BIN785 - ADVANCED MACHINE LEARNING

Course Name Code Semester Theory
(hours/week)
Application
(hours/week)
Credit ECTS
ADVANCED MACHINE LEARNING BIN785 Any Semester/Year 2 2 3 9
Prequisites-
Course languageEnglish
Course typeElective 
Mode of DeliveryFace-to-Face 
Learning and teaching strategiesLecture
Preparing and/or Presenting Reports
 
Instructor (s)Prof. Erdem Karabulut 
Course objectiveBasic concepts of Machine Learning (ML), identifying complex patterns /structures in data and developing automatic learning algorithms needed to make decisions based on the data will be discussed. Usage of supervised- unsupervised and bayesian learning algorithms and their applications in Bioinformatic studies will be discussed.  
Learning outcomes
  1. learn basic methods including unsupervised, supervised and Bayesian Learning. learn how to select the suitable methods apply the most suitable method by the support of softwares compare the results of different methods interpret the results of methods
Course ContentBasic Concepts in Machine Learning
Bootstrap and Cross-validation
Bagging ve Boosting Algorithms
Artificial Neural Networks
Deep Learning
Naive Bayes Method
Genetic Algorithms
Kohonen Map
Basic Concepts of Image Mining
Microarray Data and Machine Learning,
Unsupervised Based Classification 
References1.Aidong Zhang, Advanced Analysıs Of Gene Expressıon Mıcroarray Data, World Scientific Publishing Co. Pte. Ltd, 2006
2.Mei-Lıng Tıng Lee ,Analysıs of Mıcroarray Gene Expressıon Data, Kluwer Academic Publishers, 2004
3.David Posada (Editor), Bioinformatics for DNA Sequence Analysis Human, A Press, Springer Science, Business Media, 2009
4.Ilya Shmulevich, Wei Zhang (Editors), Computatıonal And Statistical Approaches To Genomics, Second Edition, Springer Science+Business Media, Inc.,2006
5.Rongling Wu, George Casella, Chang-Xing Ma, Statistical Genetics of Quantitative Traits, Linkage, Maps, and QTL, Springer Science + Business Media, LLC, 2007
6.Peter Schattner, Genomes, Browsers, and Databases,Cambridge University Press, 2008 

Course outline weekly

WeeksTopics
Week 1Basic Concepts in Machine Learning
Week 2Bootstrap and Cross-validation
Week 3Bagging ve Boosting Algorithms
Week 4Artificial Neural Network-1
Week 5Artificial Neural Network-2
Week 6Deep Learning
Week 7Naive Bayes Method
Week 8Midterm exam
Week 9Genetic Algorithms
Week 10Kohonen Map
Week 11Basic Concepts of İmage Mining
Week 12Midterm exam
Week 13Microarray Data and Machine Learning
Week 14Unsupervised Based Classification
Week 15Preparation to final exam
Week 16Final Exam

Assesment methods

Course activitiesNumberPercentage
Attendance00
Laboratory00
Application00
Field activities00
Specific practical training00
Assignments210
Presentation00
Project00
Seminar00
Midterms240
Final exam150
Total100
Percentage of semester activities contributing grade succes450
Percentage of final exam contributing grade succes150
Total100

WORKLOAD AND ECTS CALCULATION

Activities Number Duration (hour) Total Work Load
Course Duration (x14) 14 2 28
Laboratory 0 0 0
Application14228
Specific practical training000
Field activities000
Study Hours Out of Class (Preliminary work, reinforcement, ect)148112
Presentation / Seminar Preparation000
Project000
Homework assignment224
Midterms (Study duration)22040
Final Exam (Study duration) 15858
Total Workload4792270

Matrix Of The Course Learning Outcomes Versus Program Outcomes

D.9. Key Learning OutcomesContrubition level*
12345
1. He/She should use electronical databases; such as Science Direct, PubMed, ISI, published books and periodical publications properly.    X
2. He/She will know basic bioinformatics analysis methods and use them properly in research.    X
3. Since bioinformatics is an interdisciplinary branch of science, he/she will be able to a part of group work, have good communication skills, and will understand others' problems.    X
4. He/She should have internet utilization skills enough to follow the innovations in the field and access desired information, accessing library sources should be advanced.    X
5. He/She will prepare projects for his/her technical-scientific development, provide consultancy service for seminars and genetic analyses, attend article discussions, congresses and workshops.    X
6. /She will be able to follow recent developments in other research fields also.    X
7. He/She will use programming languages, such as R, Phyton and Linux and uses Bioinformatics tools like Bioconductor, BLAST, PLINK, GATK etc. and will know the logic of basic programming.    X

*1 Lowest, 2 Low, 3 Average, 4 High, 5 Highest