Offered By: IBMSkillsNetwork
Fundamentals of Deep Learning using Keras
Master the fundamentals of deep learning with IBM! This course covers neural networks, supervised & unsupervised models, and how to build, train, and test deep learning models using Keras. Gain hands-on skills to kickstart your AI career.
Continue reading Premium
Course
Deep Learning
At a Glance
Master the fundamentals of deep learning with IBM! This course covers neural networks, supervised & unsupervised models, and how to build, train, and test deep learning models using Keras. Gain hands-on skills to kickstart your AI career.
About this course
This course provides a comprehensive introduction to deep learning, covering key concepts, algorithms, and hands-on implementation using the Keras library. Through engaging lectures, practical labs, and quizzes, you’ll develop a solid foundation in deep learning techniques and gain experience building real-world models.
Begin your deep learning journey with an introduction to the fundamental concepts of artificial intelligence, neural networks, and deep learning. Learn how artificial neurons mimic the human brain and explore the structure of neural networks. Through hands-on labs, you’ll gain practical experience in building artificial neural networks, reinforcing key principles before testing your knowledge with quizzes and assessments.
Dive deeper into the mechanics of deep learning by understanding key optimization techniques such as gradient descent and backpropagation. Discover the challenges of training deep networks, including the vanishing gradient problem, and explore the role of activation functions in improving model performance. Practical labs provide hands-on experience in implementing these techniques, ensuring you grasp their real-world applications.
Explore the power of Keras and other deep learning libraries used in AI development. Learn how to build regression and classification models using Keras, and apply your knowledge in lab exercises focused on implementing these models. This module equips you with essential tools for developing deep learning applications efficiently.
Expand your deep learning expertise by exploring different model architectures. Compare shallow and deep neural networks, and gain insights into specialized models like convolutional neural networks (CNNs) for image processing, recurrent neural networks (RNNs) for sequence data, and transformers for advanced AI applications. Hands-on labs guide you through implementing CNNs and transformers in Keras, reinforcing theoretical concepts with practical applications.
Put your knowledge to the test with a final project that challenges you to build a deep learning model for classification and captioning tasks. Apply the skills you’ve gained throughout the course to develop and evaluate your model, demonstrating your ability to create real-world AI solutions. Upon submission and evaluation, you’ll have a tangible project to showcase your deep learning expertise.
This course is designed for professionals and students looking to enhance their deep learning skills. Whether you’re aiming for a career in AI, data science, or software development, this hands-on learning experience will provide the foundation you need.
Learning Objectives:
After completing this course, you will be able to:
- Define key concepts such as neural networks, deep learning models, and activation functions.
- Explain the differences between supervised and unsupervised deep learning models.
- Implement deep learning models using Keras to solve real-world problems.
- Compare and contrast different deep learning architectures, including convolutional and recurrent neural networks.
- Assess the performance of deep learning models using appropriate metrics.
- Design, build, train, and test deep learning models using the Keras library.
Course Syllabus:
Welcome
- Video: Course Introduction
- General Information
- Learning Objectives and Course Syllabus
- Grading Scheme
- Helpful Tips for Course Completion
Introduction to Deep Learning and Neural Networks
- Module Introduction and Learning Objectives
- Video: Introduction to Deep Learning
- Video: Neurons and Neural Networks
- Video: Artificial Neural Networks
- Lab: Artificial Neural Networks
- Practice Quiz: Introduction to Deep Learning and Neural Networks
- Reading: Summary and Highlights: Introduction to Deep Learning and Neural Networks
- Graded Quiz: Introduction to Deep Learning and Neural Networks
Basics of Deep Learning
- Module Introduction and Learning Objectives
- Video: Gradient Descent
- Video: Backpropagation
- Lab: Backpropagation
- Video: Vanishing Gradient
- Video: Activation Functions
- Lab: Vanishing Gradient and Activation Functions
- Practice Quiz: Basics of Deep Learning
- Reading: Summary and Highlights: Basics of Deep Learning
- Graded Quiz: Basics of Deep Learning
Keras and Deep Learning Libraries
- Module Introduction and Learning Objectives
- Video: Deep Learning Libraries
- Video: Regression Models with Keras
- Lab: Regression with Keras
- Video: Classification Models with Keras
- Lab: Classification with Keras
- Practice Quiz: Keras and Deep Learning Libraries
- Reading: Summary and Highlights: Keras and Deep Learning Libraries
- Graded Quiz: Keras and Deep Learning Libraries
Deep Learning Models
- Module Introduction and Learning Objectives
- Video: Shallow Versus Deep Neural Networks
- Video: Convolutional Neural Networks
- Lab: Convolutional Neural Networks with Keras
- Video: Recurrent Neural Networks
- Video: Transformers
- Lab: Transformers with Keras
- Video: Autoencoders
- Practice Quiz: Deep Learning Models
- Reading: Summary and Highlights: Deep Learning Models
- Graded Quiz: Deep Learning Models
Final Project
- Module Introduction and Learning Objectives
- Final Project: Classification and Captioning
- Final Project Submission and Evaluation
Course Wrap-Up
- Video: Course Wrap-Up
- Reading: Congratulations and Next Steps
- Reading: Team and Acknowledgments
- Copyrights and Trademarks
Course Rating and Feedback
- Course Rating and Feedback
Badge
- Claim Your Badge Here
General Information:
- This course is self paced.
- This platform works best with current versions of Chrome, Edge, Firefox, Internet Explorer, or Safari.
Recommended Skills Prior to Taking this Course
- Working knowledge of Python.
- Machine Learning with Python
Estimated Effort
9 Hours
Level
Intermediate
Skills You Will Learn
Algorithms, Artificial Intelligence, Artificial Neural Networks, Deep Learning, Keras, Python
Language
English
Course Code
DL0101EN