EE 473

Introduction to Artificial Intelligence

Professor:
Office:
Phone:
Office hours:
Login:
Web page:
Fun:
 Bob Givan
EE 313C
7248-235-567 (backwards) (text message only, any time)
follow this link
givan@purdue.edu
http://engineering.purdue.edu/~givan/
Spotify playlists
Teaching Assistant:
Email:
 Ziyu Gong
gong123@purdue.edu
Teaching Assistant:
Email:
 Jeeyung Kim
jkim17@purdue.edu

Please follow this link for our office hour schedule: GTA/UTA office hours

---------- Students registered for ECE 473 may access the following pages using their Purdue login----------

Latex Resources

Sample LaTeX document template. To compile it into a pdf, you can use an online compiler like overleaf, or install a LaTeX compiler on your machine.

Handwritten symbol recognition: detexify

Cheat sheet for Latex symbol abbreviations: cheat sheet

Timeline

The welcome video, syllabus, FAQ, and first lecture video are available below. This course will be held in a flipped-classroom style, with:

Please join the class Piazza blog and monitor all postings and announcements there.

Note: Homework due in Week n on Friday is typically associated with lectures to be watched in week n-1 and a quiz in week n+1

Week 1 — January 10 - 14

There are no meetings (no quiz and no Q&A) the first week. See the welcome video and syllabus below for more detail.

Please join the class Piazza blog and monitor all postings and announcements there.

The first homework is due Friday 1/14 at noon and you must watch the welcome video and the first lecture video (about one hour) before working on that homework. Since this is a fast start, we will waive the usual late penalty for this homework, accepting submissions without penalty until Saturday noon (NONE accepted later than that). The fast start will enable us to moderate the pace (just a little) at more critical times of the semester.

* Course Syllabus
* FAQ

* Welcome video

* View online lecture 1 before starting hw1 (see lecture schedule section below)
* Tuesday January 11 — No course meeting.
* Thursday January 13 — No course meeting
* Homework 1 Python warmup and AI teaser   (Due on Brightspace: Friday January 14 noon, but for this one time no late penalty, accepted no later than Saturday noon)

Week 2 — January 17 - January 21

* View the online lectures for hw2 before the week starts (see lecture schedule section below)
* Tuesday January 18, 1:30pm — Q&A recording
* Thursday January 20, 1:30pm — Brightspace quiz on AI History and Python warmup. You must start this quiz between 1:30pm and 2pm
* Homework 2 - Dynamic programming and math preliminaries   (Due on Brightspace: Friday January 21, noon, late homework accepted WITH penalty until Saturday noon)

Week 3 — January 24 - January 28

* View the online lectures for hw3 before the week starts (see lecture schedule section below)
* Tuesday January 25, 1:30pm — Q&A recording
* Thursday January 27, 1:30pm — Brightspace quiz on dynamic programming and math preliminaries. You must start this quiz between 1:30pm and 2pm
* Homework 3 - Machine learning introduction (updated Jan 22 10:02am)   (Due on Brightspace: Friday January 28, noon, late homework accepted WITH penalty until Saturday noon)

Week 4 — January 31 - February 4

* View the online lectures for hw4 before the week starts (see lecture schedule section below)
* Tuesday February 1, 1:30pm — Q&A recording
* Thursday February 3, 1:30pm — Brightspace quiz on machine learning introduction. You must start this quiz between 1:30pm and 2pm
* Homework 4 - Classification and overfitting (updated Jan 31 10:21am)   (Due on Brightspace: Friday February 4, noon, late homework accepted WITH penalty until Saturday noon)

Week 5 — February 7 - February 11

* View the online lectures for hw5 before the week starts (see lecture schedule section below)
* Tuesday February 8, 1:30pm — Q&A recording
* Thursday February 10, 1:30pm — Brightspace quiz on classification and overfitting. You must start this quiz between 1:30pm and 2pm
* Homework 5 - K means   (Due on Brightspace: Friday February 11, noon, late homework accepted WITH penalty until Saturday noon) * Project (Extended homework) 7 released - Local search   (Due on Brightspace: Friday February 25, noon, late homework accepted WITH penalty until Saturday noon)

Week 6 — February 14 - February 18

* View the online lectures for hw6 before the week starts (see lecture schedule section below)
* Tuesday February 15, 1:30pm — Q&A recording
* Thursday February 17, 1:30pm — Brightspace quiz on K means and Nearest neighbor. You must start this quiz between 1:30pm and 2pm
* Homework 6 - Uniform cost search (minor update 2/14/22 10:50am)   (Due on Brightspace: Friday February 18, noon, late homework accepted WITH penalty until Saturday noon)

Week 7 — February 21 - February 25

* View the online lectures for hw7/week7 before the week starts (see lecture schedule section below)
* Tuesday February 15, 1:30pm — Q&A recording
* Thursday February 24, 1:30pm — Brightspace quiz on breadth and depth-focused search methods. You must start this quiz between 1:30pm and 2pm
* Project (Extended homework) 7 released - Local search   (Due on Brightspace: Friday February 25, noon, late homework accepted WITH penalty until Saturday noon)

Week 8 — February 28 - March 4

* View the online lectures for hw8/week8 before the week starts (see lecture schedule section below)
* Tuesday March 1, 1:30pm — In-person Q&A session (Max W & Maileen Brown Hall 170). Live stream and recording on Kaltura Media ??
* Thursday March 3, 1:30pm — Brightspace quiz on informed search and adversarial search. You must start this quiz between 1:30pm and 2pm
* Homework 8 - Informed and adversarial Search   (Due on Brightspace: Friday March 4, noon, late homework accepted WITH penalty until Saturday noon)

Week 9 — March 7 - March 11

* View the online lectures for hw9/week9 before the week starts (see lecture schedule section below)
* Tuesday March 8, 1:30pm — In-person Q&A session (Max W & Maileen Brown Hall 170). Live stream and recording on Kaltura Media Gallery on BrightSpace
* Thursday March 10, 1:30pm — Brightspace quiz on Homework 8 and CSP / Bayes net lectures. You must start this quiz between 1:30pm and 2pm
* Homework 9 - Introduction to Markov Decision Processes   (Due on Brightspace: Friday March 11, noon, late homework accepted WITH penalty until Saturday noon) * Project (Extended homework) 11 released - Sokoban   (Due on Brightspace: Friday April 1, noon, late homework accepted WITHOUT penalty until Saturday noon)

Week 10 — March 21 - March 25

* View the online lectures for hw10/week10 before the week starts (see lecture schedule section below)
* Tuesday March 22, 1:30pm — Q&A recording
* Thursday March 24, 1:30pm — Brightspace quiz on Homework 9 and Markov decision processes. You must start this quiz between 1:30pm and 2pm
* Homework 10 - Q learning   (Due on Brightspace: Friday March 25, noon, late homework accepted WITH penalty until Saturday noon)
* Project (Extended homework) 11 released above under week 9 - Sokoban   (Due on Brightspace: Friday April 1, noon, late homework accepted WITHOUT penalty until Saturday noon)

Week 11 — March 28 - April 1

* View the online lectures for hw11/week11 before the week starts (see lecture schedule section below)
* Tuesday March 29, 1:30pm — Q&A recording
* Thursday March 31, 1:30pm — Brightspace quiz on Homework 10 and Q learning. You must start this quiz between 1:30pm and 2pm
* Extended Homework 11 - Sokoban   (Due on Brightspace: Friday April 1, noon, late homework accepted WITHOUT penalty until Saturday noon)

Week 12 — April 4 - April 8

* View the online lectures for hw12/week12 before the week starts (see lecture schedule section below)
* Tuesday April 5, 1:30pm — Q&A recording
* Thursday April 7, 1:30pm — Brightspace quiz on Homework 11 and policy gradient / TD learning. You must start this quiz between 1:30pm and 2pm
* Homework 12 Neural networks and Sokoban minimum standard   (Due on Brightspace: Friday April 8, noon, late homework accepted WITHOUT penalty until Saturday noon)

Week 13 — April 11 - April 15

* View the online lectures for hw13/week13 before the week starts (see lecture schedule section below)
* Tuesday April 12, 1:30pm — Q&A recording
* Thursday April 14, 1:30pm — Brightspace quiz on Homework 12 and neural networks introduction. You must start this quiz between 1:30pm and 2pm
* Homework 13 Bayesian network inference (updated Monday 5pm, slightly simplifying problem 4) (all written problems)   (Due on GradeScope: Friday April 15, noon, late homework accepted WITH penalty until Saturday noon)

Week 14 — April 18 - April 22

This is our last week of lectures and homeworks. The quiz for hw14 will be during the first half our of our final exam window, but will still be a self-proctored BrightSpace quiz like all the others.

* View the online lectures for hw14/week14 before the week starts (see lecture schedule section below)
* Tuesday March 29, 1:30pm — Q&A recording
* Thursday April 21, 1:30pm — Brightspace quiz on Homework 13 and Bayesian network inference. You must start this quiz between 1:30pm and 2pm
* Homework 14 Structured neural networks (updated 12:10pm Monday 4/18 to add explanation) (all written problems)   (Due on GradeScope: Friday April 22, noon, late homework accepted WITH penalty until Saturday noon)

Weeks 15-16 — April 25 - May 6

We have only the Q&A this week, with quiz 14 during finals week in our final exam slot. Here you reap the time rewards of our fairly intense pace to date

* Tuesday April 26, 1:30pm — Q&A recording

* Wednesday May 4, 1:00pm — Brightspace quiz on Homework 14 and structured neural networks. You must start this quiz between 1pm and 1:30pm

Online lecture and viewing schedule

* For hw1 and quiz1:
* Online Lecture 1: AI History   (1 hour, viewing recommended by Wednesday January 12)

* For hw2 and quiz2:
* Lecture 2: Dynamic programming — Part 1: Optimal substructure (24 minutes)   (Viewing recommended by Saturday, January 15)
* Lecture 3: Dynamic programming — Part 2: Repeated subproblems (33 minutes)   (Viewing recommended by Monday, January 17)
* Lecture 4: Dynamic programming — Part 3: Solution extraction (19 minutes)   (Viewing recommended by Monday, January 17)

* For hw3 and quiz3:
* Lecture 5: Machine learning — Part 1: Introduction (40 minutes)   (Viewing recommended by Saturday, January 22)
* Lecture 6: Machine learning — Part 2: A basic loss function (26 minutes)   (Viewing recommended by Monday, January 24)
* Lecture 7: Machine learning — Part 3: Linear regression (32 minutes)   (Viewing recommended by Monday, January 24)

* For hw4 and quiz4:
* Lecture 8: Machine learning — Part 4: Classification introduction (24 minutes)   (Viewing recommended by Saturday, January 29)
* Lecture 9: Machine learning — Part 5: Decision boundaries (13 minutes)   (Viewing recommended by Saturday, January 29)
* Lecture 10: Machine learning — Part 6: Logistic regression (39 minutes)   (Viewing recommended by Saturday, January 29)
* Lecture 11: Machine learning — Part 7: Softmax (11 minutes)   (Viewing recommended by Monday, January 31)
* Lecture 12: Machine learning — Part 8: Generalization (28 minutes)   (Viewing recommended by Monday, January 31)

* For hw5 and quiz5:
* Lecture 13: Machine learning — Part 9: Nearest neighbor learning (8 minutes)   (Viewing recommended by Saturday, February 5)
* Lecture 14: Machine learning — Part 10: Unsupervised learning and K means (27 minutes)   (Viewing recommended by Saturday, February 5)

* For project7 and both quiz5 and quiz7:
* Lecture 15: Local search (47 minutes)   (Viewing recommended by Tuesday, February 8)

* For hw6 and quiz6:
* Lecture 16: State space search — Part 1: Breadth-focused methods (40 minutes)   (Viewing recommended by Saturday, February 12)
* Lecture 17: State space search — Part 2: Depth-focused methods (25 minutes)   (Viewing recommended by Monday, February 14)

* For hw7 and quiz7:
* Lecture 18: State space search — Part 3: Informed methods (36 minutes)   (Viewing recommended by Saturday, February 19)
* Lecture 19: State space search — Part 4: Adversarial methods (54 minutes)   (Viewing recommended by Monday, February 21)
*

* For hw8 and quiz8:
* Lecture 20: State space search — Constraint satisfaction (65 minutes)    (Viewing recommended by Saturday, February 26)
* Lecture 21: Bayesian networks — Introduction (49 minutes)    (Viewing recommended by Monday, February 28)

* For hw9 and quiz9:
* Lecture 22: Markov decision processes — Introduction (22 minutes)    (Viewing recommended by Saturday, March 5)
* Lecture 23: Markov decision processes — Policy evaluation (69 minutes)    (Viewing recommended by Saturday, March 5)
* Lecture 24: Markov decision processes — Optimal value and optimal policies (60 minutes)    (Viewing recommended by Monday, March 7)

* For hw10 and quiz10:
* Lecture 25: Markov decision processes — Q learning (68 minutes)    (Viewing recommended by Monday, March 21)

* For week 11 and quiz11:
* Lecture 26: Markov decision processes — Policy gradient methods (17 minutes)    (Viewing recommended by Saturday, March 26)
* Lecture 27: Markov decision processes — TD Learning and alpha Zero (54 minutes)    (Viewing recommended by Tuesday, March 29)

* For hw12 and quiz12:
* Lecture 28: Neural networks — Introduction (27 minutes)    (Viewing recommended by Monday, April 4)

* For hw13 and quiz13:
* Lecture 29: Bayesian networks — D-separation (41 minutes)    (Viewing recommended by Saturday, April 9)
* Lecture 30: Bayesian networks — polytree inference (46 minutes)    (Viewing recommended by Monday, April 11)

* For hw14 and quiz14 (BrightSpace quiz 14 given in first 30 minutes of final exam time slot):
* Lecture 31: Neural networks — Convolution (57 minutes)    (Viewing recommended by Saturday, April 16)
* Lecture 32: Neural networks — Recurrent networks (31 minutes)    (Viewing recommended by Monday, April 18)

This concludes the lectures for Spring 2022. All lectures have been released.

Maintained by Bob Givan and course staff

givan@purdue.edu