SCIS 432: Artificial Intelligence

Spelman College — Spring 2026


Instructor: Antonio Khalil Moretti

Meetings: T/Th 1:00–2:15 PM, Tapley Hall 223

Office Hours: Tue 11 AM–12 PM, Tapley Hall 218

Syllabus: SCIS 432 Syllabus

Textbook: Russell & Norvig, Artificial Intelligence: A Modern Approach (4th ed.)

Prerequisites: Data Structures & Algorithms, Python

A comprehensive introduction to artificial intelligence, covering classical AI techniques and modern machine learning. Topics include search algorithms, game playing, constraint satisfaction, supervised learning, neural networks, and an introduction to deep learning and generative AI.

Schedule

Dates Topics AIMA Materials Assignment
1/15 Course Overview & Introduction to AI Slides
1/20–1/22 Uninformed Search
BFS, DFS, iterative deepening (IDDFS), search on maze problems
Ch. 3.1–3.4 Slides HW1: Intro & Search
1/27 Informed Search
Greedy best-first search, A*, admissible & consistent heuristics, IDA*, SMA*
Ch. 3.5 Slides HW2: A* on 8-Puzzle
1/29 Game Playing & Adversarial Search
Game trees, minimax algorithm, alpha-beta pruning
Ch. 5.1–5.3 Slides Minimax Viz HW3: Minimax & Alpha-Beta
2/3–2/5 Stochastic Games & Monte Carlo Tree Search
Probability basics, expectimax, explore/exploit tradeoffs, MCTS
Ch. 5.5 Slides 2048 Expectimax Autoplay
2/10 Constraint Satisfaction Problems
Backtracking, variable & value ordering, constraint propagation, arc consistency (AC-3)
Ch. 6 Slides HW4: CSP Sudoku
2/12–2/19 Introduction to Machine Learning & Linear Regression
ML fundamentals, linear regression, linear algebra review, normal equation
Ch. 18 Slides HW5: Linear Regression
2/24–3/3 Cross-Validation & Gradient Descent
Train-test split, polynomial regression, systems of equations, gradient descent
Ch. 18 Slides
3/17–3/26 Classification & Logistic Regression
Binary classification, logistic regression, decision boundaries
Ch. 18 Slides HW6: Logistic Regression
3/31–4/2 Logistic Regression Evaluation
Maximum likelihood estimation, precision, recall, F1, AUC
Slides
4/7 Introduction to Neural Networks
Perceptrons, activation functions, backpropagation
Slides
4/14–4/28 Project Presentations Project Description

Assignments

Assignments are Google Colab notebooks. To work on them, open the link and go to File → Save a copy in Drive.

Project

Project Description