Learning to Utilize Correlated Auxiliary Noise: A Possible Quantum Advantage
arXiv:2006.04863
Abstract
This paper has two messages. First, we demonstrate that neural networks that process noisy data can learn to exploit, when available, access to auxiliary noise that is correlated with the noise on the data. In effect, the network learns to use the correlated auxiliary noise as an approximate key to decipher its noisy input data. Second, we show that, for this task, the scaling behavior with increasing noise is such that future quantum machines could possess an advantage. In particular, decoherence generates correlated auxiliary noise in the environment. The new approach could, therefore, help enable future quantum machines by providing machine-learned quantum error correction.
arXiv comment11 pages, 3 figures
References in corpus (15)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Quantum Machine Learning
- Hilbert Space Representation of the Minimal Length Uncertainty Relation
- Violation of Bell's inequality under strict Einstein locality conditions
- Information in Black Hole Radiation
- The quest for a Quantum Neural Network
- Quantum machine learning: a classical perspective
- Event-Ready Bell Test Using Entangled Atoms Simultaneously Closing Detection and Locality Loopholes
- Learning to learn with quantum neural networks via classical neural networks
- A Generalized Shannon Sampling Theorem, Fields at the Planck Scale as Bandlimited Signals
- A Universal Training Algorithm for Quantum Deep Learning
- A Protocol for Quantum Energy Distribution
- Quantum Graph Neural Networks
- Natural Covariant Planck Scale Cutoffs and the Cosmic Microwave Background Spectrum
- Learning Non-Markovian Quantum Noise from Moiré-Enhanced Swap Spectroscopy with Deep Evolutionary Algorithm