神经晶体
Neural Crystals
AI总结：
本文提出受脑科学与相对论量子编码启发的 Lorentz 自旋几何神经架构，用至多16量子比特寄存器和Clifford-Lipschitz运算实现可解释的多模态图数据早期融合。
摘要：
我们直面多模态人工智能（MMAI）中的可解释性挑战。在神经科学启发与量子计算的交汇处，本文设想了用于大规模、异构、图结构化数据早期融合的、可解释且透明的自旋几何神经架构；在竞争性多维动力学下，该架构利用了自组织大脑中（共）行为状态的相对论量子神经编码的最新证据。这些设计借助特殊的 Clifford-Lipschitz 运算，采用自对偶经典描述来表示至多16个量子比特寄存器中的旋量量子态，以高效编码指数级庞大的神经结构。文中重点介绍了经过形式化“训练”的 Lorentz 神经架构，其恰好具有一个仅由抑制性中间神经元构成的侧层，用于解释反模态，以及它们带有层内连接的协同架构。该方法支持融合至多16种时间不变的互联（反）模态，并实现潜在多维模式的结晶。预计通过在多种真实场景下应用于多模态大数据，将获得全面洞见。
英文摘要：
We face up to the challenge of explainability in Multimodal Artificial Intelligence (MMAI). At the nexus of neuroscience-inspired and quantum computing, interpretable and transparent spin-geometrical neural architectures for early fusion of large-scale, heterogeneous, graph-structured data are envisioned, harnessing recent evidence for relativistic quantum neural coding of (co-)behavioral states in the self-organizing brain, under competitive, multidimensional dynamics. The designs draw on a self-dual classical description - via special Clifford-Lipschitz operations - of spinorial quantum states within registers of at most 16 qubits for efficient encoding of exponentially large neural structures. Formally 'trained', Lorentz neural architectures with precisely one lateral layer of exclusively inhibitory interneurons accounting for anti-modalities, as well as their co-architectures with intra-layer connections are highlighted. The approach accommodates the fusion of up to 16 time-invariant interconnected (anti-)modalities and the crystallization of latent multidimensional patterns. Comprehensive insights are expected to be gained through applications to Multimodal Big Data, under diverse real-world scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
