Machine Learning Fundamentals

  1. Major Paradigms of Machine Learning
    1. Supervised Learning
      1. Core Concept: Learning from Labeled Data
        1. Key Tasks
          1. Regression
            1. Predicting Continuous Outputs
              1. Linear Relationships
                1. Non-Linear Relationships
                2. Classification
                  1. Predicting Discrete Categories
                    1. Binary Classification
                      1. Multi-Class Classification
                    2. Typical Use Cases
                      1. Medical Diagnosis
                        1. Email Spam Detection
                          1. Price Prediction
                            1. Image Classification
                          2. Unsupervised Learning
                            1. Core Concept: Finding Patterns in Unlabeled Data
                              1. Key Tasks
                                1. Clustering
                                  1. Grouping Similar Data Points
                                    1. Customer Segmentation
                                      1. Market Research
                                      2. Dimensionality Reduction
                                        1. Reducing Feature Space
                                          1. Data Visualization
                                            1. Noise Reduction
                                            2. Association Rule Learning
                                              1. Discovering Relationships Between Variables
                                                1. Market Basket Analysis
                                                  1. Web Usage Mining
                                                2. Typical Use Cases
                                                  1. Data Exploration
                                                    1. Feature Engineering
                                                      1. Anomaly Detection
                                                    2. Reinforcement Learning
                                                      1. Core Concept: Learning through Rewards and Penalties
                                                        1. Key Components
                                                          1. Agent
                                                            1. Decision Maker
                                                              1. Learning Entity
                                                              2. Environment
                                                                1. External System
                                                                  1. State Space
                                                                  2. Actions
                                                                    1. Available Choices
                                                                      1. Action Space
                                                                      2. Rewards
                                                                        1. Feedback Signals
                                                                          1. Reward Functions
                                                                          2. Policy
                                                                            1. Decision Strategy
                                                                              1. Action Selection Rules
                                                                              2. Value Function
                                                                                1. Expected Returns
                                                                                  1. State Values
                                                                                2. Exploration vs. Exploitation
                                                                                  1. Balancing Trade-offs
                                                                                    1. Exploration Strategies
                                                                                      1. Exploitation Strategies
                                                                                      2. Typical Use Cases
                                                                                        1. Game Playing
                                                                                          1. Robotics Control
                                                                                            1. Resource Allocation
                                                                                              1. Trading Strategies
                                                                                            2. Semi-Supervised Learning
                                                                                              1. Concept and Motivation
                                                                                                1. Limited Labeled Data
                                                                                                  1. Abundant Unlabeled Data
                                                                                                    1. Cost-Effective Learning
                                                                                                    2. Use Cases and Challenges
                                                                                                      1. Text Classification
                                                                                                        1. Image Recognition
                                                                                                          1. Medical Applications
                                                                                                            1. Label Propagation

                                                                                                        Previous

                                                                                                        1. Introduction to Machine Learning

                                                                                                        Go to top

                                                                                                        Next

                                                                                                        3. The End-to-End Machine Learning Workflow