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 2409.00034cs.LGcs.ET
收藏

神经CRN:化学反应网络中学习的一种自然实现

Neural CRNs: A Natural Implementation of Learning in Chemical Reaction Networks

Department of Computer Science, Duke University(计算机科学系,杜克大学)

Rajiv Teja Nagipogu, John H. Reif

AI总结:

本文提出神经CRN框架,将神经计算建模为分子浓度的时间演化,仅用单分子和双分子反应及两阶段监督学习流程即可实现紧凑的线性和非线性学习电路,并借助一阶梯度近似使模型随输入维度线性扩展。

摘要:

能够自主学习的分子电路可能在生物工程和合成生物学等领域开启新的应用。为此,现有的神经计算化学实现主要依赖于利用质量作用动力学的稳态计算来模拟离散分层神经架构。相比之下,我们提出了一种基于动力系统的替代方法,其中神经计算被建模为分子浓度的时间演化。我们框架的模拟特性天然地与基于化学动力学的计算相契合,从而产生更紧凑的电路。我们通过三个关键演示展示了该框架的优势。首先,我们仅使用两个顺序阶段组装了一个端到端的监督学习流程,这是监督学习所需的最少阶段数。然后,我们展示(通过适当的简化)线性和非线性建模电路都可以仅使用单分子和双分子反应来实现,从而避免了高阶化学的复杂性。最后,我们证明一阶梯度近似可以被原生地纳入该框架,使非线性模型能够随输入维度线性扩展,而不是组合式扩展。所有电路构造都通过各种回归和分类任务的训练和推理仿真进行了验证。我们的工作为在合成生化系统中嵌入学习行为提供了一条可行的途径。

英文摘要:

Molecular circuits capable of autonomous learning could unlock novel applications in fields such as bioengineering and synthetic biology. To this end, existing chemical implementations of neural computing have mainly relied on emulating discrete-layered neural architectures using steady-state computations of mass action kinetics. In contrast, we propose an alternative dynamical systems-based approach in which neural computations are modeled as the time evolution of molecular concentrations. The analog nature of our framework naturally aligns with chemical kinetics-based computation, leading to more compact circuits. We present the advantages of our framework through three key demonstrations. First, we assemble an end-to-end supervised learning pipeline using only two sequential phases, the minimum required number for supervised learning. Then, we show (through appropriate simplifications) that both linear and nonlinear modeling circuits can be implemented solely using unimolecular and bimolecular reactions, avoiding the complexities of higher-order chemistries. Finally, we demonstrate that first-order gradient approximations can be natively incorporated into the framework, enabling nonlinear models to scale linearly rather than combinatorially with input dimensionality. All the circuit constructions are validated through training and inference simulations across various regression and classification tasks. Our work presents a viable pathway toward embedding learning behaviors in synthetic biochemical systems.

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。

↑