提出新型物理驱动的神经单元，解决时序模型记忆与稳定性的矛盾。
CHLU: The Causal Hamiltonian Learning Unit as a Symplectic Primitive for Deep Learning
- 基于哈密顿结构与辛积分，实现相空间体积守恒。
- 在无限时域下保持稳定，且可调控噪声过滤能力。
- 适用于需要长期依赖建模的任务，如时序生成。
当前处理时序动态的深度学习原语面临根本性困境：离散型（如LSTM）易出现梯度爆炸或消失；连续型（如神经微分方程）虽稳定但会耗散信息。本文提出一种名为因果哈密顿学习单元（Causal Hamiltonian Learning Unit, CHLU）的新型物理引导计算原语。通过强制满足相对论哈密顿结构并采用辛积分，CHLU严格保持相空间体积守恒，旨在突破记忆-稳定性权衡。我们证明其设计支持无限时域稳定性，并具备可控的噪声滤波能力。以MNIST数据集为验证，展示了其生成能力，初步验证了可行性。
原文摘要 · Abstract (English)
Current deep learning primitives dealing with temporal dynamics suffer from a fundamental dichotomy: they are either discrete and unstable (LSTMs) \citep{pascanu_difficulty_2013}, leading to exploding or vanishing gradients; or they are continuous and dissipative (Neural ODEs) \citep{dupont_augmented_2019}, which destroy information over time to ensure stability. We propose the \textbf{Causal Hamiltonian Learning Unit} (pronounced: \textit{clue}), a novel Physics-grounded computational learning primitive. By enforcing a Relativistic Hamiltonian structure and utilizing symplectic integration, a CHLU strictly conserves phase-space volume, as an attempt to solve the memory-stability trade-off. We show that the CHLU is designed for infinite-horizon stability, as well as controllable noise filtering. We then demonstrate a CHLU's generative ability using the MNIST dataset as a proof-of-principle.
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。