Cyprus International University Course Portal

The course has an overview of discrete time signals and systems. Sampling/Reconstruction
principles both in time and frequency domains. The Z-Transform and its
properties. Structure of discrete time systems; tapped delay or lattice etc.
Digital filter designs. Realization of digital filters (FIR and IIR). The
discrete Fourier and inverse Fourier transforms. The fast Fourier transform
(FFT) and its analysis. Image acquisition, sampling and quantization. Image
enhancement: Spatial and frequency domain techniques. Image restoration:
Inverse, Wiener and mean filtering. Image compression: Compression models.

• Introduction
  to Cryptography Concepts
• Classical
  Encryption Techniques
• Block
  Ciphers and Data Encryption Standart (DES)
• Introduction
  to Finite Fields and Advanced Encryption Standard (AES)
• Introduction
  to Number Theory
• Public
  Key Cryptography and RSA
• Network
  Security Applications and System Security

Course Description: Pattern Recognition is a fundamental area of study within the field of artificial intelligence and machine learning, focusing on the automatic discovery and identification of regularities or patterns in data. This course provides an in-depth exploration of the principles, techniques, and applications of pattern recognition.

Course Objectives:

• To introduce students to the basic concepts and terminology of pattern recognition.
• To familiarize students with various pattern recognition techniques and algorithms.
• To develop students' understanding of the theoretical foundations underlying pattern recognition.
• To enable students to apply pattern recognition techniques to solve real-world problems across diverse domains.
• To provide students with hands-on experience through practical assignments and projects.

Topics Covered:

1. Polynomial Regression Analysis
2. Logistic Regression (binary, categorical and multi-label classifications)
3. Decision Tree
4. Ensemble Learning Methods
5. Support Vector Machines (SVM)
6. Clustering Techniques (Kmeans, SOM)
7. Multi-Layer Perceptron (MLP) - Backpropagation Algorithm 
8. Radial Basis Function Network (RBFN)
9. Recurrent Neural Network (LSTM, GRU, Elman Network, Bi-directional layers)
10. Deep Convoutional Neural Network (DCNN)
11. Transfer Learning

General concepts of
systems. Discrete and continuous systems. Modelling and simulation of systems. State
vari­ables. Event scheduling. Comparison of analytical and simulation modelling
techniques. General structure of a discrete-event simulation system. Probabilistic
aspects of simulation. Simulation languages and software. Statistical models in
simulation. Random number and random variate generation techniques. Queu­ing models
in simulation. Input modelling. Verification and validation of simulation
models. Output (statistical) analysis and representation of simulation results.
Applications of simulation.

Principles of computer network design. Network design and optimization algorithms. Centralized network design, switching node location problems. Application of minimum spanning tree and shortest path algorithms to problems in network design. Static and dynamic routing algorithms. Network reliability analysis in design. Ad-hoc and cellular wireless network design. Topics in computer network performance analysis. Case studies.

In this course, fundamental concepts and applications of information retrieval and natural language processing will be discussed.  Students will gain knowledge on information retrieval (IR) techniques (tf-idf, BM25, etc.), data models (i.e. vector space model, probabilistic models, word2vec, GloVe) for IR, Semantic Web for data representation and retrieval. In addition, students will gain knowledge on theory (i.e. stemming, morphological, syntactic, semantic analysis, etc.) and applications (i.e. document clustering, question answering, sentiment analysis, etc.) of Natural Language Processing (NLP). Furthermore, students will investigate recent trends of deep learning for IR and NLP, such as neural networks, transformers, attention networks, graph convolutional neural networks, LSTM and Bidirectional Encoder Representations from Transformers (BERT). By the end of the course students will learn both theoretical and applications of IR and NLP. In addition, student will choose a topic, and will have hands-on experience by developing a project in a relevant field.