How chaos boosts the encoding capacity of small recurrent neural networks : learning consideration
How chaos boosts the encoding capacity of small recurrent neural networks : learning consideration
复制标题
混沌如何提高小型循环神经网络的编码能力：学习考虑
DOI：
10.1109/ijcnn.2004.1379874
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
H. Bersini
中科院分区：
文献类型：
--
作者：
C. Molter;U. Salihoglu;H. Bersini
到目前为止，递归网络，当采用不动点动力学，表现出非常差的编码能力。然而，当优先保持在混沌动力学中时，这些相同的网络可以在它们的循环吸引子中编码大量的信息，这提高了它们的编码能力。在以前的论文中已经描述了一种简单的方法来编码这样的信息，通过将N维空间中的每个向量与一个“符号”循环吸引子鲁棒地关联起来。主要的信息是，作为吸引子数量的函数，混沌自发机制的单调增加。然而，没有提供算法来调整连接的权重，以便对给定的输入集进行编码。为此，本文回顾了经典的基于梯度的BPTT学习算法。结果表明，该算法的效果不佳，而且通过使用它，网络的“混沌性”得到了强烈的抑制，因此它的编码能力。
So far, recurrent networks, when adopting fixed point dynamics, show a very poor encoding capacity. However, these same networks, when preferentially maintained in chaotic dynamics, can encode an enormous amount of information in their cyclic attractors and this boosts their encoding capacity. It has been described in a previous paper a simple way to encode such information by robustly associating each vector in a N-dimensional space with one "symbolic" cyclic attractor. The main message was the monotonous increase of chaotic spontaneous regimes as a function of the number of attractors to learn. However, no algorithm was provided to adjust the connection's weight in order to encode a given input set. For this purpose, this paper revisits the classical gradient-based BPTT learning algorithm. It shows that this algorithm gives poor results and furthermore that by using it the "chaoticity" of the network dampens strongly, hence it's encoding capacity.
影响因子：
64.8
作者：
GRAY, CM;KONIG, P;SINGER, W
通讯作者：
SINGER, W