标题： 神经优化：脉冲方式的进化 显示英文标题

标题： NeurOptimisation: The Spiking Way to Evolve

摘要： 人工智能系统日益增长的能源足迹促使人们寻求既高效又可扩展的计算模型。 神经形态计算（NC）通过赋予事件驱动算法以最小的功率需求来操作，从而解决了这一挑战，这些算法通过生物启发的尖峰动力学实现。 我们提出了NeurOptimiser，这是一个完全基于尖峰的优化框架，通过去中心化的NC系统实现了基于神经形态的元启发式范式。 所提出的方法包括一组神经形态启发单元（NHUs），每个单元结合尖峰神经元动力学与尖峰触发扰动启发式方法，以异步方式进化候选解决方案。 NeurOptimiser的协调是通过原生尖峰机制实现的，这些机制支持活动传播、局部信息共享和全局状态更新，而无需外部协调。 我们在英特尔的Lava平台上实现了该框架，目标是Loihi 2芯片，并在无噪声的BBOB套件上进行了评估，最多达到40个维度。 我们使用不同的配置部署了多个NeurOptimisers，主要考虑动态系统，如线性和Izhikevich模型用于尖峰神经动力学，以及固定和差分进化变异规则用于尖峰触发启发式方法。 尽管这些配置是作为概念验证实现的，但我们记录并概述了该框架实现的进一步扩展和改进。 结果表明，所提出的方法表现出结构化的种群动力学、一致的收敛性和毫瓦级的功率可行性。 它们还将原生尖峰MHs定位为实现实时、低能耗和去中心化优化的可行路径。 显示英文摘要

摘要： The increasing energy footprint of artificial intelligence systems urges alternative computational models that are both efficient and scalable. Neuromorphic Computing (NC) addresses this challenge by empowering event-driven algorithms that operate with minimal power requirements through biologically inspired spiking dynamics. We present the NeurOptimiser, a fully spike-based optimisation framework that materialises the neuromorphic-based metaheuristic paradigm through a decentralised NC system. The proposed approach comprises a population of Neuromorphic Heuristic Units (NHUs), each combining spiking neuron dynamics with spike-triggered perturbation heuristics to evolve candidate solutions asynchronously. The NeurOptimiser's coordination arises through native spiking mechanisms that support activity propagation, local information sharing, and global state updates without external orchestration. We implement this framework on Intel's Lava platform, targeting the Loihi 2 chip, and evaluate it on the noiseless BBOB suite up to 40 dimensions. We deploy several NeurOptimisers using different configurations, mainly considering dynamic systems such as linear and Izhikevich models for spiking neural dynamics, and fixed and Differential Evolution mutation rules for spike-triggered heuristics. Although these configurations are implemented as a proof of concept, we document and outline further extensions and improvements to the framework implementation. Results show that the proposed approach exhibits structured population dynamics, consistent convergence, and milliwatt-level power feasibility. They also position spike-native MHs as a viable path toward real-time, low-energy, and decentralised optimisation.