| Digital Game Design (English) | |||||
| Bachelor | TR-NQF-HE: Level 6 | QF-EHEA: First Cycle | EQF-LLL: Level 6 | ||
| Course Code: | DGD401 | ||||
| Course Name: | Machine Learning and Artificial Intelligence | ||||
| Semester: | Fall | ||||
| Course Credits: |
|
||||
| Language of instruction: | English | ||||
| Course Condition: | |||||
| Does the Course Require Work Experience?: | No | ||||
| Type of course: | Compulsory Courses | ||||
| Course Level: |
|
||||
| Mode of Delivery: | Face to face | ||||
| Course Coordinator: | Dr. Öğr. Üy. İSMAİL ERGEN | ||||
| Course Lecturer(s): | Dr. Öğr. Üyesi İsmail Ergen | ||||
| Course Assistants: |
| Course Objectives: | Introduction to the computational approaches addressing various learning tasks. Topics include supervised learning and unsupervised algorithms as well as their applications besides supporting concepts like data pre-processing, bias and variance. |
| Course Content: | Basics of Machine Learning will be explained while introducing some well-known Machine Learning algorithms besides the supporting approaches and ideas for building strong Machine Learning models. |
|
The students who have succeeded in this course;
1) Will know basic knowledge on Machine Learning 2) Will understand and be able to model supervised learningproblems and solve them 3) Will understand and be able to model unsupervised learningproblems and solve them. 4) Will be able to evalute developed learning models and improve their quality. |
| Week | Subject | Related Preparation |
| 1) | Introduction to Machine Learning | |
| 2) | Supervised Learning- Regresion Problem | |
| 3) | Supervised Learning- Classification Problem- Logistic Regression- K-Nearest Neighbour | |
| 4) | Exploratory Data Analysis, Data Pre-processing | |
| 5) | Supervised Learning- Decision Tree- Handling imbalanced dataset | |
| 6) | Supervised Learning- Random Forest- Cross Validation and its types | |
| 7) | Supervised Learning- Naive Bayes and Support Vector Machines | |
| 8) | Midterm | |
| 9) | Supervised Learning- Hyper parameter tuning, Dimensionality Reduction | |
| 10) | Unsupervised Learning | |
| 11) | Ensemble Learning Methods- Boosting Techniques | |
| 12) | Artificial Neural Networks,Perceptrons | |
| 13) | Artificial Neural Networks, Multi-layer Networks | |
| 14) | Project Presentation, Final Exam |
| Course Notes / Textbooks: | There are no resources for the course |
| References: | Introduction to Machine Learning, Ethem Alpaydın (3rd Edition), 2014,MIT Press Understanding Machine Learning: From Theory to Algorithms, ShaiShalev-Shwartz, Shai Ben-David (1st Edition), 2014, CambridgeUniversity Press Pattern Recognition and Machine Learning, Christopher Bishop (1stEdition), 2006, Springer Learning from Data, Yaser S. Abu-Mostafa, Malik Magdon-Ismail,Hsuan-Tien Lin (1st Edition), 2012, AMLBook Machine Learning - an Algorithmic Perspective, Stephen Marshland (2ndEdition), 2015, CRC Press Machine Learning Refined: Foundations, Algorithms, and Applications,Jeremy Watt, Reza Borhani, Aggelos K. Katsaggelos (1st Edition), 2016,Cambridge University Press Foundations of Machine Learning, Mehryar Mohri, Afshin Rostamizadeh,Ameet Talwalkar (2nd Edition), 2018, MIT Press Machine Learning: a Probabilistic Perspective, Kevin P. Murphy (1stEdition), 2012, MIT Press Machine Learnin, Tom Mitchell (1st Edition), 1997, McGraw Hill Press A Course in Machine Learning10, Hal Daume III (2nd Edition), 2017 Introduction to Machine Learning, Alex Smola, S.V.N. Vishwanathan (1stEdition), 2008, Cambridge University Press Machine Learning: the Art and Science of Algorithms that Make Sense ofData, Peter Flach (1st Edition), 2012, Cambridge University Press Bayesian Reasoning and Machine Learning, David Barber (1st Edition -Rev. 2020), 2012, Cambridge University Press The Hundred-Page Machine Learning Book, Andriy Burkov, 2019 Machine Learning Mastery with Python, Jason Brownlee, 2016 Reinforcement Learning: an Introduction, Richard S. Sutton, Andrew G.Barto (2nd Edition - Rev. 2020), 2018, MIT Press Artificial Intelligence - With an Introduction to Machine Learning17,Richard E. Neapolitan, Xia Jiang (2nd Edition), 2018, CRC Press Machine Learning Yearning, Andrew Ng (1st Edition), 2020,deeplearning.ai Machine Learning - The New AI, Ethem Alpaydin (1st Edition), 2016,MIT Press Deep Learning with Python, François Chollet (2nd Edition), 2018,Manning Press Deep Learning, Ian Goodfellow, Yoshua Bengio, Aaron Courville (1stEdition), 2016, MIT Press Neural Networks and Deep Learning22,Michael Nielsen, 2019 Neural Networks and Deep Learning: A Textbook, Charu C. Aggarwal(1st Edition), 2018, Springer Dive into Deep Learning, Aston Zhang, Zachary C. Lipton, Mu Li,Alexander J. Smola (V. 0.143), 2020 Advances in Deep Learning, M. Arif Wani, Farooq Ahmad Bhat, SadufAfzal, Asif Iqbal Khan, 2020, Springer Grokking Deep Learning, Andrew W. Trask (1st Edition), 2019, Manning Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow:Concepts, Tools, and Techniques to Build Intelligent Systems, AurélienGéron (2nd Edition), 2019, O'Reilly Introduction to Machine Learning with Python: A Guide for DataScientists, Andreas C. Müller, Sarah Guido (1st Edition), 2017, O'Reilly The Elements of Statistical Learning: Data Mining, Inference, andPrediction, Trevor Hastie, Robert Tibshirani, Jerome Friedman (2ndEdition), 2009, Springer Press Mathematics for Machine Learning, Marc Peter Deisenroth, A. AldoFaisal, Cheng Soon Ong (1st Edition), 2020, Cambridge University Press Linear Algebra and Optimization for Machine Learning: A Textbook,Charu C. Aggarwal (1st Edition), 2020, Springer Press Optimization for Machine Learning, Suvrit Sra, Sebastian Nowozin,Stephen J. Wright (Edited - 1st Edition), 2011, MIT Press Convex Optimization, Stephen Boyd, Lieven Vandenberghe (1st Edition),2004, Cambridge University Press Data Mining: Concepts and Techniques, Jiawei Han, Micheline Kamber,Jian Pei (3rd Edition), 2012, Morgan Kaufmann Data Mining and Analysis: Fundamental Concepts and Algorithms,Mohammed J. Zaki, Wagner Meira, Jr. (1st Edition), 2014, CambridgeUniversity Press Data Mining: Practical Machine Learning Tools and Techniques, Ian H.Witten, Eibe Frank, Mark A. Hall, Christopher J. Pal (4th Edition), 2016,Morgan Kaufmann Press Data Mining: The Textbook, Charu C. Aggarwal (1st Edition), 2015,Springer Press Data Clustering, Chandan K. Reddy, Charu C. Aggarwal (1st Edition -Ed.), 2014, CRC Press |
| Course Learning Outcomes | 1 |
2 |
3 |
4 |
||||
|---|---|---|---|---|---|---|---|---|
| Program Outcomes | ||||||||
| 1) Being able to write creatively, imagine, and produce original and inspired fictional scenarios, places, and universes. Being able to produce 2D and 3D visual designs and impressive auditory compositions. Being able to plan all these artistic practices around certain goals and with a focus on design. Being able to design the videogame design process itself. | 2 | 1 | 2 | |||||
| 2) Being able to think and produce creative content based on mathematical data. Being able to parametrically design. Being able to quantify art and design practices, such as creative writing, graphical, illustrative, spatial, and character design. Being able to ideate qualitatively and subjectively through quantitative and objective approaches. | 2 | 3 | ||||||
| 3) Being able to work on projects by incorporating various fields of expertise and the content that originates from these fields. Being able to work as part of a team while embracing different ideas and skills. Being able to produce comprehensive and total videogame concepts. Being able to edit, exhibit, present, and defend works in portfolio and presentation formats. | 2 | 3 | 1 | |||||
| 4) Achieving critical thinking literacy on videogame history and theory. Being able to think through and produce academic texts about the philosophical, anthropological, political, and social manifestations of games. Being vigilant about the contemporary problematics of videogame epistemology. Displaying professionalism in accepting criticism. | ||||||||
| 5) Being informed about the historical accumulation and contemporary productions of the videogame culture and other cultural playgrounds from which videogame culture draws. Being able to tackle, process, and position both aesthetic and technical production and thinking methods as cultural activities. | 2 | 2 | ||||||
| 6) Being knowledgeable about the past, aware of the present, and foresighted about the future potentials of the social and economic realities of videogames. Being able to handle professional relations, create correspondence, and manage production plans. Being a generalist, while also specializing in one or more areas of expertise. | 3 | 3 | 1 | |||||
| 7) Being able to research, filter data, and synthesize both within and outside videogame epistemology at every stage of production. Being able to conduct interdisciplinary research. Being able to create original ideas by remixing content from various sources. Learning to learn. | 3 | 1 | ||||||
| 8) Understanding, learning, and using professional content authoring tools and technologies. Being able to design workflows in service of various production requirements. Being able to use technologies within the workflow besides the usual and intended purposes, and researching, discovering, and putting to use technologies for new purposes. | 2 | 2 | 2 | |||||
| No Effect | 1 Lowest | 2 Average | 3 Highest |
| Program Outcomes | Level of Contribution | |
| 1) | Being able to write creatively, imagine, and produce original and inspired fictional scenarios, places, and universes. Being able to produce 2D and 3D visual designs and impressive auditory compositions. Being able to plan all these artistic practices around certain goals and with a focus on design. Being able to design the videogame design process itself. | 1 |
| 2) | Being able to think and produce creative content based on mathematical data. Being able to parametrically design. Being able to quantify art and design practices, such as creative writing, graphical, illustrative, spatial, and character design. Being able to ideate qualitatively and subjectively through quantitative and objective approaches. | 3 |
| 3) | Being able to work on projects by incorporating various fields of expertise and the content that originates from these fields. Being able to work as part of a team while embracing different ideas and skills. Being able to produce comprehensive and total videogame concepts. Being able to edit, exhibit, present, and defend works in portfolio and presentation formats. | 3 |
| 4) | Achieving critical thinking literacy on videogame history and theory. Being able to think through and produce academic texts about the philosophical, anthropological, political, and social manifestations of games. Being vigilant about the contemporary problematics of videogame epistemology. Displaying professionalism in accepting criticism. | 1 |
| 5) | Being informed about the historical accumulation and contemporary productions of the videogame culture and other cultural playgrounds from which videogame culture draws. Being able to tackle, process, and position both aesthetic and technical production and thinking methods as cultural activities. | 2 |
| 6) | Being knowledgeable about the past, aware of the present, and foresighted about the future potentials of the social and economic realities of videogames. Being able to handle professional relations, create correspondence, and manage production plans. Being a generalist, while also specializing in one or more areas of expertise. | |
| 7) | Being able to research, filter data, and synthesize both within and outside videogame epistemology at every stage of production. Being able to conduct interdisciplinary research. Being able to create original ideas by remixing content from various sources. Learning to learn. | 1 |
| 8) | Understanding, learning, and using professional content authoring tools and technologies. Being able to design workflows in service of various production requirements. Being able to use technologies within the workflow besides the usual and intended purposes, and researching, discovering, and putting to use technologies for new purposes. | 3 |
| Semester Requirements | Number of Activities | Level of Contribution |
| Homework Assignments | 1 | % 30 |
| Midterms | 1 | % 30 |
| Final | 1 | % 40 |
| total | % 100 | |
| PERCENTAGE OF SEMESTER WORK | % 60 | |
| PERCENTAGE OF FINAL WORK | % 40 | |
| total | % 100 | |
| Activities | Number of Activities | Preparation for the Activity | Spent for the Activity Itself | Completing the Activity Requirements | Workload | ||
| Course Hours | 14 | 2 | 28 | ||||
| Application | 14 | 2 | 28 | ||||
| Project | 1 | 15 | 15 | ||||
| Midterms | 1 | 0 | 0 | ||||
| Final | 1 | 20 | 20 | ||||
| Total Workload | 91 | ||||||