Principles of hierarchical neural networks for analysis of multi -images
Abstract
The principles of construction of hierarchical neural networks to solve problems of processing a large volume of video information, particularly for the analysis of stereo- and multi-images in real time. In order to achieve practically acceptable time learning neural net-works is proposed decomposition of a single neural network into subnets based on the authors introduced the principle of "cognitive ability" neurons and hierarchical organization of the architecture.References
Published
2009-09-01
How to Cite
Timofeev, A., & Derin, O. (2009). Principles of hierarchical neural networks for analysis of multi -images. SPIIRAS Proceedings, (10), 160-166. https://doi.org/10.15622/sp.10.11
Section
Articles
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
