Observing Schrödinger's Cat with Artificial Intelligence: Emergent Classicality from Information Bottleneck

Abstract

We train a generative language model on the randomized local measurement data collected from Schrödinger's cat quantum state. We demonstrate that the classical reality emerges in the language model due to the information bottleneck: although our training data contains the full quantum information about Schrödinger's cat, a weak language model can only learn to capture the classical reality of the cat from the data. We identify the quantum-classical boundary in terms of both the size of the quantum system and the information processing power of the classical intelligent agent, which indicates that a stronger agent can realize more quantum nature in the environmental noise surrounding the quantum system. Our approach opens up a new avenue for using the big data generated on noisy intermediate-scale quantum (NISQ) devices to train generative models for representation learning of quantum operators, which might be a step toward our ultimate goal of creating an artificial intelligence quantum physicist.

17 pages, 9 figures

References in corpus (22)

• Power of data in quantum machine learning
• Efficient quantum state tomography
• Quantum Darwinism
• Quantum advantage in learning from experiments
• Quantum Mechanics as Quantum Information (and only a little more)
• Quantum Tomography via Compressed Sensing: Error Bounds, Sample Complexity, and Efficient Estimators
• The randomized measurement toolbox
• Information-theoretic bounds on quantum advantage in machine learning
• Provably efficient machine learning for quantum many-body problems
• Classical Shadow Tomography with Locally Scrambled Quantum Dynamics
• Shadows of quantum machine learning
• Neural-network quantum state tomography
• Scalable and Flexible Classical Shadow Tomography with Tensor Networks
• Operator relaxation and the optimal depth of classical shadows
• Going Beyond Bell's Theorem
• Data-driven emergence of convolutional structure in neural networks
• Neural network enhanced measurement efficiency for molecular groundstates
• Neural-Shadow Quantum State Tomography
• Explainable Representation Learning of Small Quantum States
• Hardware-efficient learning of quantum many-body states
• Threshold size for the emergence of a classical-like behaviour
• Neural networks trained with SGD learn distributions of increasing complexity

Cited by in corpus (4)

• Demonstration of Robust and Efficient Quantum Property Learning with Shallow Shadows
• Machine Learning the Operator Content of the Critical Self-Dual Ising-Higgs Gauge Model
• Holographic Classical Shadow Tomography
• Neural network enhanced cross entropy benchmark for monitored circuits