Advanced Learning Algorithms Course Syllabus
Full curriculum breakdown — modules, lessons, estimated time, and outcomes.
Overview: This course provides a comprehensive introduction to advanced learning algorithms, focusing on neural networks and tree-based methods. Over approximately 32 hours, you'll gain hands-on experience building and training models using TensorFlow and Python from scratch. The curriculum emphasizes best practices in machine learning, ethical considerations, and real-world deployment strategies, supported by 14 labs and 14 quizzes that reinforce conceptual understanding and practical skills.
Module 1: Neural Networks
Estimated time: 7 hours
- Biological vs. artificial neurons
- Forward propagation
- Vectorized implementations
- Building neural nets in TensorFlow
- From-scratch Python implementations
Module 2: Neural Network Training
Estimated time: 10 hours
- Activation functions
- Loss functions
- Optimizers: Adam vs. gradient descent
- Multi-class classification
- Training strategies in TensorFlow
Module 3: Advice for Applying Machine Learning
Estimated time: 8 hours
- Model evaluation techniques
- Bias–variance trade-off
- Data-centric improvement methods
- Ethics and fairness in AI
- Error analysis and cross-validation
Module 4: Decision Trees
Estimated time: 7 hours
- Tree construction algorithms
- Information gain and splitting criteria
- Pruning techniques
- Random forests
- XGBoost and boosted trees
Prerequisites
- Familiarity with basic Python programming
- Understanding of linear algebra fundamentals
- Basic knowledge of machine learning concepts
What You'll Be Able to Do After
- Build and train neural networks using TensorFlow for multi-class classification
- Implement neural networks from scratch in Python
- Apply best practices to improve model generalization
- Construct and evaluate decision trees and ensemble models
- Conduct ethical AI assessments and error analysis