A comprehensive survey on model compression and acceleration
T Choudhary, V Mishra, A Goswami… - Artificial Intelligence …, 2020 - Springer
In recent years, machine learning (ML) and deep learning (DL) have shown remarkable
improvement in computer vision, natural language processing, stock prediction, forecasting …
improvement in computer vision, natural language processing, stock prediction, forecasting …
Tensor methods in computer vision and deep learning
Tensors, or multidimensional arrays, are data structures that can naturally represent visual
data of multiple dimensions. Inherently able to efficiently capture structured, latent semantic …
data of multiple dimensions. Inherently able to efficiently capture structured, latent semantic …
Compression of deep convolutional neural networks for fast and low power mobile applications
Although the latest high-end smartphone has powerful CPU and GPU, running deeper
convolutional neural networks (CNNs) for complex tasks such as ImageNet classification on …
convolutional neural networks (CNNs) for complex tasks such as ImageNet classification on …
An efficient statistical method for image noise level estimation
In this paper, we address the problem of estimating noise level from a single image
contaminated by additive zero-mean Gaussian noise. We first provide rigorous analysis on …
contaminated by additive zero-mean Gaussian noise. We first provide rigorous analysis on …
A review of deterministic approximate inference techniques for Bayesian machine learning
S Sun - Neural Computing and Applications, 2013 - Springer
A central task of Bayesian machine learning is to infer the posterior distribution of hidden
random variables given observations and calculate expectations with respect to this …
random variables given observations and calculate expectations with respect to this …
Tensor networks meet neural networks: A survey and future perspectives
Tensor networks (TNs) and neural networks (NNs) are two fundamental data modeling
approaches. TNs were introduced to solve the curse of dimensionality in large-scale tensors …
approaches. TNs were introduced to solve the curse of dimensionality in large-scale tensors …
A multiple-phenotype imputation method for genetic studies
Genetic association studies have yielded a wealth of biological discoveries. However, these
studies have mostly analyzed one trait and one SNP at a time, thus failing to capture the …
studies have mostly analyzed one trait and one SNP at a time, thus failing to capture the …
[PDF][PDF] Global analytic solution of fully-observed variational Bayesian matrix factorization
The variational Bayesian (VB) approximation is known to be a promising approach to
Bayesian estimation, when the rigorous calculation of the Bayes posterior is intractable. The …
Bayesian estimation, when the rigorous calculation of the Bayes posterior is intractable. The …
Automated multi-stage compression of neural networks
J Gusak, M Kholiavchenko… - Proceedings of the …, 2019 - openaccess.thecvf.com
Low-rank tensor approximations are very promising for compression of deep neural
networks. We propose a new simple and efficient iterative approach, which alternates low …
networks. We propose a new simple and efficient iterative approach, which alternates low …
Falcon: lightweight and accurate convolution based on depthwise separable convolution
How can we efficiently compress convolutional neural network (CNN) using depthwise
separable convolution, while retaining their accuracy on classification tasks? Depthwise …
separable convolution, while retaining their accuracy on classification tasks? Depthwise …