用复数神经元统一处理信号强度与时间动态，实现高效类脑学习。
Unified Complex-valued Neural Network: A Magnitude-Phase Computational Model for Event-Driven Neuromorphic Learning
- 复数状态分解为幅值和相位，分别表示信号强度与事件触发时机
- 联合优化幅值与相位路径，实现稳定时空学习，误差低于传统方法
- 适用于边缘AI与类脑计算，支持稀疏事件驱动，降低能耗
人工神经网络（ANN）提供精确的连续值表征，脉冲神经网络（SNN）则具备事件驱动的时间处理能力，但两者在单一结构中同时学习值编码与时间动态时仍存在局限。本文提出基于统一复数神经元（UCN）的新型神经计算模型，通过非对称复数状态融合连续激活与相位驱动的事件生成。其中，幅值表示信号强度，相位控制内在时间演化与有值脉冲释放。构建了结合反向传播（BP）与时间反向传播（BPTT）的基础训练框架，统一优化幅值与相位路径。为进一步降低计算复杂度，提出事件驱动自适应相位学习（EAPL）规则作为更高效的替代方案。在目标跟踪与洛伦兹吸引子学习任务上验证表明，基于UCN的网络（UCNN）能实现准确、稳定且可解释的时空学习，同时保持稀疏事件驱动计算特性，适用于类脑计算与边缘AI应用。
原文摘要 · Abstract (English)
Artificial neural networks (ANN) provide accurate continuous-valued representation, whereas spiking neural networks (SNN) offer event-driven temporal processing, yet both paradigms face limitations when value encoding and timing dynamics must be learned within a single computational structure. This paper introduces a network based on Unified Complex-valued Neuron (UCN), a new neural computational model that integrates continuous activation and phase-driven event generation through an asymmetric complex-valued state. In the UCN, magnitude encodes signal strength while phase governs intrinsic temporal evolution and valued spike emission. A foundational training framework combining backpropagation (BP) and backpropagation through time (BPTT) is first developed to optimize magnitude and phase pathways in a unified way. To reduce computational complexity, an event-driven adaptive phase learning (EAPL) rule is then introduced as a more efficient alternative. The proposed model is evaluated through object tracking and Lorenz attractor learning. Results demonstrate that UCN-based Network (UCNN) provides accurate, stable, and interpretable spatiotemporal learning while preserving sparse event-driven computation for neuromorphic and edge-AI applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。