Tensor Regression Networks with various Low-Rank Tensor Approximations

Abstract

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. In recent years, tensor regression networks have been investigated from the perspective of their compressive power, however, the regularization effect of enforcing low-rank tensor structure has not been investigated enough. We study tensor regression networks using various low-rank tensor approximations, aiming to compare the compressive and regularization power of different low-rank constraints. We evaluate the compressive and regularization performances of the proposed model with both deep and shallow convolutional neural networks. The outcome of our experiment suggests the superiority of Global Average Pooling Layer over Tensor Regression Layer when applied to deep convolutional neural network with CIFAR-10 dataset. On the contrary, shallow convolutional neural networks with tensor regression layer and dropout achieved lower test error than both Global Average Pooling and fully-connected layer with dropout function when trained with a small number of samples.

References in corpus (2)

• Improving neural networks by preventing co-adaptation of feature detectors
• Tensorizing Neural Networks

Cited by in corpus (5)

• Tensor Methods in Computer Vision and Deep Learning
• Compression and Interpretability of Deep Neural Networks via Tucker Tensor Layer: From First Principles to Tensor Valued Back-Propagation
• Biologically inspired architectures for sample-efficient deep reinforcement learning
• Semi-tensor Product-based TensorDecomposition for Neural Network Compression
• Efficient Tensor Contraction via Fast Count Sketch