Data and codes for producing results associated with the manuscript "Training self-learning circuits for power-efficient solutions"

As the size and ubiquity of artificial intelligence and computational machine learning (ML) models grow, the energy required to train and use them is rapidly becoming economically and environmentally unsustainable. Recent laboratory prototypes of self-learning electronic circuits, examples of ``physical learning machines," open the door to analog hardware that directly employs physics to learn desired functions from examples at low energy cost. In this work, we show that this hardware platform allows for even further reduction of energy consumption by using good initial conditions as well as a new learning algorithm. Using analytical calculations, simulation and experiment, we show that a trade-off emerges when learning dynamics attempt to minimize both the error and the power consumption of the solution--greater power reductions can be achieved at the cost of decreasing solution accuracy. Finally, we demonstrate a practical procedure to weigh the relative importance of error and power minimization, improving power efficiency given a specific tolerance to error.

随着人工智能与计算机器学习（Machine Learning，ML）模型的规模扩张与普及程度提升，训练与部署此类模型所需的能耗正快速达到经济与环境层面均难以持续的水平。近期问世的自学习电子电路实验室原型属于“物理学习机”范畴，其为模拟硬件领域开辟了全新路径：此类硬件可直接依托物理原理，以极低能耗从示例数据中学习目标功能。本研究表明，通过采用优质初始条件与全新学习算法，该硬件平台可进一步降低能耗。结合解析计算、仿真与实验，我们发现：当学习动力学同时尝试最小化求解误差与系统功耗时，会出现一种权衡关系——功耗的进一步降低将以牺牲求解精度为代价。最后，我们提出了一套实用的权重分配方法，用于平衡误差最小化与功耗最小化的相对优先级，并可在给定误差容忍度的前提下提升系统功率效率。