Mastering Deep Learning with Python
A comprehensive course covering the foundations of deep learning and neural networks, computer vision, and advanced techniques, through to real-world and creative applications including text and sequence data, based on Deep Learning with Python by Francois Chollet.
Course Overview
A comprehensive course covering the foundations of deep learning and neural networks, computer vision, and advanced techniques, through to real-world and creative applications including text and sequence data, based on Deep Learning with Python by Francois Chollet.
Course Syllabus
Chapter 1 — Foundations of Deep Learning
Module: Understanding Deep Learning Basics
Module: Neural Network Fundamentals
Chapter 2 — Accessing Support Resources
Module: Using the Private Web Forum
Chapter 3 — Introduction to Deep Learning
Module: Overview of Part 1
Chapter 4 — Foundational Concepts in Deep Learning
Module: Introduction to Fundamentals
Chapter 5 — Introduction to Deep Learning
Chapter 6 — Introduction to Deep Learning
Module: Understanding AI, Machine Learning, and Deep Learning
Module: History of Machine Learning
Module: Why Deep Learning Now?
Chapter 7 — Getting Started with Deep Learning
Module: Prerequisites and Target Audience
Module: Software and Hardware Requirements
Module: Accessing the Source Code
Module: Course Structure and Roadmap
Chapter 8 — Advanced Deep Learning Techniques
Module: Introduction to Advanced Deep Learning
Chapter 9 — Computer Vision with Deep Learning
Module: Introduction to Convolutional Neural Networks
Module: Training a Convnet on a Small Dataset
Module: Using Pretrained Convnets
Chapter 10 — Introduction to Neural Networks
Module: Understanding Neural Network Components
Module: Introduction to Keras and Workstation Setup
Chapter 11 — Mathematical Foundations of Neural Networks
Module: Tensors and Tensor Operations
Module: Tensor Operations in Neural Networks
Module: Introduction to Neural Networks
Chapter 12 — Machine Learning Essentials
Module: Branches of Machine Learning
Module: Evaluating Machine Learning Models
Module: Data Preprocessing and Feature Engineering
Module: Overfitting and Underfitting
Module: The Universal Workflow of Machine Learning
Chapter 13 — Applying Deep Learning in Real-World Scenarios
Module: Introduction to Convolutional Neural Networks
Module: Techniques for Improving Convolutional Neural Networks
Module: Visualizing Convolutional Neural Networks
Chapter 14 — Advanced Techniques for Deep Learning Models
Module: Advanced Model Optimization Techniques
Module: Building Complex Models with the Keras Functional API
Module: Monitoring and Controlling Model Training
Chapter 15 — Creative Applications of Deep Learning
Module: Text Generation with LSTM
Module: DeepDream
Module: Neural Style Transfer
Module: Variational Autoencoders
Module: Generative Adversarial Networks
Chapter 16 — Creative Applications of Deep Learning
Module: Text Generation with LSTM
Module: Variational Autoencoders and GANs
Module: DeepDream
Module: Neural Style Transfer
Chapter 17 — Deep Learning for Text and Sequence Data
Module: Text Preprocessing and Word Embeddings
Module: Recurrent Neural Networks
Module: Advanced Use of Recurrent Neural Networks
Module: Sequence Processing with Convnets
- Using 1D Convnets with Sequence Data
- 1D Pooling for Sequence Data
- Implementing a 1D Convnet
- Combining CNNs and RNNs
- Mapping Data Types to Deep Learning Applications
- Connect to Your EC2 GPU Instance and Manage Its Keys
- Local Generalization vs. Extreme Generalization
- Setting Up an AWS GPU Instance
- 1D Convnets Quiz
Course Access
Self-paced — start immediately after registering.
Ready to start?
Mastering Deep Learning with Python