Courses – Fakultet tehničkih nauka u Novom Sadu

Subject: Deep learning and biologically inspired machine learning (17.IISD11)

Type of studies	Title
Doctoral Academic Studies	Information Systems Engineering (Year: 2, Semester: Winter)
Doctoral Academic Studies	Mathematics in Engineering (Year: 1, Semester: Winter)
Doctoral Academic Studies	Industrial Engineering / Engineering Management (Year: 2, Semester: Winter)
Doctoral Academic Studies	Mathematics in Engineering (Year: 2, Semester: Winter)

General information:

Category	Scientific-professional
Scientific or art field	Inženjerstvo informacionih sistema Applied Computer Science and Informatics Information-Communication Systems
ECTS	10

The course is technology oriented and designed to provide an overview of the state-of-the-art in machine learning to the doctoral students, who need to have basic knowledge of information technology and artificial intelligence, mathematics or a related field. The emphasis is on the biologically inspired approaches, neural networks and deep learning. Upon completion of the course the students will gain theoretical knowledge and practical skills, which will allow them to apply the technology in question to analyze big multimodal data and embark on research projects in the area of machine learning, data science and artificial intelligence applications in their primary research areas.

Upon completion of the course the students will gain theoretical knowledge and practical skills, which will allow them to apply the technology in question to analyze big multimodal data and embark on research projects in the area of machine learning, data science and artificial intelligence applications in their primary research areas. Throughout the course they will be given a chance to take part in ongoing research projects, experiments and preparation of the results for publication. By the end of the course the students should have a draft of a scientific publication ready for submission to a relevant international scientific conference.

The course will cover the following topics: advanced concepts of I and II generation neural networks, Deep Learning and applications of deep neural networks to the problem of analyzing large amounts of multimodal data, data representation (coding) in neuromorphic systems, basic and advanced methods of supervised and unsupervised learning in these systems. The theory will be accompanied with practical training in developing and training machine learning systems in the Caffe, Tensorflow and PyTorch environments, as well as by research work training. The students will take an active role in the research projects conducted at the faculty, design and conduct experiments, as well as prepare their results for publication.

Lectures and labs, seminar paper, supervised research work and an oral exam.