Abstract
This paper illustrates a novel method to analyze artificial neural networks so as to gain insight into their internal functionality. To this purpose, we will show analysis results of some feed-forward-error-back-propagation neural networks for image processing. We will describe them in terms of domain-dependent basic functions, which are, in the case of the digital image processing domain, differential operators of various orders and with various angles of operation. Some other pixel classification techniques are analyzed in the same way, enabling easy comparison.
Original language | English |
---|---|
Title of host publication | Knowledge-Based Intelligent Information and Engineering Systems |
Subtitle of host publication | 7th International Conference, KES 2003 Oxford, UK, September 3–5, 2003 Proceedings, Part II |
Editors | Robert J. Vasile Palade, Lakhmi Jain Howlett |
Place of Publication | Heidelberg |
Publisher | Springer Nature |
Pages | 950-957 |
Number of pages | 8 |
ISBN (Electronic) | 978-3-540-45226-3 |
ISBN (Print) | 978-3-540-40804-8 |
DOIs | |
Publication status | Published - 2003 |
Externally published | Yes |
Event | Knowledge-Based Intelligent Information and Engineering Systems: 7th International Conference - Oxford, United Kingdom Duration: 3 Sept 2003 → 5 Sept 2003 |
Conference
Conference | Knowledge-Based Intelligent Information and Engineering Systems |
---|---|
Abbreviated title | KES 2003 |
Country/Territory | United Kingdom |
City | Oxford |
Period | 3/09/03 → 5/09/03 |
Keywords
- image processing
- neural network