Course Information

Schedule

Section 1:	Meeden: MW 10:30-11:45 Martin 204
Section 2:	Mitchell: TR 11:20-12:35 Sci 199
Lab A:	Meeden R 1:05-2:35 Martin 213
Lab B:	Mitchell R 1:05-2:35 Martin 313
Lab C:	Kazer F 2:00-3:30 Martin 313
Lab D:	Kazer F 3:45 - 5:15 Martin 313

Contact Information

Professor:	Lisa Meeden
Email:	lmeeden at swarthmore.edu
Office:	Martin 208
Office Hours:	TBD
Professor:	Ben Mitchell
Email:	mitchell at cs.swarthmore.edu
Office:	Martin 334
Office Hours:	TBD
Lab Instructor:	Charlie Kazer
Email:	ckazer at cs.swarthmore.edu
Office:	Martin 330
Office Hours:	TBD

Introduction

This course provides a broad introduction to the foundations of modern artificial intelligence (AI) and will also develop advanced programming and data processing skills essential for upper-level courses in computer science. Topics will include advanced Python programming, mathematical foundations, data processing, machine learning methodology, neural networks, and large language models. Throughout the course, students will examine the ethical issues that arise in AI and its societal impacts. The course culminates in a final project. Students will gain core skills that will prepare them for a deeper examination of these issues in both later courses and independent projects.

The course is suitable for any student interested in gaining a deeper understanding of AI regardless of their intended major.

Prerequisite: Completion of CPSC 21 or its equivalent.

Goals for student learning

• Gain a deeper understanding of modern AI systems including neural networks and generative models for both text and images.
• Work with data from acquisition to application, including understanding the limitations and potential pitfalls at each stage of the data pipeline.
• Learn about the societal implications of technology and different interdisciplinary tools for analyzing these systems.
• Develop more advanced programming skills in Python, including the use of notebooks, libraries, APIs, and other object-oriented programming techniques.
• Provide mathematical foundations for AI and ML including linear algebra and basic statistics.
• Prepare students for upper-level applications courses.
• Learn to work effectively as a team on an open-ended project.

---

Grading

Grade weighting

5%	Class Participation
30%	Labs
20%	Exam 1
20%	Exam 2
25%	Final Project

---

Reading

Rather than using a single textbook, we will be using materials from a variety of sources. Many of the materials will be available online.

---

Policies

Labs

Academic Integrity

Academic Accommodations

---

Schedule

WEEK	DAY	ANNOUNCEMENTS	TOPIC & READING	LAB
1	Aug 31		Overview of AI and Machine Learning Jagged Intelligence: The dangerous unknowns at the heart of LLMs, by Melanie Mitchell, The Yale Review, June, 2026 Consequences of using automated systems in the real world Motivating example: Self-driving cars	Lab 1: Critiquing generative AI models
	Sep 02
2	Sep 07	Labor Day
	Sep 09		Data Science Pre-processing data Feature engineering Data visualization Basic statistics	Lab 2: Advanced Python
3	Sep 14		Introduction to Modeling What is a model? Determining a model's fitness Complexity of a model Linear regression	Lab 3: Data cleanup and analysis using pandas
	Sep 16
4	Sep 21		Classification, Logistic Regression	Lab 4: Logistic Regression
	Sep 23
5	Sep 28		Neural Networks Non-linear models Backpropagation Hyperparameters	Lab 5: Implementing Backprop
	Sep 30
6	Oct 05		Ethical issues that arise with data Data provenance Data diversity Data imbalance How data is applied to solve problems	Exam 1 in lab
	Oct 07
	Oct 12	Fall Break
	Oct 14
7	Oct 19		Dimensionality Reduction Principal components analysis Visualizing hidden layers	Lab 6: Use PCA on models
	Oct 21
8	Oct 26		Evaluating Models Overfitting and Underfitting Hyperparameter tuning Possible harms	Lab 7: Evaluate some models
	Oct 28
9	Nov 02		Advanced Neural Networks that Process Text Generative vs Discriminative Models Word embeddings LLMs and Transformers Prediction	Lab 8: Sentiment analysis with LLMs
	Nov 04
10	Nov 09		Advanced Neural Networks that Process Images Generative Models	Lab 9: Image generation
	Nov 11
11	Nov 16		Project Development Provide limited set of possibilities Staged development plan Deliverable (paper/poster/presentation)	Project Proposal
	Nov 18
12	Nov 23		Societal Implications of ML Models Disparate Impact Transparency/explainability Stakeholders	No lab Thanksgiving break
	Nov 25
13	Nov 30		More on Societal Implications	Project Continues
	Dec 02	Exam 2
14	Dec 07	Last lecture meeting	TBD	Finish Project
	Dec 09	Follows a Friday schedule