Course Information

Schedule

Class:	Mon., Wed., Fri. 10:30 - 11:20 PM, SCI 105
Lab:	Fri. 2:15 - 3:45 PM, SCI 256

Contact Information

Professor:	Lisa Meeden
Email:	meeden at cs dot swarthmore.edu
Office:	Science Center 243
Office Hours:	Tue., Wed. 1:30-3:30

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. As a result, AI has become a very broad field that includes search, game playing, reasoning, planning, natural language processing, 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, simulated annealing, and genetic algorithms applied to AI problems. In machine learning, which is concerned with how to create programs that automatically learn from experience, we will explore reinforcement learning and neural networks. 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.
• Respond to common objections to the possibility of achieving AI.
• Respond to common fears about the dangers of AI.

---

Grading

Grade weighting

5%	Class Participation
10%	Reading Journal
35%	Labs
20%	Exam 1, in lab 10/11/19
20%	Exam 2, in lab 11/22/19
10%	Final Project

---

Reading

Rather than using a single textbook, we will be using materials from a variety of sources including:

• Artificial Intelligence: A Guide for Thinking Humans, by Melanie Mitchell (to be published Nov. 2019)
  You will be reading a draft version of this book. Please do not distribute it to anyone else.
• An Introduction to Genetic Algorithms, by Melanie Mitchell (1996)
• Artificial Intelligence: A Modern Approach (3rd Edition), by Stuart Russell and Peter Norvig (2010), denoted as R&N
• Understanding Intelligence, by Rolf Pfeifer and Christian Scheier (1999), denoted as P&S

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 a reading journal.

Preparation

You should check the class schedule and read any material that has been assigned before coming to class. 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)

Make your best effort to understand the material and bring any questions that you have to class. Then we can have a productive discussion with examples and exercises to clarify the material.

Journal

To help focus your efforts and to give us a basis for discussion, you will be provided with a short list of questions to answer 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.

Your responses are due by 11:59pm the night before class where they will be discussed. No late responses will be accepted.

You will clone a reading journal repo containing several weekly text files. You will write your responses in the appropriate file and submit them via git (using add, commit, and push) before each class meeting when reading is assigned.

While these low-stakes writing assignments are technically informal, they must reflect a certain level of engagement and evidence of thinking seriously about the material. Responses will be graded using the following scale:

• PLUS: Exhibits exceptional clarity, insight, and/or creativity
• CHECK: Exhibits evidence of processing and studying concepts
• MINUS: Superficial response or insufficient evidence of engagement
• ZERO: Did not complete

My comments on your journals will be pushed to your grading repo. I expect that most entries will receive a CHECK, thus I will primarily comment on your journal to report a PLUS or a MINUS. You should expect to discuss the issues raised in your reading journal entries during class.

Copyright 2019 Jerod Weinman

---

Policies

Labs

Labs will be assigned on Friday, during the scheduled lab time, and will be due by the following Thursday before midnight.

You should work with a partner on all labs after lab 0. We will be using Teammaker to facilitate the creation of partnerships. If you would like to be assigned a random partner, you can select this option through Teammaker as well. For each lab assignment you must re-select partners. Thus you can try out a partnership one week, and then decide to try a different partnership the following week.

You have two 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 when you submit your lab.

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 (e.g., extended illness, concussion, hospitalization) or other emergency, you must contact the dean's office and your instructors. Faculty will coordinate with the deans to determine and provide the appropriate accommodations. You should review the College's medical excuse policy.

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. In these cases, you should always include comments that indicate on which parts of the assignment you received help, and what your sources were.

Academic Accommodations

If you believe that you need accommodations for a disability, please contact the Office of Student Disability Services (Parrish 113W) or email studentdisabilityservices@swarthmore.edu to arrange an appointment to discuss your needs. As appropriate, the Office will issue students with documented disabilities a formal Accommodations Letter. Since accommodations require early planning and are not retroactive, please contact the Office of Student Disability Services as soon as possible. For details about the accommodations process, visit the Student Disability Service Website. You are also welcome to contact me privately to discuss your academic needs. However, all disability-related accommodations must be arranged through the Office of Student Disability Services.

---

Schedule

WEEK	DAY	ANNOUNCEMENTS	TOPIC & READING	LABS
1	Sep 02	Introduction	Introduction to AI M: What is AI? R&N 1.1 W: Roots of Artificial Intelligence Mitchell Ch. 1 F: AI Environments R&N 2.3 Journal questions	Python tutorial Lab 0: State Space Search on Logic Puzzles
	Sep 04	History of AI
	Sep 06	Agents and Environments
2	Sep 09	State Space Search	Problem solving with search M: Problem solving R&N 3.1-3.3 W: Uninformed search R&N 3.4 F: Informed search R&N 3.5-3.7 Journal questions	Lab 1: A* Search on Traffic Jam game
	Sep 11	Uninformed Search
	Sep 13	Informed Search
3	Sep 16	Local Search and Hill Climbing	Local search M: Hill climbing, Simulated annealing, Beam search R&N 4.1 Journal questions	Lab 2: Local search on Traveling Salesperson Problems
	Sep 18	Simuated Annealing and Stochastic Beam Search
	Sep 20
4	Sep 23		Game tree search M: Minimax algorithm R&N 5.1-5.2 W: Alpha-beta pruning R&N 5.3-5.4 Journal questions	Lab 3: Minimax search on Mancala and Breakthrough games
	Sep 25	Game Search
	Sep 27	Minimax and pruning Trace result Blank trace
5	Sep 30	Go and MCTS	Monte Carlo Search M: The Grand Challenge of Go Mitchell Ch. 9 W: MCTS Journal questions	Lab 4: MCTS on Hex game
	Oct 02	MCTS details
	Oct 04	MCTS pseudocode
6	Oct 07	Fundamental problems with classical AI	Evaluating Classical AI M: The Fundamental Problems of Classical AI and Cognitive Science P&S Ch. 3 W, F: Review Search Journal questions	EXAM 1, Friday in lab
	Oct 09	Exam 1 review
	Oct 11
	Oct 14	Fall Break
	Oct 16
	Oct 18
7	Oct 21	Percpetrons	Perceptrons and Neural Networks M: Review pgs 22-32 on Perceptrons Mitchell Ch. 1 W: Neural Networks and the Rise of Machine Learning Mitchell Ch. 2 F: Videos on neural networks and backpropagation Journal questions	Lab 5: Implementing Neural Networks
	Oct 23	Multilayer Networks
	Oct 25	Deriving Backpropagation
8	Oct 28	Motivating Convolutional Networks	Deep Learning M: Who, What, When, Where, Why Mitchell Ch. 4 W: ConvNets and ImageNet Mitchell Ch. 5 F: Convolutional Neural Networks for Visual Recognition Journal questions	Lab 6: Convolutional Neural Networks
	Oct 30	Deep Learning
	Nov 01	Research that uses ANNs
9	Nov 04	Reinforcement learning	Reinforcement Learning Rewards for Robots Mitchell Ch. 7 Beyond Games Mitchell Ch. 10 Journal questions	Lab 7: Deep Q-Learning
	Nov 06	Q-learning, Approx. Q-learning
	Nov 08	Deep Q-learning
10	Nov 11	Evolutionary Computation, GAs	Genetic Algorithms M: Genetic algorithms Mitchell GA Ch. 1 W: Evolving Neural Networks Mitchell GA Sec. 2.3 Journal questions	Lab 8: Genetic Algorithms
	Nov 13	Schema theorem
	Nov 15	Evolving neural networks
11	Nov 18	Evaluating ML	Evaluating Machine Learning M: How Machines Learn Mitchell Ch. 6 W, F: Review Machine Learning Journal questions	EXAM 2, Friday in lab
	Nov 20	Exam 2 review Review notes
	Nov 22
12	Nov 25		Final Project	No lab
	Nov 27	No class
	Nov 29	Thanksgiving
13	Dec 02	Melanie Mitchell visiting	Philosophy of AI M: Semantic Image Retrieval W: AI Spring Mitchell Ch. 3 Journal questions	Project Checkpoint
	Dec 04	Can machines think?
	Dec 06	More philsophy of AI Future of AI
14	Dec 09	Summing up	Future of AI M: Questions, Answers, and Speculations Mitchell Ch. 16 Journal questions	Finish Project