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.
|Title of host publication||Proceedings of KES2003 vol. II|
|Editors||Vasile Palade, Robert J. Howlett, Lakhmi Jain|
|Place of Publication||Oxford, UK|
|Number of pages||8|
|Publication status||Published - Sep 2003|
|Name||Lecture Notes in Computer Science|
van der Zwaag, B. J., Slump, C. H., & Spaanenburg, L. (2003). On the analysis of neural networks for image processing. In V. Palade, R. J. Howlett, & L. Jain (Eds.), Proceedings of KES2003 vol. II (pp. 950-957). (Lecture Notes in Computer Science; Vol. 2774). Oxford, UK: Springer. https://doi.org/10.1007/978-3-540-45226-3_130, https://doi.org/10.1007/b12003