A key element of biological structures is self-replication. Neural networks are the prime structure used for the emergent construction of complex behavior in computers. We analyze how various network types lend themselves to self-replication. Backpropagation turns out to be the natural way to navigate the space of network weights and allows non-trivial self-replicators to arise naturally. We perform an in-depth analysis to show the self-replicators’ robustness to noise. We then introduce artificial chemistry environments consisting of several neural networks and examine their emergent behavior. In extension to this work’s previous version (Gabor et al., 2019), we provide an extensive analysis of the occurrence of fixpoint weight configurations within the weight space and an approximation of their respective attractor basins.

生物结构的一个关键要素是自我复制。神经网络是用于在计算机中紧急构建复杂行为的主要结构。我们分析了各种网络类型是如何自我复制的。反向传播被证明是导航网络权重空间的自然方式，并允许非平凡的自我复制器自然出现。我们进行了深入分析，以显示自我复制器对噪声的鲁棒性。然后，我们介绍了由几个神经网络组成的人工化学环境，并检查了它们的涌现行为。作为对这项工作的先前版本（Gabor 等人，2019 年）的扩展，我们对权重空间内固定点权重配置的出现以及它们各自的吸引子盆地的近似进行了广泛的分析。