对于存在实际层神经元的CMAC模型,讨论了压缩映射对网络学习收敛性的影响。
Also, the influence on learning convergence from compression mapping in those CMAC models with actual neurons is discussed.
经图像边缘检测应用结果表明,该算法对于加快网络学习的收敛性有着显著成效。
The results of image edge detection show that the algorithm has better convergence properties than the conventional backpropagation learning technique.
在理论分析的基础上,提出了协同博弈的强化学习算法,并证明了算法的收敛性。
On the basis of theoretical analysis, the cooperative game reinforcement learning method is proposed and its convergence is proved.
为改进网络学习效率及大范围收敛性,提出了网络权值学习的单调同伦方法,该方法具有与牛顿法相同的二阶收敛性。
To improve the learning efficiency and global convergence we present the monotone homotopy method, which has the same convergence as the Newton's method, to train the weights of the network.
讨论了具有初态学习和任意初态两种情况下的迭代学习律的收敛性和鲁棒性问题。
Two learning laws with initial state learning and random initial states are proposed, and their convergence and robustness are proved.
本文研究系统状态初值漂移和系统参数扰动对迭代学习控制算法收敛性的影响。
In this paper, the influence about system initial shift and system parameter disturbance on convergence of the algorithm is studied.
本文主要致力于支持向量机、近似支持向量机的学习算法研究,特征提取的数学模型与算法的改进及其应用,聚类分析算法的收敛性证明。
This paper's main works is that: learning algorithm studies of support vector machine, mathematical model and application about feature selection, convergence analysis of clustering algorithm.
先通过基于模糊竞争学习确定一种在线模糊辨识算法,并给出递推模糊竞争学习算法收敛性证明。
First of all, an on-line fuzzy identifying algorithm is confirmed by means of fuzzy competitive learning, and the convergence about a recursive algorithm of fuzzy competitive learning is proved.
针对多指手爪的非线性影响,提出了一种位置离散学习控制方法,并给出了这种方法的收敛性定理。
To overcome the nonlinear effects, the discrete learning control strategy is presented. The convergence theorem is also given.
基于迭代学习控制的基本原理,阐述了单输人单输出非线性系统中il的收敛性和稳定性的一般性结论。
The theory of iterative learning control was used to ensure the astringency and stability of ILC in single-in-single-out non-linear system.
将学习矩阵作用于误差数据建立PDAG算法的数学模型,从理论上证明了PDAG算法的稳定性和收敛性。
The establishment of mathematical model of PDAG algorithm, with the application of a learning matrix to the error data, proved the stability and convergence of PDAG algorithm in theory.
与这两种迭代学习控制相比,P型迭代学习控制的收敛条件更加严苛,收敛性和鲁棒性较差,而且收敛速度比以上两种控制方法要慢得多。
Compared with the above two ILCs, the convergence condition of P-type ILC is much stricter and its robustness is worse. Besides, convergence speed of P-type ILC is much slower than that of D-type ILC.
仿真结果表明,改进的BP算法可显著加速网络训练速度,学习过程具有较好的收敛性和较强的鲁棒性。
The simulation results show the presented quick training algorithm can speed up the learning process of MLP, and improve the learning properties on convergence and robust performance.
仿真结果表明,改进的BP算法可显著加速网络训练速度,学习过程具有较好的收敛性和较强的鲁棒性。
The simulation results show the presented quick training algorithm can speed up the learning process of MLP, and improve the learning properties on convergence and robust performance.
应用推荐