A novel artificial neural network (ANN) suitable for computationally intensive problems is described in this paper. The usefulness of this ANN is demonstrated for the synthesis of a microstrip line. This ANN uses a st...
详细信息
A novel artificial neural network (ANN) suitable for computationally intensive problems is described in this paper. The usefulness of this ANN is demonstrated for the synthesis of a microstrip line. This ANN uses a standard neural network architecture consisting of a hetero-associative memory and exploits a fault-tolerant number representation, which gives significant insight into a new method of fault-tolerant computing. In addition this ANN provides an efficient method for synthesizing geometrical parameters of microwave devices, when stochastic features are incorporated in the synthesis process. Further research is required to investigate the potential of this new paradigm. (C) 2005 Published by Elsevier Ltd.
Some existence and stability results for the equilibrium points of the one-dimensional Kohonen self-organizing neural network with two neighbors are extended to most nonincreasing neighborhood functions. All the funct...
详细信息
Some existence and stability results for the equilibrium points of the one-dimensional Kohonen self-organizing neural network with two neighbors are extended to most nonincreasing neighborhood functions. All the functions mentioned in the neural literature are included. The assumption on the stimuli distribution is weakened, too. In the multidimensional setting, we derive from a general formula various stability and instability results.
Traveling Salesman Problem is one of typical NP-hard problems of combinatorial *** is because of the complexity of TSP that accurate computing algorithms couldn't find a global optimal solution in more short time ...
详细信息
Traveling Salesman Problem is one of typical NP-hard problems of combinatorial *** is because of the complexity of TSP that accurate computing algorithms couldn't find a global optimal solution in more short time or at *** analyzing the relationship between global optimal solutions and local optimal solutions computed using heuristic algorithms for TSP, it is found that union set of edge sets of multi high-qualify local optimal solutions can include all of edges of a global optimal *** method, reducing initial edge set for TSP, is put forward based on probability statistic *** search space of original problem is cut down greatly by utilizing new method;the quantity of new initial edge set is about double times of problem *** computing algorithms can find global optimal solution for small scale TSP based on new edge sets, and efficiency of stochastic search algorithms is improved greatly.
We study the problem of solving a quadratic system of equations, i.e., recovering a vector signal x ε Rn from its magnitude measurements yi = |〈ai, x〉|, i = 1, ..., m. We develop a gradient descent algorithm (referre...
详细信息
We study the problem of solving a quadratic system of equations, i.e., recovering a vector signal x ε Rn from its magnitude measurements yi = |〈ai, x〉|, i = 1, ..., m. We develop a gradient descent algorithm (referred to as RWF for reshaped Wirtinger flow) by minimizing the quadratic loss of the magnitude measurements. Comparing with Wirtinger flow (WF) (Candès et al., 2015), the loss function of RWF is nonconvex and nonsmooth, but better resembles the least-squares loss when the phase information is also available. We show that for random Gaussian measurements, RWF enjoys linear convergence to the true signal as long as the number of measurements is O(n). This improves the sample complexity of WF (O(n log n)), and achieves the same sample complexity as truncated Wirtinger flow (TWF) (Chen and Candès, 2015), but without any sophisticated truncation in the gradient loop. Furthermore, RWF costs less computationally than WF, and runs faster numerically than both WF and TWF. We further develop an incremental (stochastic) version of RWF (IRWF) and connect it with the randomized Kaczmarz method for phase retrieval. We demonstrate that IRWF outperforms existing incremental as well as batch algorithms with experiments.
暂无评论