Deep tensor networks with matrix product operators
arXiv:2209.09098 · doi:10.1007/s42484-022-00081-1
Abstract
We introduce deep tensor networks, which are exponentially wide neural networks based on the tensor network representation of the weight matrices. We evaluate the proposed method on the image classification (MNIST, FashionMNIST) and sequence prediction (cellular automata) tasks. In the image classification case, deep tensor networks improve our matrix product state baselines and achieve 0.49% error rate on MNIST and 8.3% error rate on FashionMNIST. In the sequence prediction case, we demonstrate an exponential improvement in the number of parameters compared to the one-layer tensor network methods. In both cases, we discuss the non-uniform and the uniform tensor network models and show that the latter generalizes well to different input sizes.
arXiv comment9+2 pages, 8 figures
References in corpus (16)
- Quantum Convolutional Neural Networks
- Unifying time evolution and optimization with matrix product states
- The effect of data encoding on the expressive power of variational quantum machine learning models
- Equivalence of restricted Boltzmann machines and tensor network 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
- Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines
- Supervised Learning with Projected Entangled Pair States
- Tensor network based machine learning of non-Markovian quantum processes
- Matrix Product Operators for Sequence to Sequence Learning
- Generative Tensor Network Classification Model for Supervised Machine Learning
- Probabilistic Modeling with Matrix Product States
- Mutual Information Scaling for Tensor Network Machine Learning
- Residual Tensor Train: A Quantum-inspired Approach for Learning Multiple Multilinear Correlations
- Tensor network to learn the wavefunction of data