ECTS @ IUE ECTS @ IUE ECTS @ IUE ECTS @ IUE ECTS @ IUE ECTS @ IUE ECTS @ IUE

Syllabus ( ELEC 472 )


   Basic information
Course title: Fundamentals of Machine Learning
Course code: ELEC 472
Lecturer: Assist. Prof. Ahmet GÜNEŞ
ECTS credits: 6
GTU credits: 3 ()
Year, Semester: 4, Fall and Spring
Level of course: First Cycle (Undergraduate)
Type of course: Area Elective
Language of instruction: Turkish
Mode of delivery: Face to face
Pre- and co-requisites: None
Professional practice: No
Purpose of the course: This course aim to teach different machine learning approaches by their theoretical aspects and implementation of these approaches. It covers theory and implementations of these topics: probability distiributions, Bayes decision theory, parameter estimation, dimension reduction metods, classifications algorithms, artificial neural networks, and reinforcement learning.
   Learning outcomes Up

Upon successful completion of this course, students will be able to:

  1. Manipulate the terminology in classification, regression, and clustering.

    Contribution to Program Outcomes

    1. Apply the mathematical, scientific and engineering knowledge for real life problems
    2. Formulate and solve engineering problems
    3. Find out new methods to improve his/her knowledge
    4. Employ modern techniques and operate technical devices

    Method of assessment

    1. Written exam
    2. Homework assignment
  2. Explain the theory of different machine learning approaches

    Contribution to Program Outcomes

    1. Apply the mathematical, scientific and engineering knowledge for real life problems
    2. Formulate and solve engineering problems
    3. Develop awareness for the problems in the field of Electronics Engineering and apply knowledge for the welfare of society

    Method of assessment

    1. Written exam
    2. Homework assignment
  3. Gain the necessary theoretical knowledge and coding skills required to solve real world problems

    Contribution to Program Outcomes

    1. Design and conduct experiments, as well as analyze and interpret data
    2. Formulate and solve engineering problems

    Method of assessment

    1. Homework assignment
    2. Term paper
   Contents Up
Week 1: Introduction of basic terminology in machine learning. Definitions of big data, classification, deep learning, supervised and unsupervised learning.
Week 2: Probability distributions. Moments and Gauss distributions. State vectors and multivariate distributions. Example solution and coding.
Week 3: Parameter estimation. Likelihood function. Bayesian classification. Naive Bayes classifiers. Example solution and coding. Homework 1: Naive Bayes classifiers.
Week 4: Dimension reduction. PCA, LDA, SVD, matrix factorization. Isomap. Example solution and coding. Project topics assignment.
Week 5: Unsupervised learning. Clustering. Mixture of distributions. k-means. EM algorithm. Spectral, hierarchical clustering approaches. Determining the number of clusters. Example solution and coding. Homework 2: Dimension reduction and clustering.
Week 6: Nonparametric approaches. Histograms. Kernel approaches. k-nn. Anomaly detection. Example solution and coding.
Week 7: Midterm. Decision trees. Classification and regression trees. Example solution and coding.
Week 8: Support vector machines. Example solution and coding. Homework 3: Decision trees.
Week 9: Bayesian prediction. Hypothesis testing. Example solution and coding.
Week 10: Ensemble classifiers. Example solution and coding. Homework 4: Classification algorithms.
Week 11: Linear discriminators. Multi-class discrimination. Gradient descent and parameter estimation. Example solution and coding.
Week 12: Introduction to artificial neural networks. Peceptron. Multi-layer perceptrons. Homework 5: Artificial neural network.
Week 13: Activation functions. Backpropagation. Deep learning. Example solution and coding.
Week 14: Reinforcement learning. Project presentations.
Week 15*: -
Week 16*: Final exam.
Textbooks and materials: E. Alpaydin, Introduction to Machine Learning. MIT, 2014.
Recommended readings: R. O. Duda, P. E. Hart, ve D. G. Stork, Pattern Classification. Wiley, 2000.
  * Between 15th and 16th weeks is there a free week for students to prepare for final exam.
Assessment Up
Method of assessment Week number Weight (%)
Mid-terms: 7 20
Other in-term studies: - 0
Project: 4- 14 25
Homework: 3,5,8,10,12 25
Quiz: - 0
Final exam: 16 30
  Total weight:
(%)
   Workload Up
Activity Duration (Hours per week) Total number of weeks Total hours in term
Courses (Face-to-face teaching): 3 14
Own studies outside class: 3 14
Practice, Recitation: 0 0
Homework: 4 5
Term project: 16 1
Term project presentation: 1 1
Quiz: 0 0
Own study for mid-term exam: 12 1
Mid-term: 1 1
Personal studies for final exam: 14 1
Final exam: 2 1
    Total workload:
    Total ECTS credits:
*
  * ECTS credit is calculated by dividing total workload by 25.
(1 ECTS = 25 work hours)
-->