Nonlinear Tensor Ring Network
This addresses the challenge of deploying DNNs on resource-constrained platforms like portable devices, though it is an incremental improvement in compression techniques.
The paper tackles the problem of high storage and memory costs in deep neural networks by proposing a nonlinear tensor ring network (NTRN) that compresses fully-connected and convolutional layers using tensor ring decomposition, achieving effective image classification with reduced parameters on datasets like MNIST, Fashion MNIST, and Cifar-10.
The state-of-the-art deep neural networks (DNNs) have been widely applied for various real-world applications, and achieved significant performance for cognitive problems. However, the increment of DNNs' width and depth in architecture results in a huge amount of parameters to challenge the storage and memory cost, limiting to the usage of DNNs on resource-constrained platforms, such as portable devices. By converting redundant models into compact ones, compression technique appears to be a practical solution to reducing the storage and memory consumption. In this paper, we develop a nonlinear tensor ring network (NTRN) in which both fullyconnected and convolutional layers are compressed via tensor ring decomposition. Furthermore, to mitigate the accuracy loss caused by compression, a nonlinear activation function is embedded into the tensor contraction and convolution operations inside the compressed layer. Experimental results demonstrate the effectiveness and superiority of the proposed NTRN for image classification using two basic neural networks, LeNet-5 and VGG-11 on three datasets, viz. MNIST, Fashion MNIST and Cifar-10.