Courses catalogue | Computer Science Department

Start Page
Postgraduate Studies
Courses Catalogue

Course details

Code

CS-587

Name

Neural Networks and Learning of Hierarchical Representation

Program

Postgraduate

Areas

Βioinformatics, medical informatics, and computational neuroscience

Computer vision and robotics

Signal processing and analysis

Artificial Intelligence and machine learning

(Algorithms and Systems Analysis)

Description

The scientific activity of the last decade revealed many new directions and highly successful extensions of Neural Networks towards learning data representations for various perception systems.
Representations of this kind are composed of many layers of nonlinear calculations (multilayer architectures) and are based on classic artificial neural networks. In recent years it has become evident that learning such multilayered representations can contribute to a significant improvement in perception systems performance. The purpose of this course is to present an introduction to artificial neural networks and in learning hierarchical representations based on those network structures. The course will focus on architectures, methodologies and algorithms, and will also include laboratory exercises

LEARNING OUTCOMES

1. Knowledge: Having attended and succeeded in the course, the student is able to describe how problems requiring the application of deep learning methods are addressed in recent literature.
2. Understanding: Having attended and succeeded in the course, the student has achieved an in-depth understanding of neural network training algorithms and the different architectures that can be employed.
3. Application: Having attended and succeeded in the course, the student can reuse existing deep learning methodologies and tools to solve a wide range of problems from various research areas.
4. Analysis: Having attended and succeeded in the course, the student can critically assess specific problems and perceive them as compositions of a series of individual sub-problems.
5. Synthesis: Having attended and succeeded in the course, the student can combine individual tools and methodologies to achieve the solution of complex machine learning problems.
6. Evaluation: Having attended and succeeded in the course, the student can quantitatively measure the quality of neural networks resulting from training and compare their results with other existing ones.

STUDENT PERFORMANCE EVALUATION
Class attendance/participation
Exercises/projects
Oral/written exams

ECTS

Prerequisites

CS-217, CS-119 or Μ-105

Courses catalog

A+

A-

Offered Postgraduate Cousres
Code	Course Name	ECTS(ΔΜ)	Prerequisites	Suggested	Areas
CS-500	Introduction to Research	2	--
CS-508	Technical Writing in English	4	--
CS-523	Digital Systems CAD Laboratory	6	CS-220, CS-225		A, A1
CS-527	Parallel Computer Architecture	6	CS-345, CS-425		A, A1, A2, Γ
CS-529	Multicore Architecture Programming	6	CS-345, HY425		A, A2, B1, B2, Γ
CS-531	Topics in Information theory	6	N/A		B, B2, B4
CS-533	Introduction to Research on Computer Networks	6	CS-335		A3, A4, B
CS-534	Packet Switch Architecture	6	CS-225, CS-335		A, A1, A4, B
CS-539	Advanced Topics on Wireless Networks and Mobile Systems	6	CS-335, CS-345		A4, B, Γ
CS-540	Advanced Topics in Programming Languages Development	6	CS-340		B1, B3, Z, Δ
CS-541	Wireless Sensor Networks	6	CS-335, CS-215		B, C1, Θ
CS-543	Software Systems and Technologies for Big Data Applications	6	CS-360, CS-252,or instructor permission.		B2, B4, Γ, Δ
CS-546	Types and Programming Languages	6	CS-255, CS-280		A2, B1, B3, Z, Γ, Δ
CS-548	Cloud-native Software Architectures	6	CS-335, CS-345		A2, Γ
CS-553	Interactive Computer Graphics	6	CS-358		C3, E, Δ, Θ
CS-558	Internet Technologies and Systems	6	CS-345		A3, A4, B, Γ, Δ
CS-559	Infrastructure Technologies for Large-Scale Service-Oriented Systems	6	CS-345, CS-360		A2, A3, B2, H, Γ, Δ
CS-561	Web Data Management	6	CS-460		B2, C3, Δ
CS-562	Advanced Database Topics	6	CS-360		B2, Δ
CS-563	Advanced Topics in Information Retrieval Systems	6	CS-463		B2, B4, Δ
CS-565	Process Management Systems	6	CS-360	CS-460	A3, A4, B1, H, Δ, Θ
CS-567	Knowledge Representation and Reasoning	6	CS-380, CS-387		B2, B4, Δ, Θ
CS-569	Human – Computer Confluence	6	CS-364	CS-359, CS-469	C3, H, Δ, Θ
CS-570	Statistical Signal Processing	6	CS-370, CS-217		B, B4, C1, C2, E, Θ
CS-573	Optimization Methods	6	CS-110, CS-119		B4, C2, E, Z
CS-575	Robotic Navigation Laboratory	6	CS-475		C2, E
CS-577	Machine Learning	6	CS-150, CS-217, CS-380		B4, C1, C2, C4, E, H, Z, Δ
CS-578	Voice Processing	6	CS-370		B, C1, Θ
CS-580	Topics in Algorithm Design	6	CS-240, CS-280, CS-380		B1, C4, Z
CS-583	Graph Algorithms	6	CS-240, CS-380		B1, C4, Z
CS-586	Distributed Computing	6	CS-380		A3, B1, Z, Γ
CS-587	Neural Networks and Learning of Hierarchical Representation	6	CS-217, CS-119 or Μ-105		B4, C1, C2, C4, Z
CS-588	Brain Network Analysis and Modeling	6	CS-217, CS-215, CS-240		B, B4, C4, H
CS-590.31	IoT for Smart Cities	6	CS-335, CS-150		A4, B, B2, Δ
CS-590.45	Modern Topics in Scalable Storage Systems	6	CS-345, CS-360		A3, B2, Γ
CS-590.72	Introduction to Bioinformatics for Computer Scientists	3	Basic knowledge in the areas of theoretical computer science (algorithms, data structures) and technical computer science (sequential optimization in C or C++, computer architectures, parallel programming, vector processors) is required.		C4, H
CS-590.73	Seminar in Reproducibility in Bioinformatics	3	CS-590.72		C4, H
CS-647	Modern Storage Systems	6	CS-345		A2, B2, Γ
CS-672	Advanced Topics in Computational Vision	6	CS-472		B4, C2, C3, E
CS-673	Introduction to Deep Generative Modelling	6	CS-217, CS-119		B4, C2, E, Z, Θ
CS-690.1-4	Teaching Assistantship	3	--
CS-693	Introduction to Game Theory	6			B, B1, B4, Z
CS-695	Supervised Personal Study	3	--
CS-697	Bibliographic Search	15
CS-698	Assessment of Research Direction and Development of a Research Plan	15
CS-699	Research for M.Sc. Thesis	30
CS-700	Seminar Courses	3	--