Bryn Mawr College
CMSC 373: Artificial Intelligence
Fall 2025
Course Materials
Prof. Deepak Kumar
General Information
Instructor(s)
Deepak Kumar
202 Park Science Building
526-7485
dkumar at brynmawr dot edu
https://cs.brynmawr.edu/~dkumar/
Lecture Hours: Mondays & Wednesdays from 10:10a to 11:30a
Office Hours: Mondays 2:40 to 4:00p and more TBA.
Lecture Room: Room 338 Park Science Building
Lab:
- Lab: Mondays 2:40p to 4:00p in Room Park 230
Laboratories
- Computer Science lab Room 230 (Science Building)
Texts & Software
Main Texts (Required)
- [Buy] A Brief History of Artificial Intelligence, by Michael Wooldridge
Flat Iron Books, 2021. Bookshop Price $21.00 (new), $15.25 (used)
- [Buy] Artificial Intelligence: A Guide for Thinking Humans, by Melanie Mitchell
Farrar, Strauss, and Giroux, 2019. Bookshop Price $15.00 (new), $10.50 (used)
Software
|
  |
Syllabus
Course Description: Class Number: 2176
Survey of Artificial Intelligence (AI), the study of how to program computers to behave in ways normally attributed to intelligence when observed in humans. Topics include heuristic versus algorithmic programming; cognitive simulation versus machine intelligence; problem-solving; inference; natural language understanding; scene analysis; learning; decision-making. Topics are illustrated by programs from literature, programming projects in appropriate languages. Prerequisites: CMSC B151 or CMSC H106/107, and CMSC B231. Haverford: Natural Science (NA). Enrollment Limit: 24; Enrollment Criteria: Major/Minor/Concentration.
Topics (Ambitious/Tentative List)
What is AI
Turing Test
Symbolic versus Subsymbolic AI
Narrow versus AGI
ELIZA
Winograd Schemas
The Winters of AI
Perceptron
Planning/Problem Solving
SHRDLU
SHAKEY
STRIPS
Search Algorithms
Heuristics
Knowledge Representation & Reasoning
Logical Reasoning
Expert Systems
MYCIN
R1/XCON
DENDRAL
CYC
|
Knowledge Graphs
Commonsense Reasoning
Perceptrons
Neural Networks
Backpropagation
Deep Learning
Convolution Neural Networks
ImageNet
Bias in AI Systems
Robots
Reinforcement Learning
Deep Q-Learning
AlphaGo
Natural Language Understanding
Recurrent Neural Networks
Word2Vec
Watson
ChatGPT
Explanable AI
Neuro-Symbolic Systems
Are we there yet? |
Lab Attendance: Attendance in Lab is optional, but will be required during specific weeks. Look for announcements below during the semester. Prof. Kumar will be available in the Lab during all Lab times throughout the semester.
Important Dates
| September 3 |
First class meeting |
| October 1 |
Exam 1 |
| November 10 |
Exam 2 |
| December 8 |
Last class meeting |
| December 10 |
Exam 3 |
Creating a Welcoming Environment
All members of the Instruction Staff are dedicated to the cause of improving diversity, equity, and inclusion in the field of computing, and to supporting the wellness and mental health of our students.
Diversity and Inclusion
It is essential that all members of the course community – the instructor, TAs, and students – work together to create a supportive, inclusive environment that welcomes all students, regardless of their race, ethnicity, gender identity, sexuality, or socioeconomic status. All participants in this course deserve to and should expect to be treated with respect by other members of the community.
Class meetings, lab sessions, office hours, and group working time should be spaces where everyone feels welcome and included. In order to foster a welcoming environment, students of this course are expected to: exercise consideration and respect in their speech and actions; attempt collaboration and consideration, including listening to opposing perspectives and authentically and respectfully raising concerns, before conflict; refrain from demeaning, discriminatory, or harassing behavior and speech.
Wellness
Additionally, your mental health and wellness are of utmost importance to the course Instruction Staff, if not the College as a whole. All members of the instruction staff will be happy to chat or just to listen if you need someone to talk to, even if it’s not specifically about this course.
If you or someone you know is in distress and urgently needs to speak with someone, please do not hesitate to contact BMC Counseling Serices: 610-526-7360 (610-526-7778 nights and weekends). If you are uncomfortable reaching out to Counseling Services, any member of the Instruction Staff will be happy to contact them on your behalf.
We understand that student life can be extremely difficult, both mentally and emotionally. If you are living with mental health issues such as anxiety, depression, ADHD, or other conditions that may affect you this semester, you are encouraged to discuss these with the Instructor. Although the details are up to you to disclose, the Instruction Staff will do their best to support and accommodate you in order to ensure that you can succeed this course while staying healthy.
Accessibility
Bryn Mawr College is committed to providing equal access to students with a documented disability. Students needing academic accommodations for a disability must first speak with Access Services. Students can email accessservices@brynmawr.edu to request an appointment to begin this confidential process. If eligible for accommodations as per Access Services, students should schedule an appointment with the professor as early in the semester as possible to share their verification form and make appropriate arrangements. Please note that accommodations are not retroactive and require advance notice to implement. More information can be obtained at the Access Services website. (http://www.brynmawr.edu/access-services/)
Because some students with a disability may be eligible to record lectures - and it is state law in Pennsylvania that individuals are given advance notice that they may be recorded - professors also need to include the following statement in their syllabus:
Any student who has a disability-related need to record this class must first be found eligible to do so by Access Services and must share this eligibility with me, the instructor. Class members need to be aware that this class may be recorded.
Assignments
- Extra Credit Assignment (Due on Monday, November 3): Click here.
- Assignment#1 (Due in class on Wednesday, October 22): Click here for details.
- Assignment#2 (Due on Wednesday, October 29): Click here for details.
- Assignment#3 is posted (Due November 10): Click here for details.
- Assignment#4 is posted (Due December 3): Click here for details.
Lectures
- Week 1 (September 1, 3)
- September 1: Labor Day. No Class.
September 6: First class meeting. Introduction to AI. Origins of AI: The Dartmouth Summer School of 1956. What is AI? Alan Turing, Turing Test. Pattern Matching versus Understanding: ELIZA versus Winograd Schemas. (Some) Dichotomies of AI: Strong versus Weak AI, Symbolic versus Subsymbolic AI, AGI (Artificial General Intelligence) versus Narrow AI.
Read: Chapter 1 from Woodlridge, and pages 17-26 from Mitchell. Read one (or all?!) of the several original articles mentioned in today's lecture (see References in the slides).
Do: Find an online implementation of ELIZA and play with it. Discussion next week.
Slides: 01-Introduction.
- Week 2 (September 8, 10)
September 8: Watch the video: The Thinking Machine (1961) [~54 mins]. Symbolic versus Subsymbolic AI, AI Methodology in the 1960s: perception, problem solving, automated reasoning, language understanding, machine learing. The "seasons" of AI.
Read: Start reading Chapter 2 from Wooldridge.
Slides: 02-Introduction.
September 10:
Discussion on The Thinking Machine. Two early examples of AI systems: SHRDLU and SHAKEY. The STRIPS Planner. Procedural versus Declarative Representations.
Read: Chapter 2 from Wooldridge.
Slides: 03-SHRDLU-SHAKEY.
- Week 3 (September 15, 17)
September 15: Problem Solving as search: Example Problems. Search Formulation: State, Initial State, Goal State, Search Algorithm, State Space. Search Algorithms: Blind Search (Depth-First, Breadth-First), Informed Search (Uniform-Cost, Greedy Best-First, A*). Search trees. Search Complexity. Combinatorial Explosion/Complexity Barrier.
Read: Chapter 2 from Wooldridge.
Slides: 04-ProblemSolvingSearch.
September 17:
Game Playing. 2-person, perfect information, zero-sum games. The Minimax algorithm. Improving Minomax with Alpha-Beta Pruning.
Read: Chapter 2 from Wooldridge.
Slides: 05-GamePlaying.
Konane: Click here to play online.
Extra Credit Assignment (Due on Monday, November 3): Click here.
- Week 4 (September 22, 24)
September 22: First AI Winter. Rise of Expert Systems: MYCIN and R1/XCON; Rule-based Systems; structure of rules; forward and backward chaining.
Read: Chapter 3 from Wooldridge.
Slides: 06-Expert Systems.
September 24:
Representing Knowledge using Logic: declarative representations, propositions, logical entailment, what is a logic: truth preserving consequences, First-Order Logic: syntax, semantics. Building a knowledgebase in FOPC. Examples.
Read: Chapter 3 from Wooldridge.
Slides: 07-Logic.
- Week 5 (September 29, October 1)
September 29: Review Session. Bring your questions.
Slides: Exam1Review.
October 1:
Exam 1 is today.
- Week 6 (October 6, 8)
October 6: October 2: Logic in PROLOG. An introduction to PROLOG.
Download: SWI PROLOG from here.
PROLOG File from class: simpsons.pl
As a plaint text: simpsons.txt
Slides: 08-LogicInPROLOG.
Assignment#1 (Due in class on Wednesday, October 22): Click here for details.
October 8: Other Knowledge Representation Formalisms: Frames, Conceptual Dependency, Semantic Networks.
Read: Chapter 3 from Wooldridge.
Slides: 09-KnowledgeRepresentations.
- Week 7 (October 13, 15)
Fall Break, no classes.
- Week 8 (October 20, 22)
October 20: Robots and Rationality. Subsumption Architectures. Agent-based AI. IBM's Watson. Second AI Winter.
Read: Chapter 4 from Wooldridge.
Slides: 10-RobotsAndRationality.
October 22:
Subsymbolic AI. McCulloch-Pitts Neuron. The Perceptron. Example implementation.
Slides: 11-SubsymbolicAI.
Read: Chapters 1 & 2 from Mitchell.
Assignment#2 (Due on Wednesday, October 29): Click here for details.
Week 9 (October 27, 29)
October 27: Perceptron learning. Limitations of Perceptrons. Multi-Layer perceptrons. Towards Backpropagation Networks.
Slides: 12-Perceptrons.
Read: Chapters 1-2 from MItchell.
October 29:
Backpropagation Networks: The Classic Version. Gradient Descent, Stochastic Gradient Descent (SGD), True-, Full, Mini Batch- SGD. Backpropagation (Modern Version): Activations Functions, Loss Functions, Optimizers. Introducing Keras. Keras Workflow for Machine Learning. Example: Recognizing Handwritten Digits (MNIST Digits).
Slides: 12-Backpropagation.
Read: Chapters 3, 4 and 5 from Mitchell.
- Week 10 (November 3, 5)
November 3: Backpropagation training in Neural Networks. Hyperparameter choices. Introducing Keras. Validation and Testing of trained models.
Slides: 14-NN Training.
Read: Chapters 3, 4, and 5 from Mitchell.
Assignment#3 is posted (Due November 10): Click here for details.
November 5:
Review for Exam 2.
Slides: 14A Review for Exam 2.
- Week 11 (Novmber 10, 12)
November 10: Exam 2 is today.
Konane Tournament (Winners are in bold)
Round 1:
Timothy vs Emily
Jean vs Emma
Round 2:
Timothy vs Jean
Emily vs Emma
Round 3:
Timothy vs Emma
Emily vs Jean
Points:
| Player |
Played |
Won |
Lost |
Pts |
| Emma |
3 |
3 |
0 |
9 |
| Emily |
2 |
1 |
1 |
3 |
| Timothy |
3 |
1 |
2 |
3 |
| Jean |
2 |
0 |
2 |
0 |
Finals:
Emma vs Emily
Congratulations to Emma!
November 12:
AI Milestones in the last twenty years, Examples: Furby, Pleo Robots, Google Translate, Microsoft voice translation, PASCAL Competetions, ImageNet, ImageNet Competitions, Mechanical Turk, Convolutional Neural Networks (ConvNets). Image/Object recognition versus Image understanding.
Slides: 15-Object Recognition.
Read: Chapters 4 & 5 from Mitchell. Start reading Chapters 6 & 7 as well.
- Week 12 (November 17, 19)
November 17: Convolution Networks.
Hands-on with convolution networks.
Convnets Colab: MINST Digit Recognition.
Read: Chapters 8, 9, 10 from Mitchell.
Slides: 16-Convolution Networks.
Assignment#4 is posted (Due December 3): Click here for details.
November 19:
ConvNet/Deep Learning versus human learning. Perils of Big Data. Biased AI. Trustworthy AI. Beneficial AI. Ethical AI. Regulating AI. Reinforcement Learning, Q Learning. Game playing, revisited. Monte Carlo Tree Search. MCTS+Deep Q Networks. AlphaGo.
Slides: 17-Ethical AI, 18-Deep Q Networks.
Read: Start reading Chapter 11 from Mitchell.
- Week 13 (November 24, 26)
November 24: Neural Nets for Natural Language Processing. Classic NLP pipeline. Vectorizing text. NETtalk demo. One-hot encoding. Sequence models: RNNs. Word embeddings: Word2Vec, GLoVe. Encoders (learning embeddings on the fly). Applications: IMDB Movie Reviews, machine translation.
Read: Chapters 11 & 12 from Mitchell. Chapter 5 from Wooldridge.
Slides: 19-NNsForNLP.
November 26:
No class today.
November 27: Happy Thanksgiving!
- Week 14 (December 1, 3)
December 1:
Read:
December 3:
- Week 15 (December 8, 10)
December 8: Course Wrap up.
December 10: Exam 3 is today.
Extra Readings of interest:
Course Policies
Submission and Late Policy
No assignment will be accepted after it is past due.
No past work can be "made up" after it is due.
No regrade requests will be entertained one week after the graded work is returned in class.
Any extensions will be given only in the case of verifiable medical excuses or other such dire circumstances, if requested in advance and supported by your Academic Dean.
Communication
As you will discover, we are proponents of two-way communication and we welcome feedback during the semester about the course. We are available to answer student questions, listen to concerns, and talk about any course-related topic (or otherwise!). Come to office hours and labs! This helps us get to know you. You are welcome to stop by and chat. There are many more exciting topics to talk about that we won't have time to cover in-class.
Please stay in touch with, particularly if you feel stuck on a topic or project and can't figure out how to proceed. Often a quick e-mail, phone call or face-to-face conference can reveal solutions to problems and generate renewed creative and scholarly energy. It is essential that you begin assignments early, since we will be covering a variety of challenging topics in this course.
Grading
All graded work will receive a grade, 4.0, 3.7, 3.3, 3.0, 2.7, 2.3, 2.0, 1.7,
1.3, 1.0, or 0.0. At the end of the semester, final grades will be calculated as a weighted average of all grades according to the following weights:
| Exams |
65% |
| Exam 1 |
20% |
| Exam 2 |
20% |
| Exam 3 |
25% |
| Participation & Assignments |
35% |
Incomplete grades will be given only for verifiable medical illness or other such dire circumstances.
Study Groups
All submitted work should be solely your individual work. We encourage you to discuss the material and work together to understand it. Here are our thoughts on collaborating with other students:
- The readings and lecture topics are group work. Please discuss the readings and associated topics with each other. Work together to understand the material. We highly recommend forming a reading group to discuss the material -- we will explore many ideas and it helps to have multiple people working together to understand them.
- It is fine to discuss the topics covered in the homeworks, to discuss approaches to problems, and to sketch out general solutions. However, you MUST write up the homework answers, solutions, and programs individually without sharing specific solutions, mathematical results, program code, etc. If you made any notes or worked out something on a white board with another person while you were discussing the homework, you shouldn't use those notes while writing up your answer.
- Under ABSOLUTELY NO circumstances should you share computer code with another student. You are not permitted to use or consult code found on the internet for any of your assignments.
If you have any questions as to what types of collaborations are allowed, please feel free to ask.
Created on August 13, 2025.