BIL 682 - Artificial Intelligence (Spring 2013)

Lectures: Tuesday 13:30-16:15@D7


A comic strip by Tom Gauld

Instructor: Aykut Erdem

e-mail: aykut-at-cs.hacettepe.edu.tr

Office: 111

Tel: 297 7500 / 146

Office hours: By appointment.


Course Description:

This is a graduate-level introductory course in Artificial Intelligence (AI) which will give a broad overview of many concepts and algorithms in AI, starting from basic topics like problem solving by searching, game playing, supervised and unsupervised learning to more recent topics such as online learning, ranking and structural learning. The goal is to provide students with a deep understanding of the subject matter and skills to apply these concepts to real world problems.


Prerequisites:

Basic algorithms, data structures. Basic probability and statistics. Basic linear algebra and calculus. Good programming skills.


Reading Assignments:

Each week a number of research papers will be assigned as reading assignments. Students are expected to write a brief review of any of the assigned papers (less than a page) for half of the papers. Each review should summarize the paper in 4-5 sentences. The review should clearly identify the main contribution of the paper and describe the strengths and weaknesses of the paper. The reviews should be emailed to the instructor before class (by 13:00 on Tuesdays). Each student has 3 late days for the entire semester, but beyond that limit his/her submission will not be accepted.


Programming Assignments:

There will be three assignments related to the topics covered in the class. Each assignment will involve implementing an algorithm, carrying out a set of experiments to evaluate it, and writing up a report on the experimental results. All assignments have to be done individually, unless stated otherwise.


Project:

The students taking the course will be required to do a project which should be done in a team of at most two students. For a detailed description of the course project, follow this link. In preparing your progress and final project reports, you should use the provided template and submit them electronically in PDF format.


Grading Policy:

Class participation  

5%

Reading Assignments

12%

Programming Assignments  

18%

Project

30%

Final Exam

35%


Course Schedule:


Week  

Date  

Topic  

Assignments              

Additional Readings


1

2/26  

Introduction to Artificial Intelligence [slides]   

­­­­­­

2

3/5  

Problem Solving and Search [slides]

PSet 1 out
Mazes

3

3/12  

Game Playing [slides]

­­­­­­  ­­­­­­

4

3/19  

Introduction to Machine Learning, Naïve Bayes Classifier Logistics Regression [slides

Supplemental Readings:

­­­­­­

5

3/26  

Instance based learning, Support vector machines [slides

Supplemental Readings:

PSet 1 due­

6

4/2  

Boosting, Model Selection [slides

Supplemental Readings:

PSet 2 out
beach and grassland images

7

4/9  

Clustering, Unsupervised Dimensionality Reduction [slides

Supplemental Readings:

8

4/16  

Semi-Supervised Learning, Multiple-Instance Learning [slides

Supplemental Readings:

­­­­­­PSet 2 due, PSet 3 out [files]

9

4/23  

No class (The Republic Day) 

10

4/30  

Learning with structured inputs and outputs [slides

Supplemental Readings:

PSet 3 due­­­­­­

11

5/7  

Learning to Rank, Multiple-Kernel Learning, Online Learning [slides

Supplemental Readings:

12

5/14  

Kernel Density Estimation, Kernel Regression, Outlier Detection [slides

Supplemental Readings:

­­­­­­

13

5/21  

Project Presentations 

­­­­­­

14

5/28  

Project Presentations (continued) 

­­­­­­


Resources:


Communication:

The course webpage will be updated regularly throughout the semester with reading assignments and important deadlines. All other communications will be carried out through Piazza. Please enroll it by following the link https://piazza.com/hacettepe.edu.tr/spring2013/bil682