中文
相关论文

相关论文: Compound and Parallel Modes of Tropical Convolutio…

200 篇论文

Convolutional Neural Networks (CNNs) are known to be significantly over-parametrized, and difficult to interpret, train and adapt. In this paper, we introduce a structural regularization across convolutional kernels in a CNN. In our…

计算机视觉与模式识别 · 计算机科学 2020-09-08 Ze Wang , Xiuyuan Cheng , Guillermo Sapiro , Qiang Qiu

Convolutional Neural Networks (CNNs) filter the input data using spatial convolution operators with compact stencils. Commonly, the convolution operators couple features from all channels, which leads to immense computational cost in the…

机器学习 · 计算机科学 2019-05-17 Jonathan Ephrath , Lars Ruthotto , Eldad Haber , Eran Treister

Convolutional Neural Networks (CNN) are becoming a common presence in many applications and services, due to their superior recognition accuracy. They are increasingly being used on mobile devices, many times just by porting large models…

In this era of artificial intelligence, deep neural networks like Convolutional Neural Networks (CNNs) have emerged as front-runners, often surpassing human capabilities. These deep networks are often perceived as the panacea for all…

计算机视觉与模式识别 · 计算机科学 2023-11-15 Neeraj Kumar Singh , Nikhil R. Pal

This paper optimizes the Convolutional Neural Network (CNN) algorithm using high-performance computing (HPC) technologies. It uses multi-core processors, GPUs, and parallel computing frameworks like OpenMPI and CUDA to speed up CNN model…

分布式、并行与集群计算 · 计算机科学 2024-03-11 Shahrin Rahman

Motivated by the needs from an airline crew scheduling application, we introduce structured convolutional kernel networks (Struct-CKN), which combine CKNs from Mairal et al. (2014) in a structured prediction framework that supports…

机器学习 · 计算机科学 2021-07-26 Yassine Yaakoubi , François Soumis , Simon Lacoste-Julien

A Capsule Network (CapsNet) is a relatively new classifier and one of the possible successors of Convolutional Neural Networks (CNNs). CapsNet maintains the spatial hierarchies between the features and outperforms CNNs at classifying images…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Pouya Shiri , Amirali Baniasadi

Irregularly sampled multivariate time series are ubiquitous in several application domains, leading to sparse, not fully-observed and non-aligned observations across different variables. Standard sequential neural network architectures,…

机器学习 · 计算机科学 2023-08-10 Chrysoula Kosma , Giannis Nikolentzos , Michalis Vazirgiannis

Convolutional architectures have recently been shown to be competitive on many sequence modelling tasks when compared to the de-facto standard of recurrent neural networks (RNNs), while providing computational and modeling advantages due to…

机器学习 · 计算机科学 2019-02-19 Emre Aksan , Otmar Hilliges

The deployment of deep convolutional neural networks (CNNs) in many real world applications is largely hindered by their high computational cost. In this paper, we propose a novel learning scheme for CNNs to simultaneously 1) reduce the…

计算机视觉与模式识别 · 计算机科学 2017-08-23 Zhuang Liu , Jianguo Li , Zhiqiang Shen , Gao Huang , Shoumeng Yan , Changshui Zhang

We propose Path-CNN, a method for the segmentation of centerlines of tubular structures by embedding convolutional neural networks (CNNs) into the progressive minimal path method. Minimal path methods are widely used for topology-aware…

计算机视觉与模式识别 · 计算机科学 2022-04-06 Wei Liao

Deep Convolutional Neural Networks (CNNs) for image classification successively alternate convolutions and downsampling operations, such as pooling layers or strided convolutions, resulting in lower resolution features the deeper the…

计算机视觉与模式识别 · 计算机科学 2022-09-29 Ioannis Vezakis , Antonios Vezakis , Sofia Gourtsoyianni , Vassilis Koutoulidis , George K. Matsopoulos , Dimitrios Koutsouris

Binarized convolutional neural networks (BCNNs) are widely used to improve memory and computation efficiency of deep convolutional neural networks (DCNNs) for mobile and AI chips based applications. However, current BCNNs are not able to…

计算机视觉与模式识别 · 计算机科学 2019-09-09 Chunlei Liu , Wenrui Ding , Xin Xia , Yuan Hu , Baochang Zhang , Jianzhuang Liu , Bohan Zhuang , Guodong Guo

Improving the efficiency of current neural networks and modeling them in biological neural systems have become popular research directions in recent years. Pulse-coupled neural network (PCNN) is a well applicated model for imitating the…

计算机视觉与模式识别 · 计算机科学 2026-01-01 Haoran Liu , Mingzhe Liu , Peng Li , Jiahui Wu , Xin Jiang , Zhuo Zuo , Bingqi Liu

We describe the class of convexified convolutional neural networks (CCNNs), which capture the parameter sharing of convolutional neural networks in a convex manner. By representing the nonlinear convolutional filters as vectors in a…

机器学习 · 计算机科学 2016-09-06 Yuchen Zhang , Percy Liang , Martin J. Wainwright

We introduce Mixture-of-Depths (MoD) for Convolutional Neural Networks (CNNs), a novel approach that enhances the computational efficiency of CNNs by selectively processing channels based on their relevance to the current prediction. This…

计算机视觉与模式识别 · 计算机科学 2024-09-26 Rinor Cakaj , Jens Mehnert , Bin Yang

Convolutional neural networks (CNNs) have demonstrated their capability to solve different kind of problems in a very huge number of applications. However, CNNs are limited for their computational and storage requirements. These limitations…

计算机视觉与模式识别 · 计算机科学 2019-04-04 Adrià Ciurana , Albert Mosella-Montoro , Javier Ruiz-Hidalgo

Conventional neural architectures for sequential data present important limitations. Recurrent networks suffer from exploding and vanishing gradients, small effective memory horizons, and must be trained sequentially. Convolutional networks…

机器学习 · 计算机科学 2022-03-18 David W. Romero , Anna Kuzina , Erik J. Bekkers , Jakub M. Tomczak , Mark Hoogendoorn

Convolutional Neural Networks (CNNs) have become indispensable for solving machine learning tasks in speech recognition, computer vision, and other areas that involve high-dimensional data. A CNN filters the input feature using a network…

机器学习 · 计算机科学 2020-02-13 Jonathan Ephrath , Moshe Eliasof , Lars Ruthotto , Eldad Haber , Eran Treister

Graph Neural Networks (GNNs) effectively learn from relational data by leveraging graph symmetries. However, many real-world systems -- such as biological or social networks -- feature multi-way interactions that GNNs fail to capture.…

机器学习 · 计算机科学 2025-11-21 Mathilde Papillon , Guillermo Bernárdez , Claudio Battiloro , Nina Miolane