
Data Science
Advanced Machine Learning Methods
- Class 15
- Practice 30
- Independent work 120
Course title
Advanced Machine Learning Methods
Lecture type
Obligatory
Course code
20-02-064
Semester
3
ECTS
6
Lecturers and associates
Course objectives
Deep learning is today the most important machine learning method used in the world's most important production systems for various tasks. Through this course, we will present and implement basic deep learning techniques on examples from natural language processing such as machine translation, sentiment analysis, and recognition of named entities. Also, the course will handle awarded learning. The course objective is to enable students to deepen their understanding of mathematics and algorithms of deep neural architecture and deep learning, as well as acquire practical knowledge to implement deep learning. Students will acquire the skills of designing deep architecture in TensorFlow, as well as hand-made deep neural networks that can be implemented later in any programming language.
Content
Introduction to deep learning. Perceptron. Logistic Regression. Artificial neural networks. Stochastic gradient descent. Regularization. Convolutional neural networks. Autoencoders. Recurrent neural networks. Neural language models. Trends and future.
Required reading
S.Skansi 2018. Introduction to Deep Learning. Springer
Additional reading
Goodfellow, I., Bengio, Y. i Courville, A. 2016. Deep Learning (Adaptive Computation and Machine Learning series). Cambridge: MIT Press
https://arxiv.org/abs/1609.08144
- Study program duration
- 4 semesters (2 years)
- Semester duration
- 15 weeks of active teaching + 5 examination weeks
- Total number of ECTS points
- 120
- Certifications obtained during studies
-
IT SMF – ITIL Foundation
- Title
- struč.spec.ing.comp. (Professional Master of Computer Engineering with sub-specialization in Data Science)
Minimal learning outcomes
- Understand how basic deep learning algorithms work
- Describe the flow of data through an artificial neuron
- Evaluate the impact of different depth architectures on the speed of calculation
- Analyze the results of deep learning over the data
Preferred learning outcomes
- Judge which algorithm is best for a particular problem
- Critically evaluate changes in information during passage through artificial neuron
- Evaluate the influence of different components of deep neural architecture
- Directly apply the selected depth architecture to the problems of natural language processing and computer vision
Excel at what you love doing. Light the spark.
Apply now!Why is Algebra a safe choice for your future?

A Strong
Tailwind
Here you will learn all about information technologies and prepare for a career that is constantly in demand. We offer you a platform for personal growth that makes you a prime target for employers.
Modern Methodology
We refuse to stand still in a rapidly changing world. Our programs stay relevant and keep up with modern trends.
Matchless Quality
We take pride in numerous accolades and our title of The best professional study program in Croatia and constantly strive to justify that trust. We do not take our task lightly, knowing that your future depends on it.