Biological nervous systems consist of networks of diverse, sophisticated information processors in the form of neurons of different classes. In most artificial neural networks (ANNs), neural computation is abstracted to an activation function that is usually shared between all neurons within a layer or even the whole network; training of ANNs focuses on synaptic optimization. In this paper, we propose the optimization of neuro-centric parameters to attain a set of diverse neurons that can perform complex computations. Demonstrating the promise of the approach, we show that evolving neural parameters alone allows agents to solve various reinforcement learning tasks without optimizing any synaptic weights. While not aiming to be an accurate biological model, parameterizing neurons to a larger degree than the current common practice, allows us to ask questions about the computational abilities afforded by neural diversity in random neural networks. The presented results open up interesting future research directions, such as combining evolved neural diversity with activity-dependent plasticity.

翻译：生物神经系统由多样且复杂的信息处理单元（即不同类别的神经元）构成的网络组成。在大多数人工神经网络（ANN）中，神经计算被抽象为激活函数，且通常在同一层甚至整个网络的所有神经元间共享；ANN的训练聚焦于突触优化。本文提出对神经中心参数进行优化，以获取一组能够执行复杂计算的多样化神经元。通过展示该方法的潜力，我们证明仅进化神经参数即可使智能体解决多种强化学习任务，而无需优化任何突触权重。尽管本研究无意构建精确的生物模型，但相较于当前普遍做法对神经元参数进行更高程度的参数化，使我们得以探询随机神经网络中神经多样性所赋予的计算能力。所述结果为未来研究方向（如将进化神经多样性与活动依赖性可塑性相结合）开辟了有趣的前景。