Entanglement-guided architectures of machine learning by quantum tensor network

Abstract

It is a fundamental, but still elusive question whether the schemes based on quantum mechanics, in particular on quantum entanglement, can be used for classical information processing and machine learning. Even partial answer to this question would bring important insights to both fields of machine learning and quantum mechanics. In this work, we implement simple numerical experiments, related to pattern/images classification, in which we represent the classifiers by many-qubit quantum states written in the matrix product states (MPS). Classical machine learning algorithm is applied to these quantum states to learn the classical data. We explicitly show how quantum entanglement (i.e., single-site and bipartite entanglement) can emerge in such represented images. Entanglement characterizes here the importance of data, and such information are practically used to guide the architecture of MPS, and improve the efficiency. The number of needed qubits can be reduced to less than 1/10 of the original number, which is within the access of the state-of-the-art quantum computers. We expect such numerical experiments could open new paths in charactering classical machine learning algorithms, and at the same time shed lights on the generic quantum simulations/computations of machine learning tasks.

10 pages, 5 figures

References in corpus (36)

• The density-matrix renormalization group in the age of matrix product states
• Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
• Towards A Rigorous Science of Interpretable Machine Learning
• Photonic quantum technologies
• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• A class of quantum many-body states that can be efficiently simulated
• Matrix product states represent ground states faithfully
• The quest for a Quantum Neural Network
• Criticality, the area law, and the computational power of PEPS
• Renormalization algorithms for Quantum-Many Body Systems in two and higher dimensions
• The iTEBD algorithm beyond unitary evolution
• Quantum-enhanced machine learning
• Hierarchical quantum classifiers
• Towards Quantum Machine Learning with Tensor Networks
• Differentiable Learning of Quantum Circuit Born Machine
• Simulating Strongly Correlated Quantum Systems with Tree Tensor Networks
• Resonating valence bond states in the PEPS formalism
• Variational Quantum Eigensolver with Fewer Qubits
• Advances on Tensor Network Theory: Symmetries, Fermions, Entanglement, and Holography
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Tree Tensor Networks for Generative Modeling
• Machine Learning by Unitary Tensor Network of Hierarchical Tree Structure
• Projected Entangled Pair States at Finite Temperature: Imaginary Time Evolution with Ancillas
• Learning Relevant Features of Data with Multi-scale Tensor Networks
• Discovering Symmetry Invariants and Conserved Quantities by Interpreting Siamese Neural Networks
• TensorNetwork for Machine Learning
• Quantum phase recognition via unsupervised machine learning
• Generative Tensor Network Classification Model for Supervised Machine Learning
• Interpretable Machine Learning Study of Many-Body Localization Transition in Disordered Quantum Ising Spin Chains
• A Reliable SVD based Watermarking Schem
• Phase Detection with Neural Networks: Interpreting the Black Box
• Identification of hidden order and emergent constraints in frustrated magnets using tensorial kernel methods
• Anomaly Detection with Tensor Networks
• Compact Neural Networks based on the Multiscale Entanglement Renormalization Ansatz
• Exponential improvements for quantum-accessible reinforcement learning
• Spin-qubit noise spectroscopy from randomized benchmarking by supervised learning

Cited by in corpus (9)

• Tensor networks for quantum machine learning
• Tensor networks for interpretable and efficient quantum-inspired machine learning
• Dequantizing quantum machine learning models using tensor networks
• Unsupervised Recognition of Informative Features via Tensor Network Machine Learning and Quantum Entanglement Variations
• Machine learning with tree tensor networks, CP rank constraints, and tensor dropout
• Non-separability of Physical Systems as a Foundation of Consciousness
• A Synthesis of Hidden Subgroup Quantum Algorithms and Quantum Chemical Dynamics
• Quantum max-flow in the bridge graph
• Using matrix-product states for time-series machine learning