English
Related papers

Related papers: MSE-Optimal Neural Network Initialization via Laye…

200 papers

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

We propose a new framework for processing Fringe Patterns (FP). Our novel approach builds upon the hypothesis that the denoising and normalisation of FPs can be learned by a deep neural network if enough pairs of corrupted and ideal FPs are…

Image and Video Processing · Electrical Eng. & Systems 2020-10-29 Alan Reyes-Figueroa , Mariano Rivera

Convolutional neural networks have recently been used for multi-focus image fusion. However, due to the lack of labeled data for supervised training of such networks, existing methods have resorted to adding Gaussian blur in focused images…

Computer Vision and Pattern Recognition · Computer Science 2018-06-20 Xiang Yan , Syed Zulqarnain Gilani , Hanlin Qin , Ajmal Mian

Reliable analysis of intracellular dynamic processes in time-lapse fluorescence microscopy images requires complete and accurate tracking of all small particles in all time frames of the image sequences. A fundamental first step towards…

Image and Video Processing · Electrical Eng. & Systems 2024-08-16 Yao Yao , Ihor Smal , Ilya Grigoriev , Anna Akhmanova , Erik Meijering

Binarization is an extreme network compression approach that provides large computational speedups along with energy and memory savings, albeit at significant accuracy costs. We investigate the question of where to binarize inputs at…

Computer Vision and Pattern Recognition · Computer Science 2018-04-12 Ameya Prabhu , Vishal Batchu , Rohit Gajawada , Sri Aurobindo Munagala , Anoop Namboodiri

Neuromorphic hardware tends to pose limits on the connectivity of deep networks that one can run on them. But also generic hardware and software implementations of deep learning run more efficiently for sparse networks. Several methods…

Neural and Evolutionary Computing · Computer Science 2018-08-09 Guillaume Bellec , David Kappel , Wolfgang Maass , Robert Legenstein

Deep learning-based image fusion approaches have obtained wide attention in recent years, achieving promising performance in terms of visual perception. However, the fusion module in the current deep learning-based methods suffers from two…

Computer Vision and Pattern Recognition · Computer Science 2022-02-01 Dongyu Rao , Xiao-Jun Wu , Tianyang Xu , Guoyang Chen

Precoding design based on weighted sum-rate (WSR) maximization is a fundamental problem in downlink multi-user multiple-input multiple-output (MU-MIMO) systems. While the weighted minimum mean-square error (WMMSE) algorithm is a standard…

Signal Processing · Electrical Eng. & Systems 2025-10-24 Xi Gao , Akang Wang , Junkai Zhang , Qihong Duan , Jiang Xue

Deep learning based fusion methods have been achieving promising performance in image fusion tasks. This is attributed to the network architecture that plays a very important role in the fusion process. However, in general, it is hard to…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 Hui Li , Tianyang Xu , Xiao-Jun Wu , Jiwen Lu , Josef Kittler

Network pruning is a promising avenue for compressing deep neural networks. A typical approach to pruning starts by training a model and then removing redundant parameters while minimizing the impact on what is learned. Alternatively, a…

Machine Learning · Computer Science 2020-02-18 Namhoon Lee , Thalaiyasingam Ajanthan , Stephen Gould , Philip H. S. Torr

The key distinguishing property of a Bayesian approach is marginalization, rather than using a single setting of weights. Bayesian marginalization can particularly improve the accuracy and calibration of modern deep neural networks, which…

Machine Learning · Computer Science 2022-03-31 Andrew Gordon Wilson , Pavel Izmailov

This work proposes a novel Deep Neural Network (DNN) quantization framework, namely RMSMP, with a Row-wise Mixed-Scheme and Multi-Precision approach. Specifically, this is the first effort to assign mixed quantization schemes and multiple…

Machine Learning · Computer Science 2021-11-02 Sung-En Chang , Yanyu Li , Mengshu Sun , Weiwen Jiang , Sijia Liu , Yanzhi Wang , Xue Lin

We propose an algorithm capable of identifying and eliminating irrelevant layers of a neural network during the early stages of training. In contrast to weight or filter-level pruning, layer pruning reduces the harder to parallelize…

Machine Learning · Computer Science 2024-06-10 Valentin Frank Ingmar Guenter , Athanasios Sideris

Deep Neural Network (DNN) models are usually trained sequentially from one layer to another, which causes forward, backward and update locking's problems, leading to poor performance in terms of training time. The existing parallel…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-07-25 Samson B. Akintoye , Liangxiu Han , Huw Lloyd , Xin Zhang , Darren Dancey , Haoming Chen , Daoqiang Zhang

The explicit regularization and optimality of deep neural networks estimators from independent data have made considerable progress recently. The study of such properties on dependent data is still a challenge. In this paper, we carry out…

Machine Learning · Statistics 2025-07-09 William Kengne , Modou Wade

Mimetic initialization uses pretrained models as case studies of good initialization, using observations of structures in trained weights to inspire new, simple initialization techniques. So far, it has been applied only to spatial mixing…

Machine Learning · Computer Science 2026-02-10 Asher Trockman , J. Zico Kolter

In this paper, we present a novel approach to perform deep neural networks layer-wise weight initialization using Linear Discriminant Analysis (LDA). Typically, the weights of a deep neural network are initialized with: random values,…

Computer Vision and Pattern Recognition · Computer Science 2017-11-27 Michele Alberti , Mathias Seuret , Vinaychandran Pondenkandath , Rolf Ingold , Marcus Liwicki

This paper is concerned with channel estimation in MIMO systems with few-bit ADCs. In these systems, a linear minimum mean-squared error (MMSE) channel estimator obtained in closed-form is not an optimal solution. We first consider a deep…

Signal Processing · Electrical Eng. & Systems 2023-07-19 Duy H. N. Nguyen

Despite Deep Learning's (DL) empirical success, our theoretical understanding of its efficacy remains limited. One notable paradox is that while conventional wisdom discourages perfect data fitting, deep neural networks are designed to do…

Machine Learning · Computer Science 2024-02-06 Oria Gruber , Haim Avron

Good weight initialization serves as an effective measure to reduce the training cost of a deep neural network (DNN) model. The choice of how to initialize parameters is challenging and may require manual tuning, which can be time-consuming…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Yifan Gong , Zheng Zhan , Yanyu Li , Yerlan Idelbayev , Andrey Zharkov , Kfir Aberman , Sergey Tulyakov , Yanzhi Wang , Jian Ren