While interest in artificial neural networks (ANNs) has been renewed by the ubiquitous use of deep learning to solve high-dimensional problems, we are still far from general artificial intelligence. In this article, we address the problem of emergent cognitive capabilities and, more crucially, of their detection, by relying on co-evolving creatures with mutable morphology and neural structure. The former is implemented via both static and mobile structures whose shapes are controlled by cubic splines. The latter uses ESHyperNEAT to discover not only appropriate combinations of connections and weights but also to extrapolate hidden neuron distribution. The creatures integrate low-level perceptions (touch/pain proprioceptors, retina-based vision, frequency-based hearing) to inform their actions. By discovering a functional mapping between individual neurons and specific stimuli, we extract a high-level module-based abstraction of a creature’s brain. This drastically simplifies the discovery of relationships between naturally occurring events and their neural implementation. Applying this methodology to creatures resulting from solitary and tag-team co-evolution showed remarkable dynamics such as range-finding and structured communication. Such discovery was made possible by the abstraction provided by the modular ANN which allowed groups of neurons to be viewed as functionally enclosed entities.

虽然普遍使用深度学习来解决高维问题重新激发了人们对人工神经网络 (ANN) 的兴趣，但我们离通用人工智能还很远。在这篇文章中，我们依靠具有可变形态和神经结构的共同进化生物来解决紧急认知能力的问题，更重要的是，他们的检测。前者通过静态和移动结构实现，其形状由三次样条控制。后者使用 ESHyperNEAT 不仅可以发现连接和权重的适当组合，还可以推断隐藏的神经元分布。这些生物整合了低水平的感知（触觉/疼痛本体感受器、基于视网膜的视觉、基于频率的听觉）来通知它们的行为。通过发现单个神经元和特定刺激之间的功能映射，我们提取了生物大脑的基于模块的高级抽象。这极大地简化了自然发生事件与其神经实现之间关系的发现。将这种方法应用于由单独和标记团队共同进化产生的生物，显示出非凡的动态，例如测距和结构化通信。模块化 ANN 提供的抽象使得这种发现成为可能，它允许将神经元组视为功能封闭的实体。将这种方法应用于由单独和标记团队共同进化产生的生物，显示出非凡的动态，例如测距和结构化通信。模块化 ANN 提供的抽象使得这种发现成为可能，它允许将神经元组视为功能封闭的实体。将这种方法应用于由单独和标记团队共同进化产生的生物，显示出非凡的动态，例如测距和结构化通信。模块化 ANN 提供的抽象使得这种发现成为可能，它允许将神经元组视为功能封闭的实体。