Fundamentals of Artificial Intelligence (5 cr)
Code: TT00EM55-3001
General information
Timing
01.10.2020 - 31.12.2021
Number of ECTS credits allocated
5 op
Virtual portion
5 op
Mode of delivery
Distance learning
Unit
School of ICT
Campus
Karaportti 2
Teaching languages
- English
Seats
0 - 100
Degree programmes
- Information and Communication Technology
Teachers
- Virve Prami
Teacher in charge
Janne Salonen
Groups
-
ATX21TVNonStop virtual Studies year 2021
-
ATX20TVOpen UAS - NonStop year 2020
Objective
This course is 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 and Machine Learning. At the end of this course, students are expected to be able to develop intelligent solutions for semi real-world problems through appropriate methods that are discussed in the course. Furthermore, they are expected to gain knowledge and experience to analyze inner working of the methods and customize for specific problems. They will also get familiar with three main branches of Artificial Intelligence such as Computer Vision, Natural Language Processing and Speech processing and they will find their interest among them.
This course is 100% virtual thanks to the comprehensive interactive material and content made for this course.
The student will pass this course after submitting required assignments, quiz, and projects.
Content
1. Introduction:
What is AI? - Philosophy and history of AI - AI concepts and Some Practical Applications - Python Overview
2. Problem Space and Search:
Problem Solving Agent - Uninformed Search - Informed Search – Search in Continuous Space – Beyond Classical Search – Constraint Satisfaction Problem
3. Games:
What are Games? - Mini-Max Algorithm - Alpha-Beta Pruning – Some Famous Game Agents – Game Theory
4. Machine Learning:
Introduction to Probability - What is Machine Learning? - Classification and regression – Neural Network -
5. Markov Models:
Markov Decision Process - Hidden Markov Model
6. Reinforcement Learning:
Introduction - Passive Learning vs Active Learning – Exploration and Decision Making
6. Applications:
Natural Language Processing – Speech Processing – Computer Vision
Location and time
Course is in TechClass environment and it can be done in own pace.
Materials
Online.
Teaching methods
This course is 100% virtual thanks to the comprehensive interactive material and content made for this course.
Course includes:
- Tutorial Videos
- Assignments
- Quiz
- Projects
- Self-study
Employer connections
N/A
Exam schedules
Online.
International connections
N/A
Completion alternatives
N/A
Student workload
Lectures = 40h
Assignments = 25h
Self-study = 40h
Quiz = 5h
Project = 20h
Essay = 5h
Total = 135 hours
Content scheduling
Lectures = 40h
Assignments = 25h
Self-study = 40h
Quiz = 5h
Project = 20h
Essay = 5h
Total = 135 hours
Evaluation scale
0-5
Assessment criteria, satisfactory (1)
- The student knows the basic definitions of Artificial Intelligence and applications of AI.
- The student knows different types of Artificial Intelligence agents and environments.
- The student knows different type of search.
- The student knows what games are.
- The student knows the what is machine learning and different types of it.
- The student is familiar with Probability and Python.
Assessment criteria, good (3)
- The student knows different type of search in detail and when to use them.
- The student knows strategies for winning a game.
- The student knows Linear and Logistic Regression and Naïve Bayes.
- The student knows what a Markov Model is and can model real life problem with it.
- The student knows what Neural Network.
- The student knows what Reinforcement Learning is difference of it with Machine Learning.
Assessment criteria, excellent (5)
- The student can implement different type of search such as DFS, BFS, etc.
- The student knows what Convex Optimization is and can optimize a convex function.
- The student knows what Game Theory is and can find Nash Equilibrium of it.
- The student knows how to implement Linear Regression, Logistic Regression and Naïve Bayes.
- The student knows elements of a Hidden Markov Model and can model real life problem with it.
- The student knows difference between Passive Learning and Active Learning.
- The student knows some basic intuition about Computer Vision, NLP and Speech Processing.
Assessment methods and criteria
Exercises 30%
Quizzes 20%
Project 40%
Essay 10%