AI-240-paul.wilmoth-2026-08-20-01-12-39
Title of Course [Foundations of Artificial Intelligence]
Prefix and Number [AI 240]
Semester and Year [tbd]
Number of Credit Hours [3]
Prerequisites [AI 142 or CPTS 122; MATH 225]
Course Details
Day and Time: [tbd]
Meeting Location: [tbd]
Instructor Contact Information
Instructor Name: [tbd]
Instructor Contact Information: [office location, phone, email] [tbd]
Instructor Office Hours: [click here for best practices] [tbd]
TA Name: [tbd]
TA Contact Information: [office location, phone, email]: [tbd]
TA Office Hours: [click here for best practices] [tbd]
Course Description
Building on AI 142 and MATH 225, this course develops the representational and computational foundations underlying modern artificial intelligence systems. Students repeatedly apply a common AI development pipeline (problem definition, data, approach, training or configuration, metrics, evaluation, improvement, and reflection) at increasing levels of technical sophistication. They formulate AI problems, implement a representative problem-solving method, apply linear algebra to AI implementations, manipulate multidimensional tensors, and use contemporary AI framework.
Through structured AI Studios and cumulative programming assignments, students plan before implementation, log design decisions during execution, evaluate results against defined criteria, and reflect on limitations and responsible implementation. Students construct computational workflows involving loss functions, computational graphs, automatic differentiation, and optimization, then integrate and defend their work in a final project. The course prepares students for upper-division study in machine learning, neural networks, data science, search, planning and reasoning without duplicating the advanced content of those courses.
Course Materials
Books: No single textbook is required. Selected readings will be drawn from Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach, 4th edition. Instructor-provided readings and official documentation for the selected AI framework will supplement the conceptual material.
Other Materials: Students will use Python, Jupyter Notebook, GitHub, Numpy, Matplotlib, and a contemporary AI or machine-learning framework such as PyTorch. Instructor-provided notebooks, datasets, programming exercises, and technical documentation will be available through Canvas. All required software will be open source or institutionally provided at no cost.
Fees: none
|
Course Learning Outcomes (students will be able to:) |
Activities Supporting the Learning Outcomes | Assessment of the Learning Outcomes |
|---|---|---|
| 1. Explain and trace how problem definition, data representation, computation, learning or configuration, evaluation, improvement, and reflection interact within an AI system (6a). | Lectures, pipeline maps, worked examples, AI Studios, and system analyses | Pipeline analyses, quizzes, midterm practical, and final technical defense |
| 2. Formulate well-defined AI problems using inputs, representations, objectives, computational processes, outputs, performance measures, assumptions, and constraints (1b, 1c, 2c). | Problem-formulation studios, design worksheets, critique, and case-based activities | Problem brief, studio notebooks, programming assignments, and final project proposal |
| 3. Implement a representative AI problem-solving method using an appropriate symbolic or numerical representation (2g, 6a, 7f). | Algorithm demonstrations, guided programming studios, debugging, and code review | Coding exercises, Programming Assignment 1, and practical assessments |
| 4. Apply linear algebra and introductory probability to AI representations and explain how gradients and optimization support computational learning (6a). |
Worked examples, visualizations, mathematical review, and controlled notebook experiments |
Homework, quizzes, midterm practical, and programming activities |
| 5. Create, manipulate, and analyze multidimensional tensors using a contemporary AI framework (6a). |
Tensor studios, guided notebooks, framework exercises, and peer debugging |
Studio notebooks, coding checks, and Programming Assignment 2 |
| 6. Construct and evaluate a basic computational workflow involving data tensors, a loss function, automatic differentiation, parameter updates, a baseline, and defined performance measures (2a, 2e, 2g, 6a, 6b, 7f). |
Framework demonstrations, implementation studios, controlled comparisons, and checkpoint reviews |
Programming Assignment 3, midterm practical, and final integration project |
| 7. Design, document, and defend, a reproducible AI experiment, including its assumptions, evidence, limitations, failure modes, and responsible implementation safeguards (2c, 2e, 3b, 3d, 6e, 6f). |
Version control, experiment logs, peer critique, technical writing, reflection, and oral defense |
Repository, evaluation report, responsible-implementation review, and final presentation |
| Dates | Lesson Topic | Assignment or Activity | Assessment |
|---|---|---|---|
|
Week 1 |
AI systems and the recurring development pipeline | Pipeline diagnostic and system-mapping activity | Diagnostic activity |
| Week 2 |
Problem formulation; symbolic and numerical representations | AI Studio 1: plan --> execute --> log --> debrief | Problem and representation brief |
| Week 3 |
State-space representation and representative problem solving | AI Studio 2: search implementation and debugging | Programming Assignment 1 begins |
| Week 4 |
Linear algebra for representations, similarity, and transformations | Numpy representation experiment | Programming Assignment 1 |
| Week 5 |
Tensor foundations: shapes, data types, indexing, and reshaping | AI Studio 3: tensor representations and shape debugging | Concept check 1 |
| Week 6 |
Tensor operations, broadcasting, matrix multiplication, and vectorization | Controlled tensor-computation comparison | Programming Assignment 2 begins |
| Week 7 |
Contemporary AI frameworks and device-aware computation | Framework tensor and device studio | Programming Assignment 2 |
| Week 8 |
Synthesis: representations, tensors, pipeline tracing, and failure diagnosis | Individual practical and conceptual activities | Midterm practical |
| Week 9 |
Datasets, partitions, batching, provenance, and computational workflows | AI Studio 4: data-flow plan and reproducibility log | Concept check 2 |
| Week 10 |
Objective and loss functions; gradient intuition | Loss and gradient visualization experiment | Programming Assignment 3 begins |
| Week 11 |
Computational graphs and automatic differentiation | Automatic differentiation studio and gradient debugging | Programming Assignment 3 |
| Week 12 |
Optimization, learning rates, and parameter updates | Controlled optimization experiment | Final project Checkpoint 1 |
| Week 13 |
Probability, randomness, uncertainty, and experimental variation | AI Studio 5: evaluation protocol and failure-mode plan | Final project Checkpoint 2 |
| Week 14 |
Evaluation, baselines, error analysis, and reproducibility | Peer critique of evidence, logs, and safeguards | Evaluation report draft |
| Week 15 |
Responsible implementation, communication, and technical defense | Build-evaluate-defend presentations | Presentation and defense |
| Finals | Course synthesis and integration | Final repository and report submission | Final integration project |
Expectations for Student Effort
For each hour of lecture equivalent, students should expect to have a minimum of two hours of work outside of class.
Grading
| Assessment Category | Description | Weight |
|---|---|---|
| Concept checks and pipelines briefs | Short conceptual, mathematical, problem-formulation, and reflection tasks | 15% |
| AI Studios and laboratory notebooks | Structured plan-execute-log-debrief activities completed primarily during scheduled learning time | 20% |
| Three scaffolded programming assignments | Cumulative individual assignments aligned with the major technical units | 30% |
| Midterm practical and concept examination | Pipeline tracing, controlled comparison, failure diagnosis, and foundational concepts | 15% |
| Final build-evaluate-defend project | Implementation, evaluation, repository, documentation, safeguards, report, and technical defense | 20% |
| Total | 100% |
| Grade | Percent | Grade | Percent |
|---|---|---|---|
| A |
93 -- 100% |
C | 70 -- 76.99% |
| A- | 90 -- 92.99% | C- | 67 -- 69.99% |
| B+ | 87 -- 89.99% | D | 60 -- 66.99% |
| B | 83 -- 86.99% | F | less than 60% |
| B- | 80 -- 82.99% | ||
| C+ | 77 -- 79.99% |
Attendance and Make-Up Policy
Students should make all reasonable efforts to attend all class meetings. However, in the event a student is unable to attend a class, it is the responsibility of the student to inform the instructor as soon as possible, explain the reason for the absence (and provide documentation, if appropriate), and make up class work missed within a reasonable amount of time, if allowed. Missing class meetings may result in reducing the overall grade in the class.
Academic Integrity Statement
You are responsible for reading WSU's Academic Integrity Policy, which is based on Washington State law. If you cheat in your work in this class you will:
-Fail the assignment or exam in which the cheating happened
-Be reported to the Center for Community Standards
-Have the right to appeal my decision
-Not be able to drop the course of withdraw from the course until the appeals process is finished
If you have any questions about what you can and cannot do in this course, ask me.
If you want to ask for a change in my decision about academic integrity, use the form at the Center for Community Standards website. You must submit this request within 21 calendar days of the decision.