This course offers a gentle introduction to the concepts and methodologies in Artificial Intelligence from both theoretical and practical perspectives. This includes designing intelligent agents through techniques such as state-space search methods, knowledge representation and inference, and Machine Learning. By the end of this course, students are expected to have the ability to develop intelligent solutions for semi-real world problems using the appropriate methods discussed in the course. Furthermore, they are expected to gain knowledge and experience in analyzing the inner workings of these methods and customizing them for specific problems.
Please contact the administrative team only using the course's official email address, sharifaicentral@gmail.com. Avoid sending an email or a message directly to any member of the instruction team. Ensure that you use a proper subject for your email and include your name and student ID. It is strongly encouraged to use the @Sharif webmail service to ensure easy identification by the instructional team. To ask questions about assignments and other course materials, please use Quera. Using Telegram and other messenger services is discouraged. Anything communicated in these messengers by any of the TAs will not be recognized as an official statement and will not be applicable to the grading process. Note that you can always have direct contact with the instructors via their email addresses.
Knowledge and experience of a general-purpose programming language (Python), Data Structures and Algorithms, and ideally Probability and Statistics (Random Variables, (Joint) Probability Mass Functions, Conditional Probability, Independence, Bayes Theorem) and Linear Algebra. It is highly recommended to have the Engineering Probability and Linear Algebra courses passed before taking this course.
Even though the instruction of both groups is jointly coordinated, each instructor will have their own class. Dr. Soleymani's class will be held on Sundays and Tuesdays from 15:00 to 16:30, and Dr. Rohban's class will take place on Sundays and Tuesdays from 10:30 to 12:00. Classes will be held in person by default, but in special circumstances, the class might be conducted virtually (with prior announcements), at https://vc.sharif.edu/ch/soleymani or https://vc.sharif.edu/ch/rohban.
Assessment of students of both groups will be identical. Please note that grades will be calculated out of $21.5$.
- 1$^{\text{st}}$ Midterm Exam: $3.0$ points; 1402/08/18 9:00 AM.
- 2$^{\text{st}}$ Midterm Exam: $4.0$ points; 1402/09/30 9:00 AM.
- Final Exam: $5.0$ points; 1402/10/21 9:00 AM (as scheduled in EDU).
- Homework Assignments: $7.5 + 1.0$ points; Five Series, each $1.5$ points and $1$ bonus point in total.
- Optional Task: You must choose only one of two tasks below:
- Presentation: $1.0$ point.
- Project: $1.5$ point.
Students' learning will be assessed through two midterms and a final exam. These exams will be held on the following dates, and students are required to participate in them.
- 1$^{\text{st}}$ Midterm Exam: 1402/08/18 9:00 AM.
- 2$^{\text{st}}$ Midterm Exam: 1402/09/30 9:00 AM.
- Final Exam: 1402/10/21 9:00 AM (as scheduled in EDU).
Five series of homework assignments will be distributed in this course. Assignments will be released on Sunday midnight every other week. Students will have 14 days to submit their answers on Quera. Regarding the late submission policy, you can submit answers with total delay of 5 days (maximum of 2 days for each submission) with no penalty. Any more delays and 1% of the assignment grade will be deducted for each hour of delay. Please note that submissions made between midnight (12 AM) and noon (12 PM) will not be considered. You can submit your answers during this interval, but the submission timestamp will be recorded as 12 PM on the same day. Delays will be calculated on an hourly scale, as illustrated in the figure below and described by equation following the figure, where $h$ represents the amount of delay in hours.
There will be a zero-tolerance policy for cheating or copying homework assignments. The first time you are caught, we will refer you to the committee, and you will fail the course. Please refer to the Education Committee's statement on homework etiquette.
We would be grateful if you could send us your valuable feedback. You can contact instructors or even TAs via email. Additionally, you can use this Google form to send your feedback anonymously to the instructors.
- https://sut-ai.github.io/: This is the main page of our course and all exercises, slides and course resources will be placed in it.
- Quera, https://quera.org/course/add_to_course/course/14673/: Delivery of exercises and announcements will be done entirely through Quera. Make sure you enter an email on Quera that you check regularly. Your questions from the exercises will also be answered in Quera.
|
1 |
Date:
Tue Mehr 4 |
Description:
Introduction & Intelligent Agents |
Course Materials: | Events: | Deadlines: |
|
2 |
Date:
Sun Mehr 9 |
Description:
Uninformed Search |
Course Materials: | Events: | Deadlines: |
|
3 |
Date:
Sun Mehr 16 |
Description:
Informed Search |
Course Materials: | Events: | Deadlines: |
|
Date:
Mon Mehr 17 |
Description: | Course Materials: | Events: | Deadlines: | |
|
4 |
Date:
Tue Mehr 18 |
Description:
Local Search |
Course Materials: | Events: | Deadlines: |
|
5 |
Date:
Sun Mehr 23 |
Description:
Search in Continuous spaces |
Course Materials: | Events: | Deadlines: |
|
6 |
Date:
Tue Mehr 25 |
Description:
Constraint Satisfaction Problems I |
Course Materials: | Events: | Deadlines: |
|
7 |
Date:
Sun Mehr 30 |
Description:
Constraint Satisfaction Problems II |
Course Materials: | Events: | Deadlines: |
|
Date:
Mon Aban 1 |
Description: | Course Materials: | Events: |
Deadlines:
HW1 due |
|
|
8 |
Date:
Tue Aban 2 |
Description:
Adversarial Search |
Course Materials: | Events: | Deadlines: |
|
9 |
Date:
Sun Aban 7 |
Description:
Markov Decision Process |
Course Materials: | Events: | Deadlines: |
|
10 |
Date:
Tue Aban 9 |
Description:
Markov Decision Process: Value Iteration & Policy Iteration |
Course Materials: | Events: | Deadlines: |
|
Date:
Sat Aban 13 |
Description: | Course Materials: | Events: |
Deadlines:
HW2 due |
|
|
11 |
Date:
Sun Aban 14 |
Description:
Reinforcement Learning: Passive |
Course Materials: | Events: | Deadlines: |
|
12 |
Date:
Tue Aban 16 |
Description:
Reinforcement Learning: Active |
Course Materials: | Events: | Deadlines: |
|
Date:
Thr Aban 18 |
Description:
Midterm Exam I |
Course Materials:
Sessions 1-8 |
Events: | Deadlines: | |
|
13 |
Date:
Sun Aban 21 |
Description:
Reinforcement Learning: Approximate |
Course Materials: | Events: | Deadlines: |
|
14 |
Date:
Tue Aban 23 |
Description:
Uncertainty & Inference |
Course Materials: | Events: | Deadlines: |
|
15 |
Date:
Sun Aban 28 |
Description:
Bayesian Networks: Representation |
Course Materials: | Events: | Deadlines: |
|
16 |
Date:
Tue Aban 30 |
Description:
Inference in Bayesian Networks: Exact |
Course Materials: | Events: | Deadlines: |
|
Date:
Sat Azar 4 |
Description: | Course Materials: | Events: |
Deadlines:
HW3 due |
|
|
17 |
Date:
Sun Azar 5 |
Description:
Inference in Bayesian Networks: Approximate |
Course Materials: | Events: | Deadlines: |
|
18 |
Date:
Tue Azar 7 |
Description:
Temporal Probability Models: Markov Chains & HMMs |
Course Materials: | Events: | Deadlines: |
|
19 |
Date:
Sun Azar 12 |
Description:
Temporal Probability Models: Particle Filters |
Course Materials: | Events: | Deadlines: |
|
20 |
Date:
Tue Azar 14 |
Description:
Learning in Bayesian Networks & Naive Bayes |
Course Materials: | Events: | Deadlines: |
|
21 |
Date:
Sun Azar 19 |
Description:
Decision Tree |
Course Materials: | Events: | Deadlines: |
|
22 |
Date:
Tue Azar 21 |
Description:
Concepts of Machine Learning |
Course Materials: | Events: | Deadlines: |
|
Date:
Sat Azar 25 |
Description: | Course Materials: | Events: |
Deadlines:
HW4 due |
|
|
Date:
Sun Azar 26 |
Description: | Course Materials: | Events: | Deadlines: | |
|
23 |
Date:
Tue Azar 28 |
Description:
Regression & Optimization |
Course Materials: | Events: | Deadlines: |
|
Date:
Thr Azar 30 |
Description:
Midterm Exam II |
Course Materials:
Sessions 9-19 |
Events: | Deadlines: | |
|
24 |
Date:
Sun Dey 3 |
Description:
Perceptron |
Course Materials: | Events: | Deadlines: |
|
25 |
Date:
Tue Dey 5 |
Description:
Neural Networks I |
Course Materials: | Events: | Deadlines: |
|
26 |
Date:
Sun Dey 10 |
Description:
Neural Networks II |
Course Materials: | Events: | Deadlines: |
|
27 |
Date:
Tue Dey 12 |
Description:
Applications |
Course Materials: | Events: | Deadlines: |
|
Date:
Fri Dey 19 |
Description: | Course Materials: | Events: |
Deadlines:
HW5 due |