Combining the predictions of collections of neural networks often outperforms the best single network. Such ensembles are typically trained independently, and their superior `wisdom of the crowd' originates from the differences between networks. Collective foraging and decision making in socially interacting animal groups is often improved or even optimal thanks to local information sharing between conspecifics. We therefore present a model for co-learning by ensembles of interacting neural networks that aim to maximize their own performance but also their functional relations to other networks. We show that ensembles of interacting networks outperform independent ones, and that optimal ensemble performance is reached when the coupling between networks increases diversity and degrades the performance of individual networks. Thus, even without a global goal for the ensemble, optimal collective behavior emerges from local interactions between networks. We show the scaling of optimal coupling strength with ensemble size, and that networks in these ensembles specialize functionally and become more `confident' in their assessments. Moreover, optimal co-learning networks differ structurally, relying on sparser activity, a wider range of synaptic weights, and higher firing rates - compared to independently trained networks. Finally, we explore interactions-based co-learning as a framework for expanding and boosting ensembles.

中文翻译：

---

利他多样化神经网络集合的集体学习

结合神经网络集合的预测通常优于最好的单个网络。这样的集成通常是独立训练的，它们优越的“群体智慧”源于网络之间的差异。由于同种之间的本地信息共享，在社会互动的动物群体中的集体觅食和决策通常会得到改善甚至优化。因此，我们提出了一种通过交互神经网络的集合进行共同学习的模型，旨在最大限度地提高自己的性能以及与其他网络的功能关系。我们表明交互网络的集成优于独立网络，并且当网络之间的耦合增加多样性并降低单个网络的性能时，达到最佳集成性能。因此，即使没有集合的全局目标，网络之间的局部交互也会产生最佳的集体行为。我们展示了最佳耦合强度与集成大小的缩放比例，并且这些集成中的网络在功能上专业化并且在他们的评估中变得更加“自信”。此外，与独立训练的网络相比，最佳协同学习网络在结构上有所不同，依赖于更稀疏的活动、更广泛的突触权重和更高的发射率。最后，我们探索了基于交互的共同学习作为扩展和增强集成的框架。并且这些集合中的网络在功能上专业化并且对他们的评估变得更加“自信”。此外，与独立训练的网络相比，最佳协同学习网络在结构上有所不同，依赖于更稀疏的活动、更广泛的突触权重和更高的发射率。最后，我们探索了基于交互的共同学习作为扩展和增强集成的框架。并且这些集合中的网络在功能上专业化并且对他们的评估变得更加“自信”。此外，与独立训练的网络相比，最佳协同学习网络在结构上有所不同，依赖于更稀疏的活动、更广泛的突触权重和更高的发射率。最后，我们探索了基于交互的共同学习作为扩展和增强集成的框架。