Quasiperiodic-Chaotic Neural Networks and Short-Term Analog Memory.
Quasiperiodic-Chaotic Neural Networks and Short-Term Analog Memory.
复制标题
准周期混沌神经网络和短期模拟存储器。
DOI：
10.1142/s0218127421300032
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
N. Ichinose
中科院分区：
文献类型：
--
作者：
Yooprasert S;Culham A;Tagane S;Yahara T;Nguyen VD;Nguyen KS;Utteridge TMA;東樹宏和;N. Ichinose
在混沌神经网络的基础上，提出了一种准混沌神经网络模型。准周期混沌神经元表现出原始混沌神经元所没有的准周期动力学。拟周期解和混沌解在参数空间中是孤立的。混沌区域可以通过一条不变闭曲线的折叠结构来识别。利用扰动的影响是保守的准周期解的属性，我们证明了短期视觉记忆中，真实的数字是可以接受的代表颜色。在图像复原时，拟周期解对动态噪声很敏感。而神经元之间的准周期同步可以降低噪声的影响。使用准周期性的短期模拟存储器是重要的，因为它可以直接存储模拟量。准混沌神经网络的工作作为大规模的模拟存储阵列。这种类型的模拟存储器在模拟计算（如深度学习）中具有潜在的应用。
A model of quasiperiodic-chaotic neural networks is proposed on the basis of chaotic neural networks. A quasiperiodic-chaotic neuron exhibits quasiperiodic dynamics that an original chaotic neuron does not have. Quasiperiodic and chaotic solutions are exclusively isolated in the parameter space. The chaotic domain can be identified by the presence of a folding structure of an invariant closed curve. Using the property that the influence of perturbation is conserved in the quasiperiodic solution, we demonstrate short-term visual memory in which real numbers are acceptable for representing colors. The quasiperiodic solution is sensitive to dynamical noise when images are restored. However, the quasiperiodic synchronization among neurons can reduce the influence of noise. Short-term analog memory using quasiperiodicity is important in that it can directly store analog quantities. The quasiperiodic-chaotic neural networks are shown to work as large-scale analog storage arrays. This type of analog memory has potential applications to analog computation such as deep learning.