Machine Learning
These notes cover the Machine Learning Specialization by Andrew Ng (DeepLearning.AI / Stanford).
These notes cover the Machine Learning Specialization by Andrew Ng (DeepLearning.AI / Stanford).
Specialization Roadmap
Course 1: Supervised Machine Learning: Regression and Classification
This course covers the foundations of machine learning, including:
- Linear regression
- Logistic regression (classification)
- Gradient descent
- Regularization
- Welcome to Machine Learning
- Supervised Learning
- Unsupervised Learning
- Linear Regression
- Cost Function
- Gradient Descent
- Multiple Linear Regression
- Vectorization
- Gradient Descent for Multiple Linear Regression
- Feature Scaling
- Checking Convergence and Choosing Learning Rate
- Feature Engineering and Polynomial Regression
- Classification
- Logistic Regression
- Cost Function for Logistic Regression
- Gradient Descent for Logistic Regression
- The Problem of Overfitting
- Regularization
- Regularized Linear and Logistic Regression
Course 2: Advanced Learning Algorithms
This course covers more powerful models and practical techniques:
- Neural networks
- Decision trees
- Advice for applying machine learning (bias/variance, debugging)
- Neural Networks Intuition
- Neural Network Model
- Forward Propagation
- TensorFlow Implementation
- Neural Networks in NumPy
- Lab: Handwritten Digit Recognition
- Training Neural Networks
- Activation Functions
- Multiclass Classification
- Additional Neural Network Concepts
- Lab: Handwritten Digit Recognition (Multiclass)
- Model Evaluation and Selection
- Bias and Variance
- Machine Learning Development Process
- Skewed Datasets: Precision, Recall, and the F1 Score
- Lab: Advice for Applying Machine Learning
- Decision Trees
- Decision Tree Learning
- Tree Ensembles
- Lab: Decision Trees
Course 3: Unsupervised Learning, Recommenders, Reinforcement Learning
This course covers a range of important algorithms beyond supervised learning:
- Clustering (K-means)
- Anomaly detection
- Recommender systems
- Reinforcement learning