Prof. Hao Zheng
Office hours: Mons 1:30–2:30pm, or by appointment
James R. Oliver Hall, Rm 357
Tasnim Tabassum
Office hours: Tue 1–2pm, Fris 2:00–3:00pm, or by appointment
James R. Oliver Hall, Rm 244
Schedule
Textbook:
- [RN] "Artificial Intelligence: A Modern Approach" by Stuart Russell and Peter Norvig
- [F] "The Little Book of Deep Learning" by François Fleuret
Hand-written HWs are due at the beginning of class; Labs (i.e., HW-L) are due by 5 PM, Central Time.
| Week | Topic | Materials | Assignments |
| 08/26 Mon | Lec. 1: Introduction Overview, syllabus, logistics |
Slides | |
| 08/28 Wed | Lec. 2: Introduction to AI Foundations, history |
[RN] Chap 1 Slides |
|
| 08/30 Fri | Lec. 3: Intelligent Agents Intelligent agents |
[RN] Chap 2 Slides |
|
| 09/02 Mon | No Class (Labor Day) | ||
| 09/04 Wed | Lec. 4: Searching-1 Search algorithms |
[RN] Chap 3.1, 3.3 Slides |
|
| 09/06 Fri | Lec. 5: Searching-2 Uninformed search |
[RN] Chap 3.4 Slides |
|
| 09/09 Mon | Lec. 6: Searching-3 Informed search |
[RN] Chap 3.5, 3.6 Slides |
HW1 out (due 9/18) |
| 09/11 Wed | Lec. 7: Searching-4 Search in complex environment |
[RN] Chap 4 Slides |
|
| 09/13 Fri | Lec. 8: Game Playing-1 Game theory, optimal decisions |
[RN] Chap 5.1, 5.2 Slides |
|
| 09/16 Mon | Lec. 9: Game Playing-2 Heuristic alpha-beta tree search |
[RN] Chap 5.3 Slides |
|
| 09/18 Wed | Lec. 10: Uncertainty Probability recap |
RN] Chap 12 Slides |
HW1 due HW2 out (due 9/27) |
| 09/20 Fri | Lec. 11: Naïve Bayes Models-1 Bayes’ Rule |
[RN] Chap 12 Slides |
|
| 09/23 Mon | Lec. 12: Naïve Bayes Models-2 Bayes Models |
[RN] Chap 12 Slides |
|
| 09/25 Wed | Lec. 13: Bayesian Networks-1 |
[RN] Chap 13 Slides |
|
| 09/27 Fri | Lec. 14: Bayesian Networks-2 |
[RN] Chap 13 Slides |
HW2 due HW3 out (due 10/07) |
| 09/30 Mon | Lec. 15: Temporal Models Sequential decision problems, MDP |
[RN] Chap 14.1, 14.2 Slides |
|
| 10/02 Wed | Lec. 16: Markov Models-1 | [RN] Chap 14.3 Slides |
|
| No Class (Happy Fall Break) | |||
| 10/07 Mon | Midterm Review | HW3 due | |
| 10/09 Wed | Midterm Exam | ||
| 10/11 Fri | Lec. 18: Markov Models-2 | [RN] Chap 14.3 Slides |
HW4 out (due 10/23) |
| 10/14 Mon | Lec. 19: Overview Machine learning, pipeline, tasks |
[RN] Chap 19.2, [F] Chap 1 Slides |
|
| 10/16 Wed | Lec. 20: Supervised Learning-1 Linear regression |
[RN] Chap 19.6, [F] Chap 1.2-1.3 Slides |
|
| 10/18 Fri | Lec. 21: Supervised Learning-2 logistic regression, stochastic gradient descend |
[F] Chap 3.3 Slides |
|
| 10/21 Mon | Lec. 22: Decision Trees-1 | [RN] Chap 19.3 Slides |
|
| 10/23 Wed | Lec. 23: Decision Trees-2 | [F] Chap 19.3 Slides |
HW4 due |
| 10/25 Fri | Lec. 24: SVM-1 | Slides |
|
| 10/28 Mon | Lec. 25: SVM-2 | Slides |
|
| 10/30 Wed | Lec. 26: Clustering-1 K-means |
Slides |
|
| 11/01 Fri | Lec. 27: Clustering-2 K-means |
Slides |
HW5-L out (due 11/13) |
| 11/04 Mon | Lec. 28: Neural Network-1 1-layer NN, PyTorch tutorial |
[F] Chap 3.4, 4.5 Slides |
|
| 11/06 Wed | Lec. 29: Neural Network-2 K-layer NN (MLP) |
F] Chap 3.4, 4.5 Slides) |
|
| 11/08 Fri | Lec. 30: Neural Network-3 Backpropagation |
[F] Chap 3.1, 3.4, 3.6 Slides |
|
| 11/11 Mon | Lec. 31: CNN-1 Convolution and pooling layers Normalization and dropout layers |
[F] Chap 4.5, 5.2 Slides |
|
| 11/13 Wed | Lec. 32: CNN-2 AlexNet |
[F] Chap 5.2 Slides |
HW5-L HW6-L out (due 11/22) |
| 11/15 Fri | Lec. 33: DL for Computer Vision-1 CNN review & Classification |
[F] Chap 5.2 Slides |
|
| 11/18 Mon | Lec. 34: DL for Computer Vision-2 Classification |
Slides |
|
| 11/20 Wed | Lec. 35: DL for Computer Vision-3 Segmentation: Enc-Dec, UNet |
[RN] Chap 6.4 Slides |
|
| 11/22 Fri | Lec. 36: DL for NLP-1 NLP tasks |
[RN] Chap 23.6 Slides |
HW6-L due HW7-L out (due 12/06) |
| 11/25 Mon | Lec. 37: DL for NLP-2 NLP tasks, ChatGPT |
Slides |
|
| 11/27 Wed | Lec. 38: DL for NLP-3 ChatGPT |
Slides |
|
| No Class (Happy Thanksgiving) | |||
| 12/02 Mon | Lec. 39: Foundation Modeling Multimodal input, SAM, GPT4-V |
Slides |
|
| 12/04 Wed | Lec. 40: Philosophy, Ethics, and Safety of AI | [RN] Chap 27 Slides |
|
| 12/06 Fri | Lec 41: Material Review | Slides |
HW7-L due |
| 12/09 | Final Exam 2 PM |
||
Links
- [B] "Pattern Recognition and Machine Learning" by Christopher Bishop
- [GBC] "Deep Learning" by Ian Goodfellow, Yoshua Bengio, Aaron Courville
- [ISLP] "An Introduction to Statistical Learning" by James et al.
- [CLRS] "Introduction to Algorithms” (3rd Edition) by Cormen et al.
- Linear Algebra
- Multivariate Calculus
- Deep Learning for Computer Vision
Requirements
Your work in this course consists of 4 written and 3 mini-coding assignments.
| Requirement | Points |
| Homeworks | 45 |
| Midterm Exam | 20 |
| Final Exam | 25 |
| Participation & Quiz | 10 |
| total | 100 |
Attendance: Regular attendance is expected. More than three unexcused absences may affect your grade.
Deadlines: Hand-written HWs are due at the beginning of class; Labs (i.e., HW-L) are due by 5 PM, Central Time.
| letter grade | points |
| A | 90–100 |
| B | 80–89 |
| C | 70–79 |
| D | 60–69 |
| F | 0–59 |
Policies
Honor Code
Students in this course are expected to abide by the university Academic Honesty policy .
The following table summarizes how you may work with other students and use print/online sources:
| Resources | Solutions | |
|---|---|---|
| Consulting | allowed | cite |
| Copying | cite | not allowed |
Directly generating solutions with ChatGPT is prohibited.
If an instructor sees behavior that is, in his judgment, academically dishonest, he is required to file a formal report to the University.
Students with Disabilities
Any student who has a documented disability and is registered with Disability Services should speak with the professor as soon as possible regarding accommodations. Students who are not registered should contact the Office of Disability Services.
Late Submissions
For university-excused absences (e.g., documented illness, travel for athletics or a job interview), coursework submissions will be accepted late by the same number of days as the excused absence. The late penalty increases by 10% per day and no more submissions will be accepted after 1 week.
Make-up Exam
Make-up exam is only possible (for the final) if you give notice before the exam via e-mail both to me and department administrations with a valid official document (like Med. Doctor report).
Copyright
All course materials written by the instructor and published on this website are licensed under a Creative Commons Attribution 4.0 International License.
All other course materials, including lecture recordings and materials written by the instructor and distributed privately (including through online portal) should not be redistributed in any way; doing so is a violation of both US copyright law and the University of Louisiana at Lafayette Honor Code.