现有神经网络无法实现逻辑智能，需用可微逻辑单元重构架构
Standard Neural Computation Alone Is Insufficient for Logical Intelligence
- 提出可微逻辑单元（LNUs），将与、或、非等逻辑操作嵌入神经网络
- 标准神经计算缺乏逻辑一致性，导致推理能力差、泛化性弱
- 适合追求可解释推理的可信AI研究者，推动符号与神经融合
当前神经网络架构在实现真正逻辑智能方面存在根本缺陷。现代AI模型依赖基于内积变换和非线性激活的标准神经计算来拟合数据模式，虽在归纳学习中有效，却缺乏演绎推理所需的结构保证。因此，深度网络在规则推理、结构化泛化和可解释性方面表现不佳，必须依赖大量后处理修正。本文主张应从根本上重构标准神经层，以整合逻辑推理能力。我们提出逻辑神经单元（Logical Neural Units, LNUs），即模块化组件，可直接在神经架构中嵌入可微的逻辑运算近似（如与、或、非）。本文批判现有神经符号方法，揭示标准神经计算在逻辑推断中的局限性，并将LNUs视为AI范式变革的必要方向。最后，我们勾勒了实现路径，涵盖理论基础、架构集成及未来研究的关键挑战。
原文摘要 · Abstract (English)
Neural networks, as currently designed, fall short of achieving true logical intelligence. Modern AI models rely on standard neural computation-inner-product-based transformations and nonlinear activations-to approximate patterns from data. While effective for inductive learning, this architecture lacks the structural guarantees necessary for deductive inference and logical consistency. As a result, deep networks struggle with rule-based reasoning, structured generalization, and interpretability without extensive post-hoc modifications. This position paper argues that standard neural layers must be fundamentally rethought to integrate logical reasoning. We advocate for Logical Neural Units (LNUs)-modular components that embed differentiable approximations of logical operations (e.g., AND, OR, NOT) directly within neural architectures. We critique existing neurosymbolic approaches, highlight the limitations of standard neural computation for logical inference, and present LNUs as a necessary paradigm shift in AI. Finally, we outline a roadmap for implementation, discussing theoretical foundations, architectural integration, and key challenges for future research.
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。