Home/ Majors directory/Computer Sciences (Artificial Intelligence)/Associative and Network Analysis
Associative and Network Analysis
Major: Computer Sciences (Artificial Intelligence)
Code of subject: 6.122.13.O.035
Credits: 5.00
Department: Artificial Intelligence Systems
Lecturer:
R.Ya.Kosarevych
Semester: 7 семестр
Mode of study: денна
Завдання: The study of an academic discipline involves the formation and development of students' competencies:
Integral competence (INT):
The ability to use in-depth theoretical and fundamental knowledge in information technology and artificial intelligence to effectively solve complex, specialized tasks and practical problems during professional activity or in the learning process, which involves their application to the development of complex systems characterized by complexity and uncertainty of conditions.
General competences (CG):
1. the ability to communicate in a second language;
2. the ability to learn;
3. ability to communicate orally and in writing in the first language;
4. the ability to search and analyze information from various sources;
5. the ability to identify, formulate and solve problems;
6. ability to apply knowledge in practical situations;
7. ability to make informed decisions;
8. ability to conduct research at the appropriate level;
9. ability to work in a team;
10. knowledge and understanding of the subject area and experience of the profession;
11. ability to think abstractly, analyze and synthesize;
12. ability to develop and manage projects;
13. ability to work independently.
Professional competences of the speciality (FC):
1. the ability of a flexible way of thinking, which makes it possible to understand and solve problems and tasks while maintaining a critical attitude to established scientific concepts;
2. the ability to use in-depth theoretical and fundamental knowledge in the field of artificial intelligence to develop complex systems;
3. the ability to conduct an oral presentation and write an understandable article based on the results of the conducted research, as well as on modern concepts in artificial intelligence systems and natural language processing methods;
4. the ability to formulate (making presentations or presenting reports) new hypotheses and scientific problems in the field of artificial intelligence and natural language processing, to choose appropriate directions and appropriate methods for their solution;
Learning outcomes: 1. The ability to formulate and improve a significant research problem, collect the necessary information for its solution, and develop conclusions that can be defended in a scientific context.
2. The ability to use professional knowledge and practical skills to optimize the design of information systems of any complexity to solve specific tasks of designing intelligent information systems for managing objects of different physical natures.
3. The ability to evaluate existing technologies and, based on the analysis, form requirements for developing promising information technologies.
4. The ability to carry out practical communication activities of the information system project development team.
5. The ability to work with the expert and textual sources of information to integrate data and knowledge in the organization's activities using methods of knowledge acquisition, presentation, classification and compilation of knowledge.
Required prior and related subjects: Intelligent data analysis
Machine learning
Designing deep learning systems
Management of project execution processes
Software systems design engineering
Data and knowledge engineering methods and tools
Summary of the subject: The educational discipline "Image processing by methods of artificial intelligence" is a component of the cycle of professional training of specialists of the second academic and qualification level "master". The proposed educational course will provide students with the acquisition of in-depth theoretical and practical knowledge, skills and understanding related to the areas of artificial intelligence systems, which will allow them to effectively perform tasks of an innovative nature at the appropriate level of professional activity, which is oriented to research and solving complex design problems and development of image analysis information systems to meet a wide range of needs of science, business and enterprises in various fields.
Опис: Introduction
Psychophysical properties of vision. Discretization and quantization of continuous images. Mathematical description of discrete embodiments.
Image processing and analysis systems
Image analysis systems solve the main task. Pre-processing of images: image filtering and restoration.
Preliminary image analysis
Image segmentation and clustering. Statement of the problem of cluster analysis. Hierarchical and non-hierarchical clustering algorithms: k-means and Fuzzy C-Means algorithms. Segmentation of images using the selection of homogeneous regions. Image segmentation based on boundary selection.
Recognition of images and images
Classification of images using the distance function. Variety of images using the likelihood function.
Image classifiers. Deterministic and statistical approaches. Pre-processing of images and feature selection. Syntactic pattern recognition.
Methods and means of artificial intelligence for image analysis
The architecture of neural networks. Deep learning (Deep Learning). Convolutional and recurrent neural networks. The architecture of convolutional neural networks, convolutional layers, subsampling and fully connected.
Image filtering methods using artificial neural networks
Application of convolutional neural networks for image noise removal.
Methods of preliminary image analysis using artificial neural networks
Segmentation of multispectral images using artificial neural networks
Features of visual image recognition using convolutional neural networks.
Application of convolutional neural networks in pattern recognition tasks
Assessment methods and criteria: - current control (40%): written reports on laboratory work, oral examination;
- final control (50% of exam), writing (50%), oral component (10%).
Критерії оцінювання результатів навчання: Laboratory works - 30 points
Calculated graphic work - 15 points
The written component of the exam - 40 points
Oral component of the exam - 15 points
Порядок та критерії виставляння балів та оцінок: 100-88 points - certified with an “excellent” grade - High level: the student demonstrates an in-depth mastery of the conceptual and categorical apparatus of the discipline, systematic knowledge, skills and abilities of their practical application. The mastered knowledge, skills and abilities provide the ability to independently formulate goals and organize learning activities, search and find solutions in non-standard, atypical educational and professional situations. The applicant demonstrates the ability to make generalizations based on critical analysis of factual material, ideas, theories and concepts, to formulate conclusions based on them. His/her activity is based on interest and motivation for self-development, continuous professional development, independent research activities, implemented with the support and guidance of the teacher. 87-71 points - certified with a grade of “good” - Sufficient level: involves mastery of the conceptual and categorical apparatus of the discipline at an advanced level, conscious use of knowledge, skills and abilities to reveal the essence of the issue. Possession of a partially structured set of knowledge provides the ability to apply it in familiar educational and professional situations. Aware of the specifics of tasks and learning situations, the student demonstrates the ability to search for and choose their solution according to the given sample, to argue for the use of a particular method of solving the problem. Their activities are based on interest and motivation for self-development and continuous professional development. 70-50 points - certified with a grade of “satisfactory” - Satisfactory level: outlines the mastery of the conceptual and categorical apparatus of the discipline at the average level, partial awareness of educational and professional tasks, problems and situations, knowledge of ways to solve typical problems and tasks. The applicant demonstrates an average level of skills and abilities to apply knowledge in practice, and solving problems requires assistance, support from a model. The basis of learning activities is situational and heuristic, dominated by motives of duty, unconscious use of opportunities for self-development. 49-00 points - certified with a grade of “unsatisfactory” - Unsatisfactory level: indicates an elementary mastery of the conceptual and categorical apparatus of the discipline, a general understanding of the content of the educational material, partial use of knowledge, skills and abilities. The basis of learning activities is situational and pragmatic interest.
Recommended books: Stephen Marsland. Machine Learning). Лінійна: An Alg). Лінійнаorithmic Perspective, 452 р.,
2015.
Ethem Alpaydin. Introduction To Machine Learning). Лінійна, 584 p., 2009.
Tom M. Mitchell. Machine Learning). Лінійна
[http://www.cs.cmu.edu/~tom/mlbook.html]
Уніфікований додаток: Lviv Polytechnic National University ensures the realization of the right of persons with special educational needs to obtain higher education. Inclusive educational services are provided by the "Without Limits" service of accessibility to learning opportunities, the purpose of which is to provide permanent individual support for the educational process of students with disabilities and chronic diseases. An important tool for the implementation of the inclusive educational policy at the University is the Program for improving the qualifications of scientific and pedagogical workers and educational and support staff in the field of social inclusion and inclusive education.
Contact at:
St. Karpinsky, 2/4, 1st educational building, room 112
E-mail: nolimits@lpnu.ua
Websites: https://lpnu.ua/nolimits https://lpnu.ua/integration
Академічна доброчесність: The policy regarding the academic integrity of participants in the educational process is formed on the basis of compliance with the principles of academic integrity, taking into account the norms "Regulations on academic integrity at the Lviv Polytechnic National University" (approved by the academic council of the university on June 20, 2017, protocol No. 35).