无处理器的机器学习：非线性电子超材料中的涌现学习
Machine Learning Without a Processor: Emergent Learning in a Nonlinear Electronic Metamaterial
AI总结：
针对现有线性电子学习超材料能力受限的问题，提出基于晶体管自调节非线性电阻的非线性电子学习超材料，可无处理器完成非线性任务，鲁棒性强、速度快、能耗极低，有望用于边缘计算与涌现学习研究。
摘要：
标准深度学习算法需要对大型非线性网络求导，这一过程速度慢且能耗高。电子学习超材料有望为模拟机器学习提供快速、高效且容错的硬件，但现有实现均为线性，严重限制了其性能。这类系统与人工神经网络以及大脑存在显著差异，因此引入非线性元件的可行性与实用价值尚未得到探究。本文提出了一种非线性学习超材料——一种由基于晶体管的自调节非线性电阻元件构成的模拟电子网络。我们证明，该系统无需计算机即可完成线性系统无法实现的任务，包括XOR（异或）任务和非线性回归。我们发现，这种非线性学习超材料会按顺序降低训练误差的各阶模式（均值、斜率、曲率），这与人工神经网络中的谱偏置类似。该电路对损伤具有鲁棒性，可在数秒内完成重新训练，执行已学习任务仅需微秒级时间，且每个晶体管的能耗仅为皮焦耳级。这表明其在传感器、机器人控制器和医疗设备等边缘系统的高速低功耗计算领域具有巨大潜力，同时也具备大规模制造以实现和研究涌现学习的潜力。
英文摘要：
Standard deep learning algorithms require differentiating large nonlinear networks, a process that is slow and power-hungry. Electronic learning metamaterials offer potentially fast, efficient, and fault-tolerant hardware for analog machine learning, but existing implementations are linear, severely limiting their capabilities. These systems differ significantly from artificial neural networks as well as the brain, so the feasibility and utility of incorporating nonlinear elements have not been explored. Here we introduce a nonlinear learning metamaterial -- an analog electronic network made of self-adjusting nonlinear resistive elements based on transistors. We demonstrate that the system learns tasks unachievable in linear systems, including XOR and nonlinear regression, without a computer. We find our nonlinear learning metamaterial reduces modes of training error in order (mean, slope, curvature), similar to spectral bias in artificial neural networks. The circuitry is robust to damage, retrainable in seconds, and performs learned tasks in microseconds while dissipating only picojoules of energy across each transistor. This suggests enormous potential for fast, low-power computing in edge systems like sensors, robotic controllers, and medical devices, as well as manufacturability at scale for performing and studying emergent learning.
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。
