CMP712 - Machine Learning

Spring 2026

Instructor: Assoc. Prof. Dr. Hacer Yalım Keleş

Email: hacerkeles@cs.hacettepe.edu.tr

Lectures: Wednesday, 09:40-12:30

Room: D5

Communication: Course Piazza Page

Prerequisites:

Programming (Python)
Basic Probability
Linear Algebra

Reference Textbooks:

Pattern Recognition and Machine Learning, Christopher M. Bishop, Springer (2006) (PRML: available online)
Pattern Classification, R. O. Duda, P. E. Hart, D. G. Stork, (Second Edn.)
Deep Learning, I. Goodfellow, Y. Bengio, A. Courville, MIT Press 2016 (available online)

Aim:

This graduate level lecture provides the theoretical foundations of the various machine learning models and algorithms together with the related literature. In this context, we will study the basics of statistical machine learning, including Bayesian Decision Theory, Maximum Likelihood Estimation, dimension reduction, basic supervised and unsupervised learning algorithms and optimization algorithms; with discussions on capacity, overfitting, underfitting problems and bias-variance issues. Following the basics, we will also study modern practices of deep networks, including deep feedforward networks and convolutional neural networks.

Content Summary:

Supervised Learning: regression, linear models of classification, perceptrons, support vector machines (SVMs), LDA, logistic regression, decision trees (bagging, boosting), neural networks, convolutional neural networks, recurrent neural networks, boosting, nearest neighbor search,
Unsupervised Learning: density estimation (Parzen windows, kNN), dimensionality reduction (PCA), Clustering, Autoencoders

Tentative Schedule

Weeks	Topics	Important Dates
1-(18.02.2026)	Overview of Machine Learning
2-(25.02.2026)	Linear Regression, Least Squares
3-(04.03.2026)	Basics of Linear Discriminants	Project Proposal Due
4-(11.03.2026)	Perceptron Learning
5-(18.03.2026)	Logistic Regression: Binary and Multinomial Classification Formulations
6-(25.03.2026)	SVMs and Kernel Trick Decision Trees
7-(01.04.2026)	Decision Trees	Progress Report1 Due
8-(08.04.2026)	Midterm exam I	* EXAM *
9-(15.04.2026)	Feed Forward Neural Networks, Backpropagation Algorithm
10-(22.04.2026)	Convolutional Neural Networks, Latest Architectures
11-(29.05.2026)	Recurrent Neural Networks
12-(06.05.2026)	Unsupervised Learning in Neural Networks (Autoencoders, VAE, GANs)	Progress Report2 Due
13-(13.05.2026)	Statistical Estimation: MLE, MAP, Naive Bayes Classifier
14-(20.05.2026)	Midterm exam II	* EXAM *
15-(27.05.2026)
16- (03.06.2026)		Term Paper Submission Due

Assessment:

Item	Weight
Midterm Exam I	30%
Midterm Exam II	30%
Research project	40% (Total) Each part constitutes as follows: 5% proposal 5% progress report 8% presentation 7% source codes (well documented) 15% term paper

Research Project:

Select a machine learning problem. Possible application areas: computer vision, speech recognition, NLP etc.
Find a reference paper from the recent literature (papers published since 2023). There are some constraints in the paper selection:

The selected model must be a deep learning based model
The selected paper must be cited by at least 20 papers.
Everyone needs to pick a different paper.

Read and understand your reference paper and the related literature.
Implement the selected approach (maybe only a part of it that is related to your project).
During the Finals:

Prepare a term paper (the format of the paper will be provided later)
Submission: Term paper, short video presentation (details will be provided later), and source codes ( .ipynb file of your Jupyter notebook).

Logistics:

All communication and announcements will be posted in the course’s Piazza page. It is mandatory that you enrolled the piazza (link is provided at the top of the page).