ENCE 452: Artificial Intelligence

Instructor:

Liang Zhang, Assistant Professor

Prerequisites

ENGE 320 or Equivalent, or permission of instructor.

Objectives

This course provides basic theory and important applications. Topics include probability concepts and axioms; stationarity and ergodicity; random variables and their functions; vectors; expectation and variance; conditional expectation; moment-generating and characteristic functions; random processes such as white noise and Gaussian; autocorrelation and power spectral density; linear filtering of random processes, and basic ideas of estimation and detection.

Location

EASC 2041

Time

Mon/Wed/Fri 12:00-12:50 pm

ENCE 452 Syllabus

ENCE 452 Lecture Notes

Lectures Download Links
Lecture 0 Lecture 0 (pdf)
Lecture 1 Lecture 1 (pdf)
Lecture 2 Lecture 2 (pdf)
Lecture 3 Lecture 3 (pdf)
Lecture 4 Lecture 4 (pdf)
Lecture 5 Lecture 5 (pdf)
Lecture 6 Lecture 6 (pdf)
Lecture 7 Lecture 7 (pdf)
Lecture 8 Lecture 8 (pdf) Video part 1 (mp4) Video part 2 (mp4)
Lecture 9 Lecture 9 (pdf)
Annex (Generating RVs) Annex (pdf)
Lecture 10 Lecture 10 (pdf)
Lecture 11 Lecture 11 (pdf)
Lecture 12 Lecture 12 (pdf)
Lecture 13 Lecture 13 (pdf)
Lecture 14 Lecture 14 (pdf)
Lecture 15 Lecture 15 (pdf)
Lecture 16 Lecture 16 (pdf)
Formula Sheetpmf and pdf for exam

ENCE 452 Projects

For the software installation, please visit https://eulz.net/blog/post-2023-09.html.

  1. Project 1

    Project     Solutions

  2. Project 2

    Project     Solutions

  3. Project 3

    Project     Solutions

ENCE 452 Homework

Course Schedule

Week Lecture Topic Chapter
1 — 08/24 Lecture 0, Lecture 1 Introduction to AI: Past, Present, Future Agents and environments 1, 28
2 — 08/31 Lecture 3 Uninformed Search and Search Strategies 3.1-3.4
3 — 09/07 Lecture 3 A* Search, Heuristics and Heuristic Functions Local Search 3.5-3.6,4.1
4 — 09/14 Lecture 5 Adversarial Search 5
5 — 09/21 Lecture 7 Knowledge-Based Agents Propositional Logic and Inference 7.1-7.5
6 — 09/28 Lecture 12 Quantifying Uncertainty 12.1-12.5
7 — 10/05 Lecture 13 Bayes Nets: Syntax and Semantics 13.1-13.3
8 — 10/12 Midterm
9 — 10/19 Lecture 13 Bayes nets: Exact Inference and Approximate Inference
Markov Decision Processes I
13.3-13.4, 17.1
10 — 10/26 Lecture 19 Decision Tree Learning
Neural Network Learning
19.1-19.3, 19.7
11 — 11/02 Lecture 21 Deep Neural Networks 21
12 — 11/09 Lecture 21A Convolutional Neural Networks (CNNs)
Applications in Computer Vision
21
13 — 11/16 Lecture 21B Recurrent Neural Networks (RNNs)
Sequence Modeling and Applications
21
14 — 11/23 Lecture 22 Reinforcement Learning I 22.1-22.4
15 — 11/30 Lecture 22A Reinforcement Learning II
Review and Discussion
22.4-22.5
16 — 12/07 Final Exam

Last day of class is 12/04/2026 .