2020/05/29 by Philip Blagoveschensky, Blagoveschensky, Philip, Anh Huy Phan +1 · 1 citation
Computer Science · Mathematics · Physics and Astronomy · #FOS: Computer and information sciences #I.5.1 #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Parallel Computing and Optimization Techniques #Quantum many-body systems #Tensor decomposition and applications #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2005.14506
14 pages, 18 figures, to be published in the proceedings of NeurIPS 2020 Quantum tensor networks in machine learning workshop
openalex publication_date 2020/05/29 · arxiv created 2020/11/14 · arxiv updated 2020/11/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Neural networks have achieved state of the art results in many areas, supposedly due to parameter sharing, locality, and depth. Tensor networks (TNs) are linear algebraic representations of quantum many-body states based on their entanglement structure. TNs have found use in machine learning. We devise a novel TN based model called Deep convolutional tensor network (DCTN) for image classification, which has parameter sharing, locality, and depth. It is based on the Entangled plaquette states (EPS) TN. We show how EPS can be implemented as a backpropagatable layer. We test DCTN on MNIST, FashionMNIST, and CIFAR10 datasets. A shallow DCTN performs well on MNIST and FashionMNIST and has a small parameter count. Unfortunately, depth increases overfitting and thus decreases test accuracy. Also, DCTN of any depth performs badly on CIFAR10 due to overfitting. It is to be determined why. We discuss how the hyperparameters of DCTN affect its training and overfitting.