CSCE 420: Introduction to Artificial Intelligence
Instructor: Dr. Dylan Shell.
| Office | : | PETR 315 |
| Phone | : | (979) 845-2369 |
| : | dshell@tamu.edu | |
| Web | : | http://robots.cs.tamu.edu/dshell/cs420 |
| Office hours | : | Walk-ins: Tuesdays, 10:30am–11:30am |
| Otherwise by appointment via e-mail too. |
Assistant to the Instructor: Information
| Name | : | Reza Oftadeh |
| : | reza.oftadeh@tamu.edu | |
| Office hours | : | Wednesdays noon–1:00pm |
| Fridays 11:00pm–noon | ||
| Otherwise by appointment. | ||
| Office hours location | : | Zoom https://tamu.zoom.us/j/96308037223 |
Spring 2024
| Lecture Time | : | Mon/Wed/Friday, 8:00am–8:50am. |
| Lecture Location | : | ZACH 310 |
Course Description
Fundamental concepts and techniques of intelligent systems; representation and interpretation of knowledge on a computer; search strategies and control; active research areas and applications such as notional systems, natural language understanding, vision systems, planning algorithms, intelligent agents and expert systems.
The course is a broad survey that will require a significant amount of reading with basic programming in different languages. It will provide an understanding of the state of the practice of AI and set the foundation for further study in agency, logic, neural networks, robotics, uncertainty, and computer vision.
Prerequisites
A course dealing with Design and Analysis of Algorithms, including Complexity Theory (NP-Hardness, SAT, etc.), e.g., the class CSCE 411, or equivalent.
Learning Outcomes or Course Objectives
- List the basic techniques for creating intelligent programs. This will be measured by midterm exams.
- Detail and discuss the challenges imposed by different notions of uncertainty (e.g., nondeterminism, partial-observably, adversarial agents, incomplete models), including their implications for the methods used in the creation of intelligent programs. This will be measured by midterm exams.
- Create program illustrating the successful operation of these methods. This will be measured by the programming assignments.
- Apply the right programming language or technique to the right problem and be able to evaluate a proposed AI application for likelihood of success. This will be measured by programming assignments.
- Be able to discern sensationalism from science on the possible impact of AI on society. This will be assessed by exams and the communication project.
Textbook
Artificial Intelligence: A Modern Approach by Stuart Russell and Peter
Norvig, 4th Edition, 2020/2021.
Grading Policies
Grades will be based on:
|
The grading scale is:
|
For further "compile time" details, please refer to the syllabus.
This current page (i.e., the one you are reading now) will serve as the most up-to-date source of official information.
Resources
- The course syllabus.
- [CMI] "Computing Machinery and Intelligence," by Alan M. Turing. Mind 49:433–460, 1950.
A selection of communication projects
- The Legendary Game Series Between Stockfish and AlphaZero
- How Netflix's recommendation system works
- Making Human-like AI in Counter Strike: Global Offensive
- Rain World AI
- Is A.I. Music Art?
- Source Separation - Exploring Apple Music Sing and Spotify Karoke
Communication Projects: This semester's Hall of Fame
- Pastry AI: From Backing to Biopsy by Anjali Hole, Caroline Jia, and Rhea Phatak
- Automated Theorem Provers by Preston Bied
- Creativity by Alex Pantazopol
- Using Recurrent Neural Networks to Catch Counter-Strike 2 Cheaters by Ryan Kutz
- Team Fortress 2's TFBot by William Tichenor
- Organ Donation With AI by Weston Cadena, Arjun Kurkal, and Christiana Vancura
Course Topics, Calendar of Activities, Major Assignment Dates
Syllabus topics and readings are subject to change, exact dates depend on class progress.
| Week | Topic | R&N Coverage (Global Edn.) | |
| 1 | Course overview; Introduction | Chapt. 1 | |
Readings (to do before class):
| |||
| 2 | Agents, Search, Reminder: DFS/BFS | 2, 3.1–3.3 | |
Readings (to do before class):
| |||
| 3 | Informed Search. Heuristics; Generalizations; Guest Lecture: [Likely: D*Lite] | 3.5–3.6 | |
Readings (to do before class):
| |||
| 4 | Local Search, Optimization | 4.1–4.4 | |
Readings (to do before class):
| |||
| 5 | Search for games | 6.1–6.5 | |
Readings (to do before class):
| |||
| 6 | Constraint Satisfaction Problems | 5 | |
Readings (to do before class):
| |||
| 7 | On knowledge representation Introduction to Logic | 7 | |
Readings (to do before class):
| |||
Material for class discussion: (Agenda: M)
| |||
| 8 | First-order Logic: Syntax and Semantics | 8 | |
Readings (to do before class):
| |||
| 10 | First-order Logic: Inference | 9 | |
Readings (to do before class):
| |||
| 11 | Classical Planning | 11.1–11.4 | |
Readings (to do before class):
| |||
| 12 | Learning Basics | 19.1–19.6, 22.1–22.4 | |
Readings (to do before class):
| |||
| 13 | Reinforcement Learning | 23 | |
| |||
| 14 | Philosophical Foundations | 28 | |
| |||
![[2]](https://www.nsf.gov/news/mmg/media/images/122_3_h.jpg){kind=link}
| Due Date | Class Tests and Assignments | Weight | |
| 9 Feb. | Programming Assignment 1: Search | 10% | |
| 23 Feb. | Programming Assignment 2: Game Search | 10% | |
| 6 Mar. | Midterm Exam (Sample questions + solutions) | 20% | |
| Programming Assignment 3: Basic Prolog | 5% | ||
| 10 Apr. | Communication Project | 15% | |
| 19 Apr. | Programming Assignment 4: Wumpus! | 10% | |
| 26 Apr. | Programming Assignment 5: PDDL | 5% | |
| 2 May. | Final Exam (Sample questions + solutions) | 25% | |
Late work submission policy: For programming assignments and the communication project, we have a late policy with a discount of 10% per day (computed with minute-level resolution, see the syllabus for the precise formula). The midterm and final exams, being examinations, are not permitted to be late.