Đang chuẩn bị liên kết để tải về tài liệu:
Báo cáo hóa học: " Research Article A CNN-Specific Integrated Processor Suleyman Malki and Lambert Spaanenburg (EURASIP Member)"

Tuyển tập báo cáo các nghiên cứu khoa học quốc tế ngành hóa học dành cho các bạn yêu hóa học tham khảo đề tài: Research Article A CNN-Specific Integrated Processor Suleyman Malki and Lambert Spaanenburg (EURASIP Member) | Hindawi Publishing Corporation EURASIP Journal on Advances in Signal Processing Volume 2009 Article ID 854241 14 pages doi 10.1155 2009 854241 Research Article A CNN-Specific Integrated Processor Suleyman Malki and Lambert Spaanenburg EURASIP Member Department of Electrical and Information Technology Lund University P.O. Box 118 22100 Lund Sweden Correspondence should be addressed to Suleyman Malki suleyman.malki@gmail.com Received 2 October 2008 Accepted 16 January 2009 Recommended by David Lopez Vilarino Integrated Processors IP are algorithm-specific cores that either by programming or by configuration can be re-used within many microelectronic systems. This paper looks at Cellular Neural Networks CNN to become realized as IP. First current digital implementations are reviewed and the memoryprocessor bandwidth issues are analyzed. Then a generic view is taken on the structure of the network and a new intra-communication protocol based on rotating wheels is proposed. It is shown that this provides for guaranteed high-performance with a minimal network interface. The resulting node is small and supports multi-level CNN designs giving the system a 30-fold increase in capacity compared to classical designs. As it facilitates multiple operations on a single image and single operations on multiple images with minimal access to the external image memory balancing the internal and external data transfer requirements optimizes the system operation. In conventional digital CNN designs the treatment of boundary nodes requires additional logic to handle the CNN value propagation scheme. In the new architecture only a slight modification of the existing cells is necessary to model the boundary effect. A typical prototype for visual pattern recognition will house 4096 CNN cells with a 2 overhead for making it an IP. Copyright 2009 S. Malki and L. Spaanenburg. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted .