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

Short summary

This paper introduces Accessibility Plasticity, a principle of adaptive computation where systems adapt not only by changing what computation exists but by reorganizing which existing computations can interact. It establishes a reuse-first hierarchy where accessibility modification precedes more costly capability and structural changes. A proof-of-concept on sequential learning tasks shows accessibility adaptation can reduce capability modification while maintaining comparable performance, suggesting accessibility as a distinct adaptive dimension for future dynamic neural systems.

• •Introduces Accessibility Plasticity as a new adaptive computation principle
• •Establishes reuse-first hierarchy: accessibility changes precede structural changes
• •Proof-of-concept shows reduced capability modification with comparable performance

Generated with AI, which can make mistakes.