arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2608.18248cond-mat.dis-nnq-bio.PE

涌现系统的构造模型学习

Learning constructive models of emergent systems

Bipul Pandey, Caden Proctor, Vinay Ramanathan, Nico Roth, Arjun S. Raman

首次发表
浏览论文内容

中文总结 AI 辅助

该研究受统计系统发育学启发,提出Layer-Restricted Boltzmann Machine(LRBM)架构,用于构建涌现系统,经数字图像、自然语言、酶序列及分支酸变位酶实验验证,揭示了构造涌现系统的层级统计逻辑。

中文摘要 AI 辅助

涌现系统——包含多尺度相互作用的系统——通常通过迭代而非显式前向设计产生,因此构建涌现系统的设计原则尚未得到充分探索。当前的人工智能架构虽在生成方面有用,但未提供如何构造涌现系统的逻辑。受统计系统发育学启发,我们发现推断系统熵的尺度,再显式约束从低熵尺度到高熵尺度的信息流,可得到数据驱动的、逐步的涌现系统“构造模型”,我们将所得架构命名为层受限玻尔兹曼机(Layer-Restricted Boltzmann Machine,LRBM)。将LRBM以相同方式应用于数字图像、自然语言和酶序列,其模型遵循层级逻辑:低层编码全局结构,高层编码细粒度特征。作为对基于LRBM的构造的严格实验挑战,我们在体内功能测定中构建并评估了160条合成分支酸变位酶(chorismate mutase,CM)酶的构造轨迹和1130条天然CM酶的构造轨迹。设计的CM酶与最近的天然同源物的序列差异最高达53%。值得注意的是,酶折叠出现在LRBM的中间层,而功能仅在满足所有层的要求时才出现。因此,在该酶家族中,折叠是功能的必要条件而非充分条件。我们的结果表明,存在一种共享的、可学习的层级统计逻辑,用于构造涌现系统。

英文摘要

Emergent systems - systems with multiscale interactions - arise through iteration than forward design, leaving principles for building them under-explored. Current artificial intelligence architectures, while useful for generation, provide no logic for construction. Inspired by statistical phylogenetics, we show that inferring scales of system entropy then constraining information from low to high entropic scales yields stepwise constructive models. We term this architecture the Layer-Restricted Boltzmann Machine (LRBM). Applied identically to digit images, natural language, and enzyme sequences, LRBMs follow a common hierarchical logic: lower layers encode global structure, higher layers fine-grained features. As a stringent test, we assayed 160 synthetic chorismate mutase (CM) constructive trajectories alongside 1,130 natural homologs in vivo. Designed CMs functioned up to 53% divergent from nearest natural homolog. Fold emerged at intermediate layers while function required all layers, illustrating that fold was necessary but insufficient for function. Our results demonstrate a shared, learnable logic for constructing emergent systems.

补充信息

↑