论文标题
深度卷积张量网络
Deep convolutional tensor network
论文作者
论文摘要
神经网络已经在许多领域实现了最先进的状态，据推测是由于参数共享，位置和深度。张量网络（TNS）是基于其纠缠结构的量子多体态的线性代数表示。 TNS在机器学习中发现了使用。我们设计了一个基于新型TN的模型，称为图像分类的深卷积张量网络（DCTN），该模型具有参数共享，局部性和深度。它基于纠缠的Plaquette状态（EPS）TN。我们展示了如何将EPS实现为可逆转层。我们在MNIST，FashionMnist和CIFAR10数据集上测试DCTN。浅的DCTN在MNIST和FashionMnist上表现良好，并且参数计数很小。不幸的是，深度增加过度拟合，从而降低了测试准确性。同样，由于过度拟合，任何深度的DCTN在CIFAR10上的表现不佳。这要确定原因。我们讨论DCTN的超参数如何影响其训练和过度拟合。
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.
