TensorNetwork for Machine Learning

Abstract

We demonstrate the use of tensor networks for image classification with the TensorNetwork open source library. We explain in detail the encoding of image data into a matrix product state form, and describe how to contract the network in a way that is parallelizable and well-suited to automatic gradients for optimization. Applying the technique to the MNIST and Fashion-MNIST datasets we find out-of-the-box performance of 98% and 88% accuracy, respectively, using the same tensor network architecture. The TensorNetwork library allows us to seamlessly move from CPU to GPU hardware, and we see a factor of more than 10 improvement in computational speed using a GPU.

9 pages, 8 figures. All code can be found at https://github.com/google/tensornetwork

References in corpus (20)

• The density-matrix renormalization group
• Efficient classical simulation of slightly entangled quantum computations
• Entanglement renormalization
• Tensor-Entanglement-Filtering Renormalization Approach and Symmetry Protected Topological Order
• A class of quantum many-body states that can be efficiently simulated
• Tensor renormalization group approach to 2D classical lattice models
• Classical simulation of quantum many-body systems with a tree tensor network
• Renormalization algorithms for Quantum-Many Body Systems in two and higher dimensions
• Corner Transfer Matrix Renormalization Group Method
• Hand-waving and Interpretive Dance: An Introductory Course on Tensor Networks
• Tensor Network Renormalization
• Algorithms for entanglement renormalization
• Tensor product methods and entanglement optimization for ab initio quantum chemistry
• Continuous Matrix Product States for Quantum Fields
• Entanglement renormalization for quantum fields
• Equivalence of restricted Boltzmann machines and tensor network states
• Quantum Entanglement in Deep Learning Architectures
• A Density Matrix Algorithm for 3D Classical Models
• Supervised Learning with Quantum-Inspired Tensor Networks
• Fermionic orbital optimisation in tensor network states

Cited by in corpus (31)

• Variational Quantum Reinforcement Learning via Evolutionary Optimization
• Supervised Learning with Projected Entangled Pair States
• Multi-class quantum classifiers with tensor network circuits for quantum phase recognition
• Tree tensor network classifiers for machine learning: from quantum-inspired to quantum-assisted
• Generative machine learning with tensor networks: benchmarks on near-term quantum computers
• Tensor-based algorithms for image classification
• Entanglement-guided architectures of machine learning by quantum tensor network
• Hybrid quantum-classical classifier based on tensor network and variational quantum circuit
• Differentiable Programming of Isometric Tensor Networks
• Residual Tensor Train: A Quantum-inspired Approach for Learning Multiple Multilinear Correlations
• Efficient MPS representations and quantum circuits from the Fourier modes of classical image data
• Machine learning with tree tensor networks, CP rank constraints, and tensor dropout
• Tensor Networks for Medical Image Classification
• Quantum Tensor Network in Machine Learning: An Application to Tiny Object Classification
• Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models
• Stack operation of tensor networks
• Interaction Decompositions for Tensor Network Regression
• Tensor network to learn the wavefunction of data
• Residual Matrix Product State for Machine Learning
• Quantum-Classical Machine learning by Hybrid Tensor Networks
• Non-parametric Semi-Supervised Learning in Many-body Hilbert Space with Rescaled Logarithmic Fidelity
• Unifying O(3) Equivariant Neural Networks Design with Tensor-Network Formalism
• Accuracy and Efficiency of Simplified Tensor Network Codes
• Gleipnir: Toward Practical Error Analysis for Quantum Programs (Extended Version)
• Tensor-Train Networks for Learning Predictive Modeling of Multidimensional Data
• A Tensor Network Approach to Finite Markov Decision Processes
• Adaptive sampling-based optimization of quantics tensor trains for noisy functions: applications to quantum simulations
• Multi-layered tensor networks for image classification
• Tensor Network for Supervised Learning at Finite Temperature
• SchrödingeRNN: Generative Modeling of Raw Audio as a Continuously Observed Quantum State
• Patch-based Medical Image Segmentation using Matrix Product State Tensor Networks