论文标题
用于准量词编码的波浪脉冲神经网络
A wave-pulse neural network for quasi-quantum coding
论文作者
论文摘要
我们为波和脉冲传播设计了一个物理波脉冲神经网络（WPNN），它比Spike神经网络（SNN）给出了更大的神经编码自由度。我们定义了这种神经网络的规则和信息熵，其中信号速度，到达时间和神经元之间的连接长度都成为信号编码的关键参数。我们称其为准量子编码（QQC），因为这里的波和脉冲信号的组合表现得像量子波颗粒偶性的经典模仿，并且可以通过借用某些概念形成量子力学来研究。我们表明，准量词编码可以为声音和图像识别提供有效的方法。我们还讨论了波脉冲神经网络以及在生物学大脑中运行的准量子编码方法的可能性，在这些大脑中，神经振荡和动作电位对认知都很重要。
We design a physical wave-pulse neural network (WPNN) for both wave and pulse propagation, which gives more degrees of freedom for neural coding than spike neural networks (SNN). We define the rules and the information entropy of this kind of neural network, where the signal speed, arrival time, and the length of connections between neurons all become crucial parameters for signal coding. We call it quasi-quantum coding (QQC) since the combination of wave and pulse signals here behaves like a classical mimic of quantum wave-particle duality, and can be studied by borrowing some concepts form quantum mechanics. We present that the quasi-quantum coding can give efficient methods for both sound and image recognitions. We also discuss the possibility of the wave-pulse neural network and the quasi-quantum coding methods running on it in biological brains where both neural oscillations and action potentials are important to cognition.
