Simulating a large artificial neural network to solve real-world application problems often requires large amounts of computational *** of the algorithm on conventional hardware are rather slow and direct VLSI or spec...
详细信息
Simulating a large artificial neural network to solve real-world application problems often requires large amounts of computational *** of the algorithm on conventional hardware are rather slow and direct VLSI or special purpose hardware implementations are rather *** this paper,it is investigated to simulate a fully connected multilayered feedforword neural network using the backpropagation learning algorithm on a distributed memory multiprocessor *** partitioning and data partitioning schemes and their algorithms are described and the network partitioning method was realized in a ring network topology of transputer *** almost linear acceleration result has been achieved.
A novel approach to obstacle detection using optical flow without recovering range information has been developed. This method can be used for ground vehicles to navigate through man-made roadways or natural outdoor t...
详细信息
The authors have parallelized the AMBER molecular dynamics program for the AP1000 highly parallel computer. To obtain a high degree of parallelism and an even load balance between processors for model problems of prot...
详细信息
The authors have parallelized the AMBER molecular dynamics program for the AP1000 highly parallel computer. To obtain a high degree of parallelism and an even load balance between processors for model problems of protein and water molecules, protein amino acid residues and water molecules are distributed to processors randomly. Global interprocessor communication required by this data mapping is efficiently done using the AP1000 broadcast network, to broadcast atom coordinate data for other processors' reference and its torus network; also for point-to-point communication to accumulate forces for atoms assigned to other processors. Experiments showed that a problem with 41095 atoms is processed 226 times faster with a 512 processor AP1000 than by a single processor.< >
In constructing highly reliable LAN systems, a mechanism that enables every active node to maintain timely and consistent knowledge about the health status of all cooperating nodes can be used as a cornerstone. The au...
详细信息
In constructing highly reliable LAN systems, a mechanism that enables every active node to maintain timely and consistent knowledge about the health status of all cooperating nodes can be used as a cornerstone. The authors consider the case where maintenance of such knowledge is achieved in a decentralized manner and timely and consistent recognition of newly joining nodes is also facilitated. The authors develop an optimal version of H. Kopetz et al.'s (1985) periodic reception history broadcast (PRHB) method. The authors' version enables detection of failures with minimum latency and is called the PRHB with earliest detection (PRHB/ED). This scheme has much shorter latency than the previous PRHB scheme and is yet equally practical in the sense that it does not increase the communication traffic at all, and the complexity of the algorithm for analyzing the observations exchanged among the active nodes is still bounded by a linear function of the number of nodes in the system.< >
Given two subsets S/sub 1/ and S/sub 2/ (not necessarily finite) of R/sup d/ separable by a Boolean combination of N halfspaces, the authors consider the problem of learning the separation function from a finite set o...
详细信息
Given two subsets S/sub 1/ and S/sub 2/ (not necessarily finite) of R/sup d/ separable by a Boolean combination of N halfspaces, the authors consider the problem of learning the separation function from a finite set of examples. The solution consists of a system of N perceptrons and a single consolidator which combines the outputs of the individual perceptrons. The authors show that an off-line version of this problem where the examples are given in a batch, can be solved in time polynomial in the number of examples. The authors also provide an on-line learning algorithm that incrementally solves the problem by suitably training a system of N perceptrons much in the spirit of classical perceptron learning algorithm.< >
Recursive Auto-Regressive (AR) identification algorithms, applied to the study of Heart rate Variability (HRV), allow to investigate transient biological phenomena. Each time the AR parameters are updated, the positio...
详细信息
Recursive Auto-Regressive (AR) identification algorithms, applied to the study of Heart rate Variability (HRV), allow to investigate transient biological phenomena. Each time the AR parameters are updated, the positions of poles must be evaluated in order to quantify frequency and power of spectral peaks by means of a spectral decomposition based on the residual integration method. We describe a recursive method for pole tracking that estimate the new pole positions on the basis of the AR parameters variations, in a more efficient way than traditional factorization algorithms. The method is suitable for an on-line monitoring of traditional HRV parameters, which measure the symphato-vagal balance elicited by the control mechanisms of cardiovascular system.
The AutoRegressive (AR) spectral estimation is implemented in a recursive way with a forgetting factor w both in the classical RLS form, with a constant w value, and in the Fortescue variant with w changing with time,...
详细信息
The AutoRegressive (AR) spectral estimation is implemented in a recursive way with a forgetting factor w both in the classical RLS form, with a constant w value, and in the Fortescue variant with w changing with time, according to the changing characteristics of the signals. The time-variant AR algorithm is here employed, in the study of heart rate and blood pressure variability signals obtained during syncope episodes. The spectral parameters (LF, HF powers, LF/HF ratio), which are able to quantify the sympatho-vagal balance in the assessing of the heart rate and blood pressure values, are evaluated on a beat-to-beat basis, in order to obtain more information about the role played by the autonomie nervous system during these episodes.
暂无评论