论文标题
蜂窝自动机可以通过诱导轨迹阶段共存对数据进行分类
Cellular automata can classify data by inducing trajectory phase coexistence
论文作者
论文摘要
我们表明，细胞自动机可以通过诱导动态相共存形式对数据进行分类。我们使用蒙特卡洛方法搜索一般的二维确定性自动机，该自动机根据活动对图像进行分类，即从图像引发的轨迹中发生的状态变化数量。当自动机的时间段数量是可训练的参数时，搜索方案确定了自动机，该自动机会根据初始条件而产生的动态轨迹群体显示出较高或低活动。这种性质的自动机的行为表现为非线性激活功能，其输出有效二进制，类似于尖峰神经元的新兴版本。
We show that cellular automata can classify data by inducing a form of dynamical phase coexistence. We use Monte Carlo methods to search for general two-dimensional deterministic automata that classify images on the basis of activity, the number of state changes that occur in a trajectory initiated from the image. When the number of timesteps of the automaton is a trainable parameter, the search scheme identifies automata that generate a population of dynamical trajectories displaying high or low activity, depending on initial conditions. Automata of this nature behave as nonlinear activation functions with an output that is effectively binary, resembling an emergent version of a spiking neuron.
