Scribd
Upload
55 views2 pages

ME 466 Introduction To Artificial Intelligence Fall 2021: Kerem Altun

The document outlines the schedule, instructor information, overview, prerequisites, grading plan, and course content for ME 466 Introduction to Artificial Intelligence being offered in the fall 2021 semester, with topics including neural networks, machine learning, genetic algorithms, and applications of AI to physical systems. Assignments, a midterm exam, and final exam will contribute to the final grade, with programming assignments making up 40-50% and exams 20-40% depending on the grading plan selected.

Uploaded by

Seçkin Martin
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
55 views2 pages

ME 466 Introduction To Artificial Intelligence Fall 2021: Kerem Altun

The document outlines the schedule, instructor information, overview, prerequisites, grading plan, and course content for ME 466 Introduction to Artificial Intelligence being offered in the fall 2021 semester, with topics including neural networks, machine learning, genetic algorithms, and applications of AI to physical systems. Assignments, a midterm exam, and final exam will contribute to the final grade, with programming assignments making up 40-50% and exams 20-40% depending on the grading plan selected.

Uploaded by

Seçkin Martin
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

ME 466 Introduction to Artificial Intelligence

Fall 2021
Course schedule: Wednesday 14:30 – 17:15 (D03)

Instructor: Kerem Altun

Office: Mechanical Engineering Building Z-15

E-mail: [email protected]

Office hours: Tuesday 10:45 – 12:30, or by appointment, or whenever I am in my office.

Course assistant: Sefa Furkan Küçükoğlu (Robotics Lab Z30, Ext. 6751, [email protected])

Overview: The aim of this course is to provide senior mechanical engineering students with an
overview of artificial intelligence at the introductory level. We will start with neural networks and
continue with probabilistic representation of uncertainty and its application to machine learning
and related problems. We will try to focus on applications of AI to physical systems working in the
physical world, which are of main concern to mechanical engineers.

Course catalog content: A Brief History of Artificial Intelligence; An Introduction to Matlab; Uses
and Limitations of AI; Knowledge Representation; Search Methodologies; Machine Learning;
Artificial Life: Learning through Emergent Behavior; Neural Networks; Genetic Algorithms

Prerequisites: Basic calculus and linear algebra. At least a CB grade from CS106 (or equivalent) or
enthusiasm for programming is strongly recommended. Students from programs other than the ME
undergraduate program must be approved by the instructor before taking the class.

Reference books

• C. Say, 50 Soruda Yapay Zeka, Bilim ve Gelecek Kitaplığı, 2018.


• S. Russell, P. Norvig, Artificial Intelligence: A Modern Approach, 4th Edition, Global
Edition, Pearson, 2021.
• S. Haykin, Neural Networks and Learning Machines, Pearson, NJ, 2009.
• R.O. Duda, P.E. Hart, D.G. Stork, Pattern Classification, Second Edition, Wiley, 2001.
• G. Strang, 18.065 Matrix Methods in Data Analysis, Signal Processing, and Machine
Learning. Spring 2018. Massachusetts Institute of Technology: MIT OpenCourseWare,
License: Creative Commons BY-NC-SA.
• G. Strang, Linear Algebra and Learning from Data, Wellesley-Cambridge Press, 2019.

Grading: Programming assignments, midterm and final exams will contribute to the final grade.
The overall grade will be calculated according to one of the plans below, in favor of each student:

Plan A Plan B Plan C


Programming assignments 50% 40% 40%
Midterm Exam 20% 30% 20%
Final Exam 30% 30% 40%
Programming assignments: 3--4 programming assignments will be given throughout the semester.
The assignments should be submitted following the rules below:

• Assignments should be typed on a computer. Handwritten papers will not be accepted.


You should have access to a word processor that can also display mathematical expressions
(such as MS Word and Equation Editor).
• Assignments should be submitted in the form of a well-documented report. If you use
references other than the course notes, they should be properly referenced. Any figures,
tables, graphs, plots, code, algorithm, etc. should be properly numbered and captioned.
• Every step you take in solving the assignments should be explained in the report in
words. Do not submit your solutions as uncommented code or a list of mathematical
expressions. Write down your solution as if you were explaining it to a classmate.
• You are allowed to collaborate with your classmates on solving the assignments. However,
the assignment report should be prepared individually by each student. You should provide
detailed explanations of the solution in your own words; this is the way to demonstrate that
you worked on the problem on your own. Any duplicate papers will be disregarded and
legal action will be taken.
• If you use MATLAB or any other software for the solutions, include all codes, plots, graphs,
tables, etc. in your submission.
• Late submissions will not be accepted.

Midterm and final exams: The exam dates and format will be announced later and will cover the
theoretical material that we cover in class. Use of class notes, books, computers, internet, etc. are
allowed in the exams, provided that you properly cite your references. The purpose of the exams is
to evaluate how you demonstrate your knowledge about the course in a limited amount of time.

Course Outline (tentative)

Week Content
1 Introduction; brief overview of AI, history, embodied AI, behavioral AI, data-driven AI
2 Classical AI; search algorithms; behavior-based AI; simple robot navigation algorithms
3 Linear algebra review
4 Neural networks, neuron model, activation function, perceptron, linear separability
5 Learning rules, gradient descent, multi-layer networks, backpropagation
6 Signal and image processing, pattern matching, linear filters, convolution
7 Overview of multi-layer deep networks, CNN, recurrent networks, LSTM
8 Midterm Exam
9 Basics of probability theory, random variables, Bayes theorem
10 Decision making and planning, Bayesian decision theory, other decision rules
11 Pattern classification problems, parametric and non-parametric methods
12 Feature extraction, selection and reduction, principal components analysis
13 Unsupervised learning and clustering
14 Applications

You might also like