论文标题
置换二进制神经网络：周期轨道及其应用的分析
Permutation Binary Neural Networks: Analysis of Periodic Orbits and Its Applications
论文作者
论文摘要
本文提出了一个以局部二元连接，全局置换连接和信号激活函数为特征的排列二进制神经网络。动力学由二进制变量的差方程描述。根据连接，网络会生成各种二进制向量的周期性轨道。二进制/置换连接为精确分析和基于FPGA的硬件实现带来了好处。为了考虑周期性轨道，我们介绍了三个工具：可视化动力学的组成返回图，两个用于周期轨道分类的功能数量以及用于工程应用程序的基于FPGA的硬件原型。使用工具，我们分析了所有6维网络。实验确认典型的周期轨道。
This paper presents a permutation binary neural network characterized by local binary connection, global permutation connection, and the signum activation function. The dynamics is described by a difference equation of binary state variables. Depending on the connection, the network generates various periodic orbits of binary vectors. The binary/permutation connection brings benefits to precise analysis and to FPGA based hardware implementation. In order to consider the periodic orbits, we introduce three tools: a composition return map for visualization of the dynamics, two feature quantities for classification of periodic orbits, and an FPGA based hardware prototype for engineering applications. Using the tools, we have analyzed all the 6-dimensional networks. Typical periodic orbits are confirmed experimentally.
