Unsupervised Recognition of Informative Features via Tensor Network Machine Learning and Quantum Entanglement Variations

Abstract

Given an image of a white shoe drawn on a blackboard, how are the white pixels deemed (say by human minds) to be informative for recognizing the shoe without any labeling information on the pixels? Here we investigate such a ``white shoe'' recognition problem from the perspective of tensor network (TN) machine learning and quantum entanglement. Utilizing a generative TN that captures the probability distribution of the features as quantum amplitudes, we propose an unsupervised recognition scheme of informative features with the variations of entanglement entropy (EE) caused by designed measurements. In this way, a given sample, where the values of its features are statistically meaningless, is mapped to the variations of EE that statistically characterize the gain of information. We show that the EE variations identify the features that are critical to recognize this specific sample, and the EE itself reveals the information distribution of the probabilities represented by the TN model. The signs of the variations further reveal the entanglement structures among the features. We test the validity of our scheme on a toy dataset of strip images, the MNIST dataset of hand-drawn digits, the fashion-MNIST dataset of the pictures of fashion articles, and the images of brain cells. Our scheme opens the avenue to the quantum-inspired and interpreted unsupervised learning, which can be applied to, e.g., image segmentation and object detection.

arXiv comment7 pages, 8 figures. In the updated version, we added the unsupervised segmentation of images of cells, and the results with multi-qubit measurements

References in corpus (15)

• Quantum Machine Learning
• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• Matrix Product States and Projected Entangled Pair States: Concepts, Symmetries, and Theorems
• Tensor networks for complex quantum systems
• Renormalization and tensor product states in spin chains and lattices
• Unsupervised Generative Modeling Using Matrix Product States
• Tree Tensor Networks for Generative Modeling
• Machine Learning by Unitary Tensor Network of Hierarchical Tree Structure
• Learning Relevant Features of Data with Multi-scale Tensor Networks
• Supervised Learning with Projected Entangled Pair States
• Generative Tensor Network Classification Model for Supervised Machine Learning
• Generative machine learning with tensor networks: benchmarks on near-term quantum computers
• Entanglement-guided architectures of machine learning by quantum tensor network
• Experimental realization of a quantum image classifier via tensor-network-based machine learning
• Quantum Compressed Sensing with Unsupervised Tensor-Network Machine Learning

Cited by in corpus (8)

• Phase Transition Study meets Machine Learning
• Tensor networks for quantum machine learning
• MatChat: A Large Language Model and Application Service Platform for Materials Science
• Tensor networks for interpretable and efficient quantum-inspired machine learning
• Machine learning with tree tensor networks, CP rank constraints, and tensor dropout
• Locally purified density operators for noisy quantum circuits
• Universal scaling laws in quantum-probabilistic machine learning by tensor network towards interpreting representation and generalization powers
• Using matrix-product states for time-series machine learning