548-0135/01 – Basics in Artificial Intelligence in GIS (AIGIS)
Gurantor department | Department of Geoinformatics | Credits | 5 |
Subject guarantor | Ing. Lucie Orlíková, Ph.D. | Subject version guarantor | Ing. Lucie Orlíková, Ph.D. |
Study level | undergraduate or graduate | Requirement | Compulsory |
Year | 3 | Semester | summer |
| | Study language | Czech |
Year of introduction | 2021/2022 | Year of cancellation | |
Intended for the faculties | HGF | Intended for study types | Bachelor |
Subject aims expressed by acquired skills and competences
The student demonstrates knowledge of:
- fundamental concepts of statistics and geostatistics
- fundamental concepts of neural networks
- basic Concepts of Python Programming
- spatial exploratory data analysis
- Basic Concepts of R Programming
The student can:
- select AI methods and use it for prediction
- apply the introduced methods of data processing
- interpret the results obtained
The student is able to:
- orientate in the issue of neural networks
- critically interpret foreign solutions based on neural networks
- explain the problems of neural networks
- choose a suitable method for the given issue
Teaching methods
Lectures
Tutorials
Summary
The aim of the course is to acquaint students with the basics of neural network theory. The student will learn not only the basic theory, but they will be able to solve complex tasks. Students will also expand their knowledge of statistics and spatial analysis.
Compulsory literature:
Recommended literature:
Way of continuous check of knowledge in the course of semester
Students are asked about knowledge from areas that they should have already known from previous lectures. They also work on individual tasks. Written and oral exam.
E-learning
Other requirements
No additional requirements are imposed on the student.
Prerequisities
Subject has no prerequisities.
Co-requisities
Subject has no co-requisities.
Subject syllabus:
1. Introduction, major topics, context, history, and GIS applications of AI.
2. Exploratory spatial data analysis, introduction to statistical learning theory.
3. Support vector machine: classification and regression, cluster analysis, supervised and unsupervised learning.
4. Decision-trees algorithms: rule learning.
5. Logic and machine learning: specialization, generalization, logical consequence.
6. Verification of learning outcomes: training and test dataset, re-learning, cross-validation, confusion matrices, learning curve.
7. Linear regression, ordinary least square regression modelling.
8. Kernel methods for pattern analysis, kernel transformation.
9. Artificial neural networks: multilayer perceptron, backpropagation method.
10. Cluster analysis: k-nearest neighbours algorithm, hierarchical clustering.
11. Support vector machine. Data preprocessing: selection of attributes, construction of new attributes, sampling methods.
12. Support vector machine. Verification and validation of results.
13. Probabilistic neural network: Bayesian neural network.
Conditions for subject completion
Occurrence in study plans
Occurrence in special blocks
Assessment of instruction
Předmět neobsahuje žádné hodnocení.