用局部物理规则实现低功耗自主学习，无需复杂结构。
Harnessing intuitive local evolution rules for physical learning
- 通过边界参数控制，让物理系统按局部规则自适应演化
- 在回归与分类任务中表现良好，非线性规则下性能更优
- 适合硬件加速、低功耗场景，适用于边缘计算
尽管机器学习广泛且易用，但其计算密集、功耗高，促使人们探索学习任务的物理实现方式。我们提出一种物理系统的训练方案，通过最小化能量耗散来实现学习，仅需外部调控边界参数（即输入输出）。基于此，边界可控自适应状态调谐系统（BEASTS）利用局部物理规则进行自主学习。提出的BEASTAL（BEAST-Adaline）是此类系统中最接近经典Adaline算法的模拟。我们在仿真中验证了其在回归与分类任务中的有效性。该方法优于以往物理学习方案，无需大规模存储或复杂内部架构，仅依赖直观的局部演化规则。BEASTAL可完成任意线性任务，在局部演化规则为非线性时表现最佳。
原文摘要 · Abstract (English)
Machine Learning, however popular and accessible, is computationally intensive and highly power-consuming, prompting interest in alternative physical implementations of learning tasks. We introduce a training scheme for physical systems that minimize power dissipation in which only boundary parameters (i.e. inputs and outputs) are externally controlled. Using this scheme, these Boundary-Enabled Adaptive State Tuning Systems (BEASTS) learn by exploiting local physical rules. Our scheme, BEASTAL (BEAST-Adaline), is the closest analog of the Adaline algorithm for such systems. We demonstrate this autonomous learning in silico for regression and classification tasks. Our approach advances previous physical learning schemes by using intuitive, local evolution rules without requiring large-scale memory or complex internal architectures. BEASTAL can perform any linear task, achieving best performance when the local evolution rule is non-linear.
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。