paper-with-me

홈 › Papers

Deep convolutional tensor network

2020-05-29 · Philip Blagoveschensky, Anh Huy Phan

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.

📄 PDF Abstract BibTeX arXiv:2005.14506

Code (1)

philip-bl/dctn 공식 구현 pytorch

Tasks

image-classificationImage ClassificationTensor Networks

Similar Papers 제목 키워드 기반

Tensor Graph Convolutional Network for Dynamic Graph Representation Learning

2024-01-13 · Ling Wang, Ye Yuan

Dynamic graphs (DG) describe dynamic interactions between entities in many practical scenarios. Most existing DG representation learning models combine graph convolutional network and sequence neural network, which model…

Graph Representation LearningRepresentation Learning

T- Hop: Tensor representation of paths in graph convolutional networks

2022-04-11 · Abdulrahman Ibraheem

We describe a method for encoding path information in graphs into a 3-d tensor. We show a connection between the introduced path representation scheme and powered adjacency matrices. To alleviate the heavy computational …

Dimensionality Reduction

Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network

2020-08-12 · ECCV 2020 8 · Anh-Huy Phan, Konstantin Sobolev, Konstantin Sozykin, Dmitry Ermilov 외

Most state of the art deep neural networks are overparameterized and exhibit a high computational cost. A straightforward approach to this problem is to replace convolutional kernels with its low-rank tensor approximatio…

image-classificationImage ClassificationTensor Decomposition

Ultimate tensorization: compressing convolutional and FC layers alike

2016-11-10 · Timur Garipov, Dmitry Podoprikhin, Alexander Novikov, Dmitry Vetrov

Convolutional neural networks excel in image recognition tasks, but this comes at the cost of high computational and memory complexity. To tackle this problem, [1] developed a tensor factorization framework to compress f…

Tensor Regression Networks with various Low-Rank Tensor Approximations

2017-12-27 · Xingwei Cao, Guillaume Rabusseau

Tensor regression networks achieve high compression rate of neural networks while having slight impact on performances. They do so by imposing low tensor rank structure on the weight matrices of fully connected layers. I…

regression