用梯度下降训练热力学计算机，实现低能耗高效计算。
Training thermodynamic computers by gradient descent
- 通过最大化理想轨迹概率来优化热力学计算机参数。
- 在图像分类任务中实现与神经网络相当的计算性能。
- 硬件可自动运行，能量成本比数字计算低七数量级以上。
我们展示如何通过梯度下降调整热力学计算机的参数，使其在指定观测时间完成期望计算。在数字仿真中，训练目标是最大化计算机生成理想动态轨迹的概率，该轨迹模仿已训练神经网络的激活模式。采用教师-学生范式，使热力学计算机的有限时间动力学模拟出与神经网络类似的计算行为。由此确定的参数可直接用于热力学计算机的硬件实现，系统将由热噪声驱动自动执行计算。我们在标准图像分类任务上验证了该方法，并估算其热力学优势（数字与热力学实现的能量成本比）超过七数量级。结果表明梯度下降可用于热力学计算的训练，使机器学习核心方法成功应用于这一新兴领域。
原文摘要 · Abstract (English)
We show how to adjust the parameters of a thermodynamic computer by gradient descent in order to perform a desired computation at a specified observation time. Within a digital simulation of a thermodynamic computer, training proceeds by maximizing the probability with which the computer would generate an idealized dynamical trajectory. The idealized trajectory is designed to reproduce the activations of a neural network trained to perform the desired computation. This teacher-student scheme results in a thermodynamic computer whose finite-time dynamics enacts a computation analogous to that of the neural network. The parameters identified in this way can be implemented in the hardware realization of the thermodynamic computer, which will perform the desired computation automatically, driven by thermal noise. We demonstrate the method on a standard image-classification task, and estimate the thermodynamic advantage -- the ratio of energy costs of the digital and thermodynamic implementations -- to exceed seven orders of magnitude. Our results establish gradient descent as a viable training method for thermodynamic computing, enabling application of the core methodology of machine learning to this emerging field.
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。