Recurrent spiking neural networks (RSNNs) hold great potential for advancing artificial general intelligence, as they draw inspiration from the biological nervous system and show promise in modeling complex dynamics. However, the widely-used surrogate gradient-based training methods for RSNNs are inherently inaccurate and unfriendly to neuromorphic hardware. To address these limitations, we propose the evolving connectivity (EC) framework, an inference-only method for training RSNNs. The EC framework reformulates weight-tuning as a search into parameterized connection probability distributions, and employs Natural Evolution Strategies (NES) for optimizing these distributions. Our EC framework circumvents the need for gradients and features hardware-friendly characteristics, including sparse boolean connections and high scalability. We evaluate EC on a series of standard robotic locomotion tasks, where it achieves comparable performance with deep neural networks and outperforms gradient-trained RSNNs, even solving the complex 17-DoF humanoid task. Additionally, the EC framework demonstrates a two to three fold speedup in efficiency compared to directly evolving parameters. By providing a performant and hardware-friendly alternative, the EC framework lays the groundwork for further energy-efficient applications of RSNNs and advances the development of neuromorphic devices.

翻译：递归脉冲神经网络（RSNN）受生物神经系统启发，在建模复杂动态方面展现出潜力，为推进通用人工智能提供了重要可能。然而，当前广泛使用的基于替代梯度的RSNN训练方法存在固有不准确性，且对神经形态硬件不友好。为解决这些局限，我们提出演化连接（EC）框架——一种仅需推理的RSNN训练方法。该框架将权重调整重构为参数化连接概率分布的搜索过程，并采用自然演化策略（NES）优化这些分布。EC框架从根本上规避了对梯度的依赖，同时具备稀疏布尔连接与高可扩展性等硬件友好特性。我们在标准机器人运动控制任务序列中评估EC方法，其性能可与深度神经网络相媲美，且优于梯度训练型RSNN，甚至能解决复杂的17自由度人形机器人控制任务。此外，相较于直接演化参数的方法，EC框架实现了2-3倍的效率提升。通过提供兼具高性能与硬件友好性的替代方案，EC框架为RSNN的进一步节能应用奠定基础，并推动神经形态器件的发展。