Course Information

Schedule

Class:	Monday, Wednesday, 9:00-10:15am, Science Center 204
Lab A (Hope):	Tuesday 1:05-2:35pm, Martin 113
Lab B (Hope):	Tuesday 2:45-4:15pm, Martin 113
Lab C (Soni):	Tuesday 2:45-4:15pm, Martin 313

Contact Information

Communication:	Ed Discussion Platform Important announcements will be posted here You can ask questions and answer other students' questions here
Instructor:	Gabriel Hope
Email:	ghope1@swarthmore.edu
Office:	Martin 236
Office Hours:	Monday, 3:00–5:00 p.m., Martin 236 Wednesday, 11:00 a.m.–12:30 p.m., Martin 236
Co-Instructor:	Ameet Soni
Email:	asoni1 at swarthmore dot edu
Office:	Martin 232
Office Hours:	Friday, 10:00–11:00 a.m., Martin 232 Wednesday, 3:30–4:30 p.m., Martin 232

Introduction

Artificial Intelligence (AI) is the branch of computer science that is concerned with the automation of intelligent behavior. "Intelligent behavior" encompasses a wide range of abilities, and as a result AI has become a very broad field.

In recent years, the term "AI" has become associated very strongly with large-language models used for text generation (e.g. ChatGPT, Gemini, Claude, etc.). While we will discuss these models, the course will not be entirely centered on them. Our understanding of "AI" will be that AI is a field of study which has existed for many decades, and includes search, game playing, reasoning, planning, natural language processing, computer vision, modeling human performance (cognitive science), machine learning, and robotics. This course will focus on a subset of these topics, specifically search and machine learning, while also drawing connections to cognitive science.

In search, we will see familiar techniques such as depth-first and breadth-first, as well as new techniques such as A*, minimax, and simulated annealing applied to AI problems. In machine learning, which is concerned with programs that define their behavior in terms of previous examples, we will explore reinforcement learning and neural networks, including the popular sub-field of deep learning, of which LLMs are a sub-sub-field. The first half of the semester will focus on search, and the second half of the semester will focus on machine learning.

Goals for the course

• Apply a variety of search techniques to AI problems.
• Apply a variety of machine learning techniques to AI problems.
• Compare and contrast the strengths and weaknesses of various AI approaches.
• Given a particular AI problem, determine an appropriate representation and approach for solving it.
• Understand the ethical implications and dangers of AI.

---

Grading

Course grade breakdown

Weight	Coursework
10%	Class Participation
45%	Exams
25%	Labs
20%	Final Project

Class Participation

Staying engaged with the course material throughout the semester is critical for your learning and for your grade.

---

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. You only need to purchase the first text listed below by Melanie Mitchell, which is required.

• Artificial Intelligence: A Guide for Thinking Humans, by Melanie Mitchell
• Artificial Intelligence: A Modern Approach (3rd Edition), by Stuart Russell and Peter Norvig
• Note: there is a 4th Edition of this book, which is very expensive and isn't actually any better for the parts we're using. If you happen to already have a copy of the 4th edition you can use it, but don't go out of your way to buy one.
• Artificial Intelligence: Foundations of Computational Agents (2nd Edition), by David Poole and Alan Mackworth

Our class meetings will be a combination of lecture and discussion. To be ready to participate in the discussion will require some preparation on your part. Most of this will consist of careful reading and reflection on the assigned reading through the use of reading questions.

Preparation

You should check the class schedule and complete each assigned reading before the class meeting where it appears. You will get the most out of the reading if you approach it as follows:

• Overview: You should quickly skim through the reading once to get an overview of the material to be covered, paying particular attention to subject headings and topic introductions. This should be very quick.
  (Estimated time: 5 minutes)
• In-Depth: Next, read the material closely. Try to understand what individual steps of algorithms are accomplishing. Not everything will make sense at this point, but hopefully many things will.
  (Estimated time: 40 minutes)
• Final Notes: After carefully reading the material, mentally review and try making a few notes to yourself about what you think are the most important concepts being covered, as well as any questions that you have.
  (Estimated time: 5 minutes)

Many of the readings are fairly short, but can contain mathematics or algorithms that require a moderate amount of study. Make your best effort to understand the material and bring any questions you have to class. Then we can have a productive discussion with examples and exercises to clarify the material.

Reading Questions

To help focus your efforts and give us a basis for discussion, you will be provided with a short list of reading questions to consider for each week's reading. Reflecting on your responses to the questions will help give you a deeper understanding of the most important concepts surrounding each topic. Be ready to discuss your answers in class!

---

Policies

Labs

Lab release and due dates will be posted on the course schedule and course platforms. Generally, labs will be due the following Monday at 11:59 PM, with the exception of Lab 1. Even if you do not fully complete a lab, you should submit what you have done to receive partial credit.

You have three late days that you may use on any lab, for any reason. If you are using a late day, you must contact me by email or private message on Ed to let me know.

Your late days will be counted at the granularity of full days and will be tracked on a per-student (NOT per-partnership) basis. That is, if you turn in an assignment five minutes after the deadline, it counts as using one day. For partnered labs, using a late day counts towards the late days for each partner. In the rare cases in which only one partner has unused late days, that partner's late days may be used, barring a consistent pattern of abuse.

If you feel that you need an extension on an assignment or that you are unable to attend class for two or more meetings due to a medical condition or other extenuating circumstance, please let me know as soon as possible.

Academic Integrity

Academic honesty is required in all of your work. Under no circumstances may you hand in work done with (or by) someone else under your own name. Your code should never be shared with anyone; you may not examine or use code belonging to someone else, nor may you let anyone else look at or make a copy of your code. The only exception to this policy is that you may freely share code with your lab partner.

You should not obtain solutions from students who previously took the course or copy code that can be found online. You may not share solutions after the due date of the assignment.

Failure to abide by these rules constitutes academic dishonesty and will lead to a hearing of the College Judiciary Committee. According to the Faculty Handbook: "Because plagiarism is considered to be so serious a transgression, it is the opinion of the faculty that for the first offense, failure in the course and, as appropriate, suspension for a semester or deprivation of the degree in that year is suitable; for a second offense, the penalty should normally be expulsion."

Discussing ideas and approaches to problems with others on a general level is fine (in fact, we encourage you to discuss general strategies with each other), but you should never read any other student's code or let another student read your code. All code you submit must be your own with the following permissible exceptions: code distributed in class and code given in the readings. Regardless of the source, you should always include comments that indicate on which parts of the assignment you received help, and what your sources were. You may not share your solutions even after the due date of the assignment.

Any code, text, or content not created exclusively by you and used without attribution is plagiarism. This is true regardless of whether the original source was a scholarly text, another student, an online platform (e.g. StackOverflow), or a generative model (e.g. ChatGPT). Using resources such as these may be appropriate under some circumstances, and not under others, but regardless you must always properly acknowledge and cite the source of the information. When in doubt, add a statement of attribution! In addition, when using any type of generative AI, you must also describe how it was used, e.g. by giving the prompt.

AI Usage Policy

In this course we will be learning the fundamental tools for building large language models and chat AIs, such as ChatGPT. Therefore I encourage you to experiment with ChatGPT and its competitors during this course, but only for learning about concepts.

The use of generative AI tools (e.g. ChatGPT, GitHub Copilot, etc.) for lab assignments without permission is considered to be unauthorized collaboration with an outside source and is a violation of our academic integrity policy. You may not share any assignment materials with large language models including assignment questions, support code and your own answers. This includes AI-assisted coding tools such as GitHub Copilot and Google Gemini in Colab. Please disable these tools when working on class lab assignments. As stated above, failure to do so will be considered a violation of the academic integrity policy.

Be cautious when using generative AI tools for learning purposes. AI models are not an authoritative source of information, and they can produce incorrect or misleading information. You should always first seek primary sources (e.g. textbooks, scholarly articles, or other authoritative sources) as your starting point, and use generative AI tools only as a supplement to your learning. If you do use generative AI tools for learning purposes, you must always properly attribute the source of the information and describe how it was used.

You may not use generative AI to respond to reading questions or questions on Ed.

You may use AI-assisted coding tools in the final project for debugging and for coding non-core parts of your project (e.g. for setting up the development environment, reading and writing files and interacting with libraries). If you feel these tools would be appropriate in a given context, please contact the instructor to ask. Note that even if permission is granted, these sources must be properly attributed.

Here are some examples of what this might look like:

Academic Accommodations

If you believe you need accommodations for a disability or a chronic medical condition, please visit the Student Disability Services website for details about the accommodations process. Since accommodations require early planning and are not retroactive, contact Student Disability Services as soon as possible. You are also welcome to contact me privately to discuss your academic needs. However, all disability-related accommodations must be arranged, in advance, through Student Disability Services.

---

Schedule

WEEK	DAY	TOPICS	READINGS	LAB	EXTRAS
1	Aug 31	Intro to AI Course survey		Guide to lab assignments Lab 1: Robot Maze Due Sep. 9 at 11:59 p.m.	Optional: Quick, Draw! AI game
	Sep 02	Agents, Environments, State-based Search [S26]	Roots of Artificial Intelligence Mitchell Ch. 1 Reading questions Problem solving R&N 3.1-3.3		Optional: The Fastest Maze-Solving Competition On Earth
2	Sep 07	No class on Labor Day		Lab 2: Informed search Due Sep. 14 at 11:59 p.m.
	Sep 09	Uninformed Search [S26], Informed Search [S26]	Uninformed search R&N 3.4 Informed search R&N 3.5-3.7 Reading questions		Optional: Google Maps is unreasonably fast. Let me explain A* pathfinding visualizer
3	Sep 14	Local Search [S26]	Hill climbing, Simulated annealing, and Beam search R&N 4.1 Reading questions	Lab 3: Local search Due Sep. 21 at 11:59 p.m.	Optional: Simulated annealing demo
	Sep 16	Game Search [S26]	Minimax
4	Sep 21	Minimax and Alpha-Beta Pruning [S26]	Alpha-beta pruning P&M 11.3 Reading questions	Lab 4: Game play with Minimax Due Sep. 28 at 11:59 p.m.	Optional: Minimax and alpha-beta visualizer
	Sep 23	Monte Carlo Tree Search [S26]	The Grand Challenge of Go Mitchell Ch. 9 (pgs. 152-164) MCTS Reading questions		Optional: AlphaGo Movie
5	Sep 28	MCTS implementation [S26]		Lab 5: MCTS Due Oct. 5 at 11:59 p.m.	Optional: Monte Carlo Tree Search (Computerphile)
	Sep 30	Problems with symbolic AI [S26]	The Fundamental Problems of Classical AI and Cognitive Science P&S Ch. 3 Reading questions		Optional: ELIZA rule-based chatbot demo
6	Oct 05	Exam 1 Review Exam 1 Study Guide Exam 1 in lab (Oct 06)	Exam 1 Study Guide	Exam 1 in lab
	Oct 07	Intro to Neural Networks [S26] Perceptron training rule [S26]	Review pgs 24-34 on Perceptrons Mitchell Ch. 1 Neural Networks and the Ascent of Machine Learning Mitchell Ch. 2
	Oct 12	Fall Break
	Oct 14
7	Oct 19	Multi-layer Neural Networks [S26] Derivation of Back Propagation [S26]	Videos on neural networks and backpropagation Reading questions	Lab 6: Neural Networks Due Oct. 26 at 11:59 p.m.	Optional: TensorFlow neural network playground
	Oct 21	Applying ML to categorization tasks [S26]	Who, What, When, Where, Why Mitchell Ch. 4
8	Oct 26	Deep learning and Convolution networks [S26]	ConvNets and ImageNet Mitchell Ch. 5 Convolutional Neural Networks for Visual Recognition Reading questions	Lab 7: Convolutional Networks Due Nov. 2 at 11:59 p.m.	Optional: Teachable Machine CNN Explainer
	Oct 28	Introduction to Reinforcement Learning [S26]	Rewards for Robots Mitchell Ch. 8
9	Nov 02	Approximate Q-learning [S26]	Game On Mitchell Ch. 9 (pgs. 145-152) Beyond Games Mitchell Ch. 10 Reading questions	Lab 8: Reinforcement Learning Due Nov. 9 at 11:59 p.m.	Optional: Q-learning Snake visualizer
	Nov 04	Evolutionary Computation [S26]	Genetic algorithms Mitchell GA Ch. 1
10	Nov 09	GA Schema Theorem [S26] Worksheet [S26]	Evolving Neural Networks Mitchell GA Sec. 2.3 Reading questions	Lab 9: Genetic Algorithms Due Nov. 16 at 11:59 p.m.	Optional: Genetic Cars 2
	Nov 11	Evaluating ML [S26]	A Closer Look at Machines that Learn Mitchell Ch. 6 Reading questions		Optional: Precision, recall, and F1 interactive demo
11	Nov 16	Word embeddings demo Nano GPT demo	Financial Times on Generative AI LLM reading questions	Final Project Introduction	Optional: Interactive LLM tokenization demo
	Nov 18	Large Language Models			Optional: How LLMs work and that's why they don't
12	Nov 23	In-class review [S26]	Exam 2 Study Guide	Exam 2 in lab
	Nov 25	Thanksgiving Break
13	Nov 30	Transformers [S26]	Transformers, the Tech Behind LLMs (video) Transformer reading questions	Project checkpoint & peer review	Optional: Transformer Explainer
	Dec 02	Philosophy of AI [S26] Embodiment [S26] Subsumption demo	Knowledge, Abstraction, and Analogy in AI Mitchell Ch. 15 Questions, Answers, and Speculations Mitchell Ch. 16 Reading questions		Optional: Moral Machine 3D Boids simulation Optional: AI and our future
14	Dec 07	Last CS 63 lecture meeting Project Tips [S26] Summing up [S26]
	Dec 14	Final project poster session (exact date and time to be announced)