Deep learning, quantum chaos, and pseudorandom evolution
AI Breakdown
Get a structured breakdown of this paper — what it's about, the core idea, and key takeaways for the field.
Abstract
By modeling quantum chaotic dynamics with ensembles of random operators, we explore how a deep learning architecture known as a convolutional neural network (CNN) can be used to detect pseudorandom behavior in qubit systems. We analyze samples consisting of pieces of correlation functions and find that a CNN is capable of determining the degree of pseudorandomness which a system is subject to. This is done without computing any correlators explicitly. Interestingly, even samples drawn from two-point functions are found to be sufficient to solve this classification problem. This presents the possibility of using deep learning algorithms to explore late time behavior in chaotic quantum systems which have been inaccessible to simulation.