神经网络中物理系统的具有操作意义的表示
Operationally meaningful representations of physical systems in neural networks
AI总结:
本文提出一种以智能体间高效通信为原则的神经网络架构,用于学习分离不同物理参数、具有操作意义的表示,并通过经典与量子示例及强化学习交互场景验证其能力。
摘要:
为了推动科学进步,我们经常构建物理系统的抽象表示,以有意义的方式编码关于这些系统的信息。当前大多数机器学习技术所学到的表示反映了训练数据中存在的统计结构;然而,这些方法不允许我们对表示规定明确且具有操作意义的要求。在这里,我们提出一种神经网络架构,其核心思想是:处理同一物理系统不同方面的智能体,应当能够尽可能高效地相互传递相关信息。这会产生将不同参数分离开的表示,这些参数有助于在不同实验设置下对物理系统作出陈述。我们给出了涉及经典物理和量子物理的示例。例如,我们的架构为任意两量子比特系统找到了一种紧凑表示,将局部参数与描述量子关联的参数分离开。我们进一步表明,该方法可以与强化学习相结合,从而在交互式场景中实现表示学习;在这些场景中,智能体需要探索实验设置以识别相关变量。
英文摘要:
To make progress in science, we often build abstract representations of physical systems that meaningfully encode information about the systems. The representations learnt by most current machine learning techniques reflect statistical structure present in the training data; however, these methods do not allow us to specify explicit and operationally meaningful requirements on the representation. Here, we present a neural network architecture based on the notion that agents dealing with different aspects of a physical system should be able to communicate relevant information as efficiently as possible to one another. This produces representations that separate different parameters which are useful for making statements about the physical system in different experimental settings. We present examples involving both classical and quantum physics. For instance, our architecture finds a compact representation of an arbitrary two-qubit system that separates local parameters from parameters describing quantum correlations. We further show that this method can be combined with reinforcement learning to enable representation learning within interactive scenarios where agents need to explore experimental settings to identify relevant variables.
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。