Course title

Advanced Machine Learning Methods

Lecture type

Obligatory

Course code

20-02-064

Semester

3

ECTS

6

Lecturers and associates

• Assistant Professor PhD Hrvoje Jerković
• Mladen Fernežir

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