Introduction to Deep Learning & Neural Networks with Keras Course Syllabus

Overview: This course provides a comprehensive introduction to deep learning and neural networks using the Keras library. Designed by IBM, it blends theoretical concepts with hands-on practice, ideal for professionals seeking to build practical AI skills. The course spans approximately 9 hours of content, divided into five core modules and a final project, offering flexible pacing for working learners.

Module 1: Introduction to Deep Learning and Neural Networks

Estimated time: 1 hour

• Explore the basics of deep learning
• Understand neural network architectures
• Examine real-world applications of neural networks
• Learn the role of deep learning in artificial intelligence

Module 2: Supervised Deep Learning Models

Estimated time: 2 hours

• Study the principles of supervised learning
• Implement convolutional neural networks (CNNs)
• Explore recurrent neural networks (RNNs)
• Apply supervised models to labeled datasets

Module 3: Unsupervised Deep Learning Models

Estimated time: 2 hours

• Understand unsupervised learning frameworks
• Implement autoencoders for feature learning
• Explore restricted Boltzmann machines (RBMs)

Module 4: Building Deep Learning Models with Keras

Estimated time: 2 hours

• Learn the Keras library fundamentals
• Construct and compile deep learning models
• Train and evaluate models using Keras

Module 5: Applications of Deep Learning

Estimated time: 2 hours

• Discover applications in computer vision
• Explore natural language processing (NLP) use cases
• Examine industry implementations in healthcare, finance, and technology

Module 6: Final Project

Estimated time: 3 hours

• Design a deep learning model using Keras
• Apply concepts from supervised or unsupervised learning
• Present findings and model performance

Prerequisites

• Basic familiarity with Python programming
• Fundamental understanding of machine learning concepts
• Comfort with mathematical reasoning and data structures

What You'll Be Able to Do After

• Understand the fundamentals of neural networks and deep learning models
• Differentiate between supervised and unsupervised deep learning models
• Implement deep learning models using the Keras library
• Build and train models for real-world applications
• Gain insights into deep learning applications across industries