Learning to Access Computation: Accessibility Plasticity as a Principle of Adaptive Intelligence

学习访问计算：可访问性可塑性作为自适应智能的一项原则

Abstract: Modern neural networks primarily adapt through parameter modification within predefined computational structures. While recent methods introduce modularity, conditional computation, and parameter-efficient adaptation, they generally do not distinguish computational capability from computational accessibility as separate adaptive variables. 摘要： 现代神经网络主要通过预定义计算结构内的参数修改来进行自适应。尽管近期的研究方法引入了模块化、条件计算和参数高效自适应，但它们通常并未将“计算能力”与“计算可访问性”作为独立的自适应变量进行区分。

This work introduces Accessibility Plasticity, a principle of adaptive computation in which systems adapt not only by changing what computation exists, but also by reorganizing which existing computations can interact and participate. 本研究引入了“可访问性可塑性”（Accessibility Plasticity），这是一种自适应计算原则。在该原则下，系统不仅通过改变现有的计算内容来适应，还通过重组哪些现有计算可以相互作用和参与来完成自适应。

We formalize Accessibility Plasticity through a relationship-based operational realization and establish a reuse-first hierarchy of adaptation, where accessibility modification precedes more costly capability and structural changes. 我们通过基于关系的运算实现对“可访问性可塑性”进行了形式化，并建立了一种“重用优先”的自适应层级结构，其中可访问性的修改优先于代价更高的能力和结构性变更。

A proof-of-concept evaluation on sequential learning tasks shows that accessibility adaptation can reduce capability modification while maintaining comparable task performance. 在序列学习任务上的概念验证评估表明，可访问性自适应可以在保持相当任务性能的同时，减少对计算能力的修改需求。

These results suggest accessibility as a distinct adaptive dimension and provide a foundation for future dynamic neural systems whose computational relationships evolve with changing environments. 这些结果表明，可访问性是一个独特的自适应维度，并为未来的动态神经网络系统奠定了基础，使其计算关系能够随着环境的变化而演进。