CIW AI Self-Study Course

26 short units that fill the gaps between the textbook and the CIW exam. Each unit has a concept, vocabulary, a working example, flashcards, a 10 point activity, a 20 point quiz, and a PDF summary with your percentage score. Each unit also has a Vocab Match assignment worth 20 points: drag the words onto their definitions, then submit and upload its own PDF for credit.

Domain 1: Ideas of AI,

A1Deep Learning, AI Careers, and Core NLP Vocabulary A2Rational Agents and the Environments They Act In A3How AI Systems Plan and Reason Under Uncertainty A4Logic Systems: Propositional, First-Order, and Fuzzy Logic A5Detecting Misinformation, Deepfakes, and Compromised Data A6Planning an AI Project: Deployment, Cost, and Risk

Domain 4: Legal, Ethical, and Privacy Issues,

A7Copyright, Training Data, and Evaluating Source Credibility

Domain 2: Data Management

B1Data Cleaning and Dataset Curation B2Common Data File Formats: CSV, JSON, and XML B3Feature Engineering and Sampling Plans B4Distribution Shift and Outlier Detection

Domain 3: Algorithms

C1Algorithm Families: Classification, Search, and Optimization C2Temperature and Controlling Generative AI Output C3Maximum Likelihood Estimation (Conceptual Introduction)C4Search Algorithms and Search Operators C5Bivariate Linear Regression and Computational Complexity C6K-Means Clustering, and Classification vs. Regression Mechanics

Domain 5: Machine Learning,

D1Reinforcement Learning and Transfer Learning D2Decision Trees, Random Forests, and Ensemble Methods D3Underfitting, Overfitting, and the Bias-Variance Tradeoff D4Naive Bayes, One-Hot Encoding, and Logistic vs. Linear Regression D5Explainability and the Black-Box Model Problem

Domain 6: Statistics

E1Data Types: Continuous, Binary, Categorical, and Ordinal E2Bayesian vs. Frequentist Approaches to Probability E3Cost Functions, Standard Error, and Bootstrapping E4Hypothesis Testing, the Curse of Dimensionality, and Sources of Uncertainty