Although deep neural networks have seen great success in recent years through various changes in overall architectures and optimization strategies, their fundamental underlying design remains largely unchanged. Computational neuroscience may provide more biologically realistic models of neural processing mechanisms, but they are still high-level abstractions of empirical behaviour. Here we propose an evolvable neural unit (ENU) that can evolve individual somatic and synaptic compartment models of neurons in a scalable manner. We demonstrate that ENUs can evolve to mimic integrate-and-fire neurons and synaptic spike-timing-dependent plasticity. Furthermore, by constructing a network where an ENU takes the place of each synapse and neuron, we evolve an agent capable of learning to solve a T-maze environment task. This network independently discovers spiking dynamics and reinforcement-type learning rules, opening up a new path towards biologically inspired artificial intelligence.

尽管近年来，通过整体体系结构和优化策略的各种变化，深层神经网络取得了巨大的成功，但其基本的基础设计在很大程度上保持不变。计算神经科学可以提供神经处理机制的生物学上更现实的模型，但是它们仍然是经验行为的高级抽象。在这里，我们提出了一种可演化的神经单元（ENU），它可以以可扩展的方式演化神经元的个体体细胞和突触间隔模型。我们证明，ENU可以进化为模仿整合并发射神经元和突触时机依赖的可塑性。此外，通过构建一个用ENU代替每个突触和神经元的网络，我们开发了一种能够学习解决T迷宫环境任务的代理。