Diversity conveys advantages in nature, yet homogeneous neurons typically comprise the layers of artificial neural networks. Here we construct neural networks from neurons that learn their own activation functions, quickly diversify, and subsequently outperform their homogeneous counterparts on image classification and nonlinear regression tasks. Sub-networks instantiate the neurons, which meta-learn especially efficient sets of nonlinear responses. Examples include conventional neural networks classifying digits and forecasting a van der Pol oscillator and a physics-informed Hamiltonian neural network learning H\'enon-Heiles orbits. Such learned diversity provides examples of dynamical systems selecting diversity over uniformity and elucidates the role of diversity in natural and artificial systems.

翻译：多样性在自然界中具有优势，然而人工神经网络层通常由同质神经元构成。我们构建了一个由神经元构成的神经网络，这些神经元可以学习自己的激活函数，快速多样化，并随后在图像分类和非线性回归任务上优于同质网络。子网络实例化神经元，它们通过元学习特别高效的非线性响应集合。例如，传统的神经网络可以对数字进行分类并预测van der Pol振荡器和一个物理学相关的Hamiltonian神经网络可以学习 Hénon-Heiles轨道。这种学习多样性提供了动态系统在选择多样性而不是一直性上的例子，并阐明了多样性在自然和人工系统中的作用。