期刊:
Journal of Theoretical and Applied Information Technology,2012年46(1):114-119 ISSN:1817-3195
通讯作者:
Li, L.
作者机构:
[Xu, Tian; Li, Long] Department of Mathematics and Computational Science, Hengyang Normal University, Hengyang, 421008, China;[Yang, Jie] School of Mathematical Sciences, Dalian University of Technology, Dalian, 116024, China;[Liu, Yan] Department of Applied Mathematics, Dalian Polytechnic University, Dalian, 116034, China
通讯机构:
Department of Mathematics and Computational Science, Hengyang Normal University, China
摘要:
In the training of feedforward neural networks, it is usually suggested that the initial weights should be small in magnitude in order to prevent premature saturation. The aim of this paper is to point out the other side of the story: In some cases, the gradient of the error functions is zero not only for infinitely large weights but also for zero weights. Slow convergence in the beginning of the training procedure is often the result of sufficiently small initial weights. Therefore, we suggest that, in these cases, the initial values of the weights should be neither too large, nor too small. For instance, a typical range of choices of the initial weights might be something like (−0.4,−0.1) ∪ (0.1, 0.4), rather than (−0.1, 0.1) as suggested by the usual strategy. Our theory that medium size weights should be used has also been extended to a few commonly used transfer functions and error functions. Numerical experiments are carried out to support our theoretical findings.
摘要:
In this paper, A class of third-order nonlinear neutral damped functional differential equations with distributed deviating arguments are studied. By using a generalized Riccati transformation and Kamenev-type or Philos-type integral averaging technique,we establish some new sufficient conditions which insure that any solution of this equation oscillates or converges to zero.
关键词:
Improved ant colony optimization;improved Tabu search;vehicle routing problem;simultaneous pickups and deliveries;time window constraints
摘要:
A mixed integer programming mathematical formulation of vehicle routing problem with simultaneous pickups and deliveries, and time window constraints (VRP-SPDTW) is presented in this paper. The proposed model aims at minimizing the vehicle number and the overall travel cost. A novel two-stage hybrid metaheuristic method for VRP-SDPTW is also proposed. The first stage adopts improved ant colony optimization (IACO) to determine the minimum number of used vehicles. The second stage employs improved Tabu search to optimize the total travel cost, in which the initial solutions are obtained by IACO in the first stage. Experimental results demonstrate the effectiveness of the proposed metaheuristic method.
作者:
Tong, Xiaojiao*;Qi, Liqun;Wu, Soon-Yi;Wu, Felix F.
期刊:
Computational Optimization and Applications,2012年51(1):175-197 ISSN:0926-6003
通讯作者:
Tong, Xiaojiao
作者机构:
[Tong, Xiaojiao] Hengyang Normal Univ, Dept Math, Hengyang 421008, Hunan, Peoples R China.;[Qi, Liqun] Hong Kong Polytech Univ, Dept Appl Math, Kowloon, Hong Kong, Peoples R China.;[Wu, Soon-Yi] Natl Cheng Kung Univ, Dept Math, Natl Ctr Theoret Sci, Tainan 70101, Taiwan.;[Wu, Felix F.] Univ Hong Kong, Dept Elect & Elect Engn, Hong Kong, Hong Kong, Peoples R China.
通讯机构:
[Tong, Xiaojiao] H;Hengyang Normal Univ, Dept Math, Hengyang 421008, Hunan, Peoples R China.
关键词:
Power systems;Stability constraint;Nonlinear programs;Smoothing SQP method;Convergence