Sequence Processing Neural Network with a Non-Monotonic Transfer Function
Sequence Processing Neural Network with a Non-Monotonic Transfer Function
复制标题
具有非单调传递函数的序列处理神经网络
DOI：
10.1143/jpsj.70.1300
复制
发表时间：
2001
影响因子：
1.7
通讯作者：
T. Horiguchi
中科院分区：
文献类型：
--
作者：
K. Katayama;T. Horiguchi
我们研究的存储容量和检索性能的同步全连接的神经网络与非单调的传递函数检索序列的模式，通过分析方法，也通过数值模拟。由于相互作用的不对称性和传递函数的非单调性，很难用传统的平衡态统计力学方法来研究网络。然后，我们使用路径积分表示的生成函数方法，并获得方程的动力学序参数的定态。我们澄清，网络与非单调的传递函数检索更多的序列的模式比单调的传递函数在零温度时，非单调性的传递函数是最佳选择。当传递函数的非单调性增大时，动力学序参量方程的解会出现混沌行为。那个...
We investigate storage capacity and retrieval property for a synchronous fully connected neural network with a non-monotonic transfer function which retrieves sequences of patterns, by an analytic method and also by numerical simulations. Because of asymmetry of interactions and non-monotonicity of the transfer function, it is difficult to use conventional methods of the equilibrium statistical mechanics in order to investigate the network. We then use a generating-function method of path-integral representation, and obtain equations for dynamical order parameters in the stationary state. We clarify that the network with the non-monotonic transfer function retrieves more sequences of patterns than that with a monotonic transfer function at zero temperature when non-monotonicity of the transfer function is selected optimally. It is also clarified that some chaotic behavior appears in solutions for the equations of the dynamical order parameters when non-monotonicity of the transfer function increases. The ...
M. Shiino 和 T. Fukai：“模拟神经网络统计行为的自洽信噪比分析和存储容量的增强”
DOI：
--
发表时间：
--
期刊：
影响因子：
--
作者：
通讯作者：
--