您要查找的是不是：
- In this paper, a novel variant activation (transform) sigmoid function with three parameters is proposed, and then the improved BP algorithm based on it is educed and discussed. 摘要提出了人工神经元的一种新颖的多参数可调激活函数，推导出相应的BP学习算法。
- Research on main parameters modification of Duncan-Chang model based on the improved BP network. 基于改进的BP网络对邓肯张模型主要参数修正研究。
- Than we study the major decoding algorithms, BF, WBF, LP-WBF, BP and two other improved BP algorithms. 本文介绍了BF、WBF、LP-WBF、BP、BP_based和Normalized BP_based算法,详细的推导了BP译码的各个步骤。
- Through applying an improved BP(back propagation) algorithm to city consume,a BP model is built. 针对城市消费预测问题;应用一种改进的BP算法;建立了相应的BP网络模型;并设计了基于BP神经网络的城市消费预测系统.
- The typical BP algorithm and improved BP algorithm are applied to the fault diagnosis of Tennessee Eastman(TE) model. 并分别将典型的BP算法和改进后的BP算法用于TE(Tennessee Eastman)模型的故障诊断中。
- GSP algorithm is an AprioriAll based algorithm. GSP算法是一个基于AprioriAll的算法。
- It is shown, by derivations and calculations, that the improved BP algorithm can obviously reduce the learning time. 最后，利用实测数据进行验证。结果表明，改进的神经网络算法明显提高网络收敛速度；
- It states that the improved BP algorithm and the hybrid BP algorithm are adapted well to treating the prototype observation data of a dam. 由此表明,采用改进的BP算法和混合BP算法来处理大坝观测数据是行之有效的。
- The algorithms were discussed detailedly, which used BP neural network and improved BP neural network with conjugate gradient algorithm forecast power network short-term load. 详细讨论了应用BP神经网络、共轭梯度算法改进BP神经网络方法进行电力系统短期负荷预报的算法，及在预报过程中对电网负荷数据进行预处理方法。
- Neural networks have been widely used in kinds of research fields. In this paper, faults of CSTR will be detected and diagnosed using an improved BP algorithm. 将BP算法和使用复合法修正初始权值的BP算法运用到CSTR模型中进行故障诊断。
- A improved BP neural network algorithm with the stability of the steepest descent method and the speed performance of the Newton approach method is educed. 导出一种既有最速下降法的稳定性又有牛顿法的快速性的新算法；
- The system employs a diagnosis method,which combines fuzzy neural networks with improved BP algorithm and can swiftly and accurately determine the location of a condenser fault. 系统采用了模糊神经网络与改进的BP算法相结合的故障诊断方法,能快速地、准确地判断出凝汽器故障所在。
- Using improved BP neural network, equidistant surface reconstruction of NURBS is proposed. 利用改进的BP神经网络构造三次有理B样条曲面等距面。
- The traditional state-space traversal based algorithm is analyzed and two main engines - BDD and SAT are compared. 该算法的特点有:1)由于我们的算法只使用到了可满足性算法引擎,因而和采用BDD引擎的算法不同,不存在内存增长过快的问题。
- This paper presents a fault diagnosis method that an improved BP neutral network model is applied to CNC machine. 提出了一种改进的BP神经网络模型应用于数控机床的故障诊断方法。
- An ant colony optimization based algorithm for permutation flow shop scheduling was proposed. 摘要提出了一种求解置换流水车间调度的蚁群优化算法。
- Simulation results show that KPR is fault-tolerant, scalable, and better than non-security-aware and fixed-number replication based algorithms. 仿真结果表明，该算法可以有效提高不安全网格环境下的任务调度成功率，具有很好的容错性和可扩展性，优于固定备份数的网格任务调度算法。
- Fuzzy optimal controlarithmetic was designed for each module, and an improved BP neural network was introduced to implement the fuzzy relation. 对每个控制模块设计了相应的模糊优化控制算法,并用改进的BP神经网络实现算法的模糊关系。
- For linear model reduction algorithms, The Krylov subspace based algorithms including Arnoldi process and Lanczos algorithm are introduced. 同时对于这两种常见的模型降阶算法，本文将给出相关的误差分析。
- Theory and practical approach of using improved BP network to raise the precision of intelligent olfaction are proposed. 研究采用改进BP网络提高智能嗅敏系统精度的理论与方法。
