- About this Course: Machine Learning Fundamentals
- What is Covered in this Course, Learning Support, & Discounts
- Brief Instructor Bio
- Introduction to Part 1 & The definition of a Model
- Example: A Basic Linear Regression Model
- Initial High-Level Model Lifecycle & Model-Related Terminology
- How our linear regression example fits the definition of a model
- The Two Essential Model Types: Regression & Classification
- Example: A Basic Decision Tree Classification Model
- Wrapping Up Our Knowledge of Models
- Optional: Model Parameters & Model Hyperparameters Defined
- Models: A Key Component of a Learning Process
- Updating Models
- Machine Learning Defined
- ML-Related Terminology
- Optional: Old School Statistical Methods vs. New School Machine Learning Methods
- Optional: Supervised vs. Unsupervised Learning
- Deep Learning Defined
- AutoML Defined
- Artificial Intelligence (AI) Defined
- Common Machine Learning Pitfalls
- Optional (Humor): Model Training vs. Model Building
- Conclusion of Part 1
- Introduction to Part 2
- Common ML Misconceptions
- Paths to Identifying Use Cases
- Browsing / Gathering ML & AI Use Cases
- Process Inspection
- Process Inspection: Leverage Process Improvement Disciplines
- Process Inspection: Unpack your KPIs
- ML Themes
- ML Theme 1: Replace Imperfect Rule-Based Systems
- ML Theme 2: Breaking an Average
- ML Theme 3: Allocate Limited Resources
- ML Theme 4: Analyze Human Decisions
- ML Theme 5: Analyze Activities at Scale
- ML Theme 6: Predict Events
- ML Theme 7: Predict People
- AI & Chatbots
- Conclusion of Part 2
- Introduction to Part 3
- Potential Disqualifier: Ethical Concerns
- Potential Disqualifier: Fitness for Use
- Feasibility Analysis
- Feasibility Analysis: Establish a Business Hypothesis
- Feasibility Analysis: Sketch Out the Business Process
- Feasibility Analysis: Estimate High-Level ROI
- Optional: Lock Down the Target & Population
- Feasibility Analysis: Assessing Your Data - The Model Target
- Feasibility Analysis: Assessing Your Data - Do we have enough data?
- Feasibility Analysis: Assessing Your Data - Availability & Readiness
- Feasibility Analysis: Assessing Your Data - Data Quality
- Feasibility Analysis: Determine Model Requirements
- Feasibility Analysis: Wrap-Up
- Performance Measurement
- Performance Measurement: Introduction to Analyzing Regressors
- Performance Measurement: Mean Absolute Error (MAE)
- Performance Measurement: Regression Simulation Example
- Performance Measurement: Simulation of Repeated Processes
- Performance Measurement: Historical Median Baseline
- Performance Measurement: Summary for Measuring Regressors
- Performance Measurement: Analyzing Classifiers
- Performance Measurement: Limitations of Accuracy & Class Imbalance
- Performance Measurement: Classifier Outcomes & Value
- Performance Measurement: The Baseline for Classification Models
- Performance Measurement: Using Probability of Class Membership
- Performance Measurement: Summary for Measuring Classifiers
- Optional: Assessing Classifier Calibration
- Experimental Design
- Conclusion of Part 3
- Introduction to Part 4 & Organizational Context
- Buying Software & Services
- Buying Software & Services: Deployment Configurations
- Buying Software & Services: Key Questions
- Consulting Engagements
- Infrastructure - MLOps
- Infrastructure: Data Concerns
- Infrastructure: Compute Concerns
- Infrastructure: Cloud Computing
- Infrastructure: AutoML
- Conclusion of Part 4
- Introduction to Part 5 & Optimizing your Business
- Optimizing your Business: Opportunities & Probabilities
- Optimizing your Business: Human & Machine Learning
- AutoML
- Information Strategy
- Conclusion