Implementation Issues of Kohonen Self-Organizing Map Realized on FPGA
نویسندگان
چکیده
Presented are the investigations showing an impact of the length of data signals in hardware implemented Kohonen Self-Organizing Maps (SOM) on the quality of the learning process. The aim of this work was to determine the allowable reduction of the number of bits in particular signals that does not deteriorate the network behavior. The efficiency of the learning process has been quantified by using the quantization error. The results obtained for the SOM realized on Field Programmable Gate Array (FPGA), as well as by means of the software model of the SOM show that the smallest allowable resolution (expressed in bits) of the weight signals equals seven, while the minimal bit length of the neighborhood signal ranges from 3 to 6 (depending on the map topology). For such values and properly selected values of other parameters the learning process remains undisturbed. Reducing the number of bits has an influence on the number of neurons that can be synthesized on a single FPGA device.
منابع مشابه
An accelerator for Kohonen Self-Organizing Maps
In this work we are describing hardware implementation of Kohonen SelfOrganizing Map. We examined existing neurocomputers and decided to work out our own neurocomputer with a different, more suitable architecture. Our neurocomputer is being realized on FPGA (Field-Programmable Gate Array). In this article we are describing basic neurocomputer unit structure as well as linkage of these elements ...
متن کاملKohonen Self Organizing for Automatic Identification of Cartographic Objects
Automatic identification and localization of cartographic objects in aerial and satellite images have gained increasing attention in recent years in digital photogrammetry and remote sensing. Although the automatic extraction of man made objects in essence is still an unresolved issue, the man made objects can be extracted from aerial photos and satellite images. Recently, the high-resolution s...
متن کاملDesign, Implementation, and Test of a Multi-Model Systolic Neural-Network Accelerator
A multi-model neural network computer has been designed and realized. A compute intensive application using the Kohonen self-organizing map, in the eld of power system monitoring , has been ported onto the neu-ral machine. The system is described and its performance is evaluated and discussed.
متن کاملA Scalable Digital Architecture of a Kohonen Neural Network
Kohonen self-organizing feature maps are unsupervised learning neural networks that categorize or classify data. Efficient hardware implementation of such neural networks requires the definition of a certain number of simplifications to the original algorithm. In particular, multiplications should be avoided by means of simplifications in the distance metric, the neighborhood function and the l...
متن کاملFPGA Based System for Human Chromosome Classification
Computer-aided systems based on artificial neural networks (ANN) are suitable for automatic chromosome classification process. However, the software based implementation of these systems running on conventional computer transforms the parallelism features of the ANN into serial operations that reduce their computation power. The hardware implementation of such system can achieve the parallelism...
متن کامل