提出梯度驱动的神经模糊网络同步优化方法，实现参数与结构协同进化。
Gradient-Based Neuroplastic Adaptation for Concurrent Optimization of Neuro-Fuzzy Networks
- 基于梯度的神经可塑性机制，同步优化参数与网络结构
- 在视觉游戏DOOM中通过在线强化学习成功训练，完成复杂任务
- 突破传统顺序设计瓶颈，支持动态自适应架构演化
神经模糊网络（NFNs）具有透明性、符号化表达和通用函数逼近能力，性能媲美传统神经网络，但其知识以语言规则形式表达。尽管优势明显，系统化设计仍具挑战。现有方法通常通过低效的分步识别参数与结构，导致过早锁定脆弱且次优的架构。本文提出一种无需依赖具体应用场景的新型方法——梯度基神经可塑性适应，用于同步优化NFN的参数与结构。认识到参数与结构本质耦合，应协同优化，使此前难以实现的场景成为可能，例如在视觉任务中对NFN进行在线强化学习。实验验证了该方法的有效性：通过在线强化学习，在视觉游戏DOOM中成功训练出能熟练应对高难度场景的NFN模型。
原文摘要 · Abstract (English)
Neuro-fuzzy networks (NFNs) are transparent, symbolic, and universal function approximations that perform as well as conventional neural architectures, but their knowledge is expressed as linguistic IF-THEN rules. Despite these advantages, their systematic design process remains a challenge. Existing work will often sequentially build NFNs by inefficiently isolating parametric and structural identification, leading to a premature commitment to brittle and subpar architecture. We propose a novel application-independent approach called gradient-based neuroplastic adaptation for the concurrent optimization of NFNs' parameters and structure. By recognizing that NFNs' parameters and structure should be optimized simultaneously as they are deeply conjoined, settings previously unapproachable for NFNs are now accessible, such as the online reinforcement learning of NFNs for vision-based tasks. The effectiveness of concurrently optimizing NFNs is empirically shown as it is trained by online reinforcement learning to proficiently play challenging scenarios from a vision-based video game called DOOM.
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。