One kind of steepest descent incremental projection learning algorithm for improving the training of radial basis function(RBF)neural network is proposed,which is applied to analog circuit fault isolation.This algorit...One kind of steepest descent incremental projection learning algorithm for improving the training of radial basis function(RBF)neural network is proposed,which is applied to analog circuit fault isolation.This algorithm simplified the structure of network through optimum output layer coefficient with incremental projection learning(IPL)algorithm,and adjusted the parameters of the neural activation function to control the network scale and improve the network approximation ability.Compared to the traditional algorithm,the improved algorithm has quicker convergence rate and higher isolation precision.Simulation results show that this improved RBF network has much better performance,which can be used in analog circuit fault isolation field.展开更多
Flash memory is widely used in embedded de- vices and enterprise storage systems. Currently, flash-based storage devices usually use a flash translation layer （FFL） to cope with the special features of flash memory....Flash memory is widely used in embedded de- vices and enterprise storage systems. Currently, flash-based storage devices usually use a flash translation layer （FFL） to cope with the special features of flash memory. Many meth- ods for the design and implementation of the FTL have been proposed, such as BAST （block-associative sector transla- tion）, FAST （fully associative sector translation）, and IPL （in- page logging）, of which IPL has been demonstrated to have the best performance. However, IPL offers little considera- tion to reducing merge operations that consequently result in the degradation of the overall performance of flash-memory storage systems. We propose an improvement to IPL, called adaptive IPL （AIPL）. The idea of adaptive IPL is to make the log region in a block resizable, therefore a hot block （i.e., a write-intensive block） will use a large log region so as to absorb more page updates and in turn reduce the merge op- erations, while a cold block, i.e., a block rarely written to, will use a small log region. This is realized by first detecting the update pattern of a block and then presenting an update- pattern-based algorithm to dynamically adjust the log region size of a newly allocated block. We conduct experiments on TPC-C traces and synthetic traces and compare the perfor- mance of AIPL with other competitors in terms of merge count, write count and elapsed time. The results demonstrate that compared with IPL, AIPL can reduce merge operations by 65% and write operations by 54% on average.展开更多
基金Pre-research Projects Fund of the National Ar ming Department,the 11th Five-year Projects
文摘One kind of steepest descent incremental projection learning algorithm for improving the training of radial basis function(RBF)neural network is proposed,which is applied to analog circuit fault isolation.This algorithm simplified the structure of network through optimum output layer coefficient with incremental projection learning(IPL)algorithm,and adjusted the parameters of the neural activation function to control the network scale and improve the network approximation ability.Compared to the traditional algorithm,the improved algorithm has quicker convergence rate and higher isolation precision.Simulation results show that this improved RBF network has much better performance,which can be used in analog circuit fault isolation field.
文摘Flash memory is widely used in embedded de- vices and enterprise storage systems. Currently, flash-based storage devices usually use a flash translation layer （FFL） to cope with the special features of flash memory. Many meth- ods for the design and implementation of the FTL have been proposed, such as BAST （block-associative sector transla- tion）, FAST （fully associative sector translation）, and IPL （in- page logging）, of which IPL has been demonstrated to have the best performance. However, IPL offers little considera- tion to reducing merge operations that consequently result in the degradation of the overall performance of flash-memory storage systems. We propose an improvement to IPL, called adaptive IPL （AIPL）. The idea of adaptive IPL is to make the log region in a block resizable, therefore a hot block （i.e., a write-intensive block） will use a large log region so as to absorb more page updates and in turn reduce the merge op- erations, while a cold block, i.e., a block rarely written to, will use a small log region. This is realized by first detecting the update pattern of a block and then presenting an update- pattern-based algorithm to dynamically adjust the log region size of a newly allocated block. We conduct experiments on TPC-C traces and synthetic traces and compare the perfor- mance of AIPL with other competitors in terms of merge count, write count and elapsed time. The results demonstrate that compared with IPL, AIPL can reduce merge operations by 65% and write operations by 54% on average.
