Hybrid tensor decomposition in neural network compression
نویسندگان
چکیده
منابع مشابه
Tensor Decomposition for Compressing Recurrent Neural Network
In the machine learning fields, Recurrent Neural Network (RNN) has become a popular algorithm for sequential data modeling. However, behind the impressive performance, RNNs require a large number of parameters for both training and inference. In this paper, we are trying to reduce the number of parameters and maintain the expressive power from RNN simultaneously. We utilize several tensor decom...
متن کاملBTF Compression via Sparse Tensor Decomposition
In this paper, we present a novel compression technique for Bidirectional Texture Functions based on a sparse tensor decomposition. We apply the K-SVD algorithm along two different modes of a tensor to decompose it into a small dictionary and two sparse tensors. This representation is very compact, allowing for considerably better compression ratios at the same RMS error than possible with curr...
متن کاملNeural Network Based ROI Detection and Hybrid Image Compression
Region of Interest based compression is an efficient method of compression for images with a particular part to be most significant. It is always a better choice to compress the ROI with lossless compression while the rest of image with lossy compression technique. This paper proposes lossless compression for medical image(ROI) and near lossless compression for the rest of the image. Image othe...
متن کاملEstimation of Reference Evapotranspiration Using Artificial Neural Network Models and the Hybrid Wavelet Neural Network
Estimation of evapotranspiration is essential for planning, designing and managing irrigation and drainage schemes, as well as water resources management. In this research, artificial neural networks, neural network wavelet model, multivariate regression and Hargreaves' empirical method were used to estimate reference evapotranspiration in order to determine the best model in terms of efficienc...
متن کاملTensor graph convolutional neural network
In this paper, we propose a novel tensor graph convolutional neural network (TGCNN) to conduct convolution on factorizable graphs, for which here two types of problems are focused, one is sequential dynamic graphs and the other is cross-attribute graphs. Especially, we propose a graph preserving layer to memorize salient nodes of those factorized subgraphs, i.e. cross graph convolution and grap...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Neural Networks
سال: 2020
ISSN: 0893-6080
DOI: 10.1016/j.neunet.2020.09.006