Introduction to artificial neural networks WF-R-PS-WWS
1. Introduction. Basic information about artificial neural networks
2. Structure of artificial neural networks
3. Teaching artificial neural networks
4. Artificial linear and non-linear neural networks
5. Backward propagation of errors in artificial neural networks
6. Types of artificial neural networks
7. The accuracy of prediction of artificial neural networks
8. Crediting. Test
(in Polish) E-Learning
(in Polish) Grupa przedmiotów ogólnouczenianych
Subject level
Learning outcome code/codes
Type of subject
Course coordinators
Learning outcomes
Knowledge - the student has basic knowledge of artificial neural networks, their structure, learning methods, types.
Competences and skills - the student can interpret the results of artificial neural networks.
ECTS:
participation in classes - 15 hours
preparation for classes - 7.5 hours
preparation for the test - 7.5 hours
ECTS NUMBER - 1
Assessment criteria
Colloquium in the form of a knowledge test. Passing with a satisfactory grade from 60%.
Bibliography
Elder, J., Hill, T., Miner, G., Nisbet, B., Delen, D., & Fast, A. (2012). Practical Text Mining and Statistical Analysis for Nono-structured Text Data Application. Oxford: Elsevier.
Nisbet, R., Elder, J., & Miner, G. (2009). Handbook of statistical analysis and data mining applications. Burlington, MA: Academic Press (Elsevier).
Tadeusiewicz, R. (2007). Odkrywanie właściwości sieci neuronowych. Kraków: Polska Akademia Umiejętności.
Additional information
Additional information (registration calendar, class conductors, localization and schedules of classes), might be available in the USOSweb system: