn the principles of unsupervised learning in Keras. You will learn to build and train autoencoders and diffusion models. In addition, you will develop generative adversarial networks (GANs) using Keras and integrate TensorFlow for advanced unsupervised learning tasks. You will apply your learnings in labs and test your concepts in quizzes.

What's included

5 videos1 reading3 assignments3 app items1 discussion prompt1 plugin

5 videosTotal 19 minutes

Introduction to Unsupervised Learning in Keras 4 minutesPreview module
Building Autoencoders in Keras3 minutes
Diffusion Models 3 minutes
Generative Adversarial Networks (GANs) 4 minutes
TensorFlow for Unsupervised Learning 3 minutes

1 readingTotal 2 minutes

Summary and Highlights: Unsupervised Learning and Generative Models in Keras 2 minutes

3 assignmentsTotal 50 minutes

Graded Quiz: Unsupervised Learning and Generative Models in Keras 30 minutes
Practice Quiz: Unsupervised Learning, Autoencoders, and Diffusion Models 10 minutes
Practice Quiz: GANs and TensorFlow 10 minutes

3 app itemsTotal 135 minutes

Lab: Building Autoencoders60 minutes
Lab: Implementing Diffusion Models45 minutes
Lab: Develop GANs using Keras30 minutes

1 discussion promptTotal 10 minutes

[Optional] Exploring Autoencoders and GANs10 minutes

1 pluginTotal 15 minutes

Glossary: Unsupervised Learning and Generative Models in Keras 15 minutes

In this module, you will learn advanced techniques in Keras for model development. You will create custom training loops and optimize models using Keras and perform hyperparameter tuning with Keras Tuner. Finally, you will learn to use TensorFlow for model optimization and custom training loops. You will apply your learnings in labs and test your concepts in quizzes.

What's included

5 videos1 reading3 assignments2 app items1 discussion prompt1 plugin

5 videosTotal 18 minutes

Advanced Keras Techniques 3 minutesPreview module
Custom Training Loops in Keras 3 minutes
Hyperparameter Tuning with Keras Tuner 3 minutes
Model Optimization 4 minutes
TensorFlow for Model Optimization 3 minutes

1 readingTotal 2 minutes

Summary and Highlights: Advanced Keras Techniques 2 minutes

3 assignmentsTotal 55 minutes

Advanced Keras Techniques30 minutes
Practice Quiz: Advanced Keras Techniques and Custom Training Loops 10 minutes
Practice Quiz: Hyperparameter and Model Optimization 15 minutes

2 app itemsTotal 90 minutes

Lab: Custom Training Loops in Keras30 minutes
Lab: Hyperparameter Tuning with Keras Tuner60 minutes

1 discussion promptTotal 10 minutes

[Optional] Discussion Prompt: Custom Training Loops and Hyperparameter Optimization10 minutes

1 pluginTotal 15 minutes

Glossary: Advanced Keras Techniques15 minutes

In this module, you will learn the fundamentals of reinforcement learning and its applications in Keras. The module also covers the Q-Learning algorithms using Keras. You will develop and train deep Q-networks (DQNs) with Keras for advanced reinforcement learning tasks. You will apply your learnings in labs and test your concepts in quizzes.

What's included

3 videos1 reading2 assignments2 app items1 discussion prompt1 plugin

3 videosTotal 21 minutes

Reinforcement Learning (RL)8 minutesPreview module
Q-Learning with Keras 7 minutes
Deep Q-Networks (DQNs) with Keras 5 minutes

1 readingTotal 1 minute

Summary and Highlights: Introduction to Reinforcement Learning with Keras1 minute

2 assignmentsTotal 40 minutes

Graded Quiz: Introduction to Reinforcement Learning with Keras 30 minutes
Practice Quiz: Reinforcement Learning, Q-Learning, Q-Networks (DQNs) 10 minutes

2 app itemsTotal 120 minutes

Lab: Implementing Q-Learning in Keras60 minutes
Lab: Building a Deep Q-Network with Keras60 minutes

1 discussion promptTotal 10 minutes

Discussion Prompt: The Promise and Challenge of Reinforcement Learning10 minutes

1 pluginTotal 5 minutes

Glossary: Introduction to Reinforcement Learning with Keras5 minutes

In this module, you will implement the final project and attempt the final assessment.

What's included

1 video2 readings1 peer review2 app items2 plugins

1 videoTotal 6 minutes

Course Wrap-up6 minutesPreview module

2 readingsTotal 4 minutes

Congratulations and Next Steps2 minutes
Thanks from the Course Team2 minutes

1 peer reviewTotal 60 minutes

Peer-graded Assignment: Classify Waste Products Using Transfer Learning60 minutes

2 app itemsTotal 120 minutes

Practice Project: Fruit Classification Using Transfer Learning60 minutes
Final Project: Classify Waste Products Using Transfer Learning60 minutes

2 pluginsTotal 30 minutes

Practice Project Overview: Fruit Classification Using Transfer Learning15 minutes
Final Project Overview: Classify Waste Products Using Transfer Learning15 minutes