中文
相关论文

相关论文: A novel S-shape based NURBS interpolation with acc…

200 篇论文

We propose a sparse interpolation construction and a practical coarsening algorithm for the algebraic multigrid (AMG) method, tailored towards H(curl). Building on the generalized AMG framework, we introduce an interior/exterior splitting…

数值分析 · 数学 2026-03-02 Taoli Shen , James Brannick , Robert Falgout , Karsten Kahl , Jacob Schroder

This paper presents a residual-informed machine learning approach for replacing algebraic loops in equation-based Modelica models with neural network surrogates. A feedforward neural network is trained using the residual (error) of the…

机器学习 · 计算机科学 2025-10-13 Felix Brandt , Andreas Heuermann , Philip Hannebohm , Bernhard Bachmann

Recurrent neural networks (RNNs) are valued for their computational efficiency and reduced memory requirements on tasks involving long sequence lengths but require high memory-processor bandwidth to train. Checkpointing techniques can…

神经与进化计算 · 计算机科学 2024-12-17 Wadjih Bencheikh , Jan Finkbeiner , Emre Neftci

This paper presents a new version of Dropout called Split Dropout (sDropout) and rotational convolution techniques to improve CNNs' performance on image classification. The widely used standard Dropout has advantage of preventing deep…

计算机视觉与模式识别 · 计算机科学 2015-08-03 Fa Wu , Peijun Hu , Dexing Kong

We propose a new random pruning method (called "submodular sparsification (SS)") to reduce the cost of submodular maximization. The pruning is applied via a "submodularity graph" over the $n$ ground elements, where each directed edge is…

机器学习 · 计算机科学 2016-06-02 Tianyi Zhou , Hua Ouyang , Yi Chang , Jeff Bilmes , Carlos Guestrin

Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain. However, these works have primarily focused on classification accuracy,…

计算机视觉与模式识别 · 计算机科学 2020-09-10 Gongbo Liang , Yu Zhang , Xiaoqin Wang , Nathan Jacobs

Channel Pruning, widely used for accelerating Convolutional Neural Networks, is an NP-hard problem due to the inter-layer dependency of channel redundancy. Existing methods generally ignored the above dependency for computation simplicity.…

机器学习 · 计算机科学 2019-03-28 Yuefu Zhou , Ya Zhang , Yanfeng Wang , Qi Tian

We propose a new instruction (FPADDRE) that computes the round-off error in floating-point addition. We explain how this instruction benefits high-precision arithmetic operations in applications where double precision is not sufficient.…

数值分析 · 计算机科学 2016-03-03 Marat Dukhan , Richard Vuduc , Jason Riedy

Modern machine learning frameworks can train neural networks using multiple nodes in parallel, each computing parameter updates with stochastic gradient descent (SGD) and sharing them asynchronously through a central parameter server. Due…

分布式、并行与集群计算 · 计算机科学 2020-03-02 Zhuojin Li , Wumo Yan , Marco Paolieri , Leana Golubchik

A novel fast multi-impulse optimization method for long-duration perturbed orbit rendezvous is proposed. First, based on the analytically estimated impulses, the terminal rendezvous deviation with precise dynamics model can be predicted.…

混沌动力学 · 物理学 2021-08-11 An-yi Huang , Ya-zhong Luo , Heng-nian Li

Neuromorphic computing is a new paradigm for design of both the computing hardware and algorithms inspired by biological neural networks. The event-based nature and the inherent parallelism make neuromorphic computing a promising paradigm…

新兴技术 · 计算机科学 2019-07-10 Sebastian Glatz , Julien N. P. Martel , Raphaela Kreiser , Ning Qiao , Yulia Sandamirskaya

Deep neural networks have enormous representational power which leads them to overfit on most datasets. Thus, regularizing them is important in order to reduce overfitting and enhance their generalization capabilities. Recently, channel…

计算机视觉与模式识别 · 计算机科学 2021-06-18 Sudhakar Kumawat , Gagan Kanojia , Shanmuganathan Raman

The existence of redundancy in Convolutional Neural Networks (CNNs) enables us to remove some filters/channels with acceptable performance drops. However, the training objective of CNNs usually tends to minimize an accuracy-related loss…

计算机视觉与模式识别 · 计算机科学 2021-08-02 Xiaohan Ding , Tianxiang Hao , Jungong Han , Yuchen Guo , Guiguang Ding

Neural Radiance Field (NeRF) technology has made significant strides in creating novel viewpoints. However, its effectiveness is hampered when working with sparsely available views, often leading to performance dips due to overfitting.…

计算机视觉与模式识别 · 计算机科学 2025-09-10 Yuru Xiao , Xianming Liu , Deming Zhai , Kui Jiang , Junjun Jiang , Xiangyang Ji

We developed a flexible parallel algorithm for graph summarization based on vertex-centric programming and parameterized message passing. The base algorithm supports infinitely many structural graph summary models defined in a formal…

数据结构与算法 · 计算机科学 2022-11-07 Till Blume , Jannik Rau , David Richerby , Ansgar Scherp

Neural Radiance Fields (NeRF) have achieved remarkable progress in neural rendering. Extracting geometry from NeRF typically relies on the Marching Cubes algorithm, which uses a hand-crafted threshold to define the level set. However, this…

计算机视觉与模式识别 · 计算机科学 2024-12-16 Yi Gu , Zhaorui Wang , Dongjun Ye , Renjing Xu

The stochastic rounding (SR) function is proposed to evaluate and demonstrate the effects of stochastically rounding row and column subscripts in image interpolation and scan conversion. The proposed SR function is based on a pseudorandom…

图形学 · 计算机科学 2022-04-01 Olivier Rukundo , Samuel Emil Schmidt

The beam interruptions (interlocks) of particle accelerators, despite being necessary safety measures, lead to abrupt operational changes and a substantial loss of beam time. A novel time series classification approach is applied to…

We present the first theoretical framework for applying spiking neural networks (SNNs) to synthetic aperture radar (SAR) interferometric phase unwrapping. Despite extensive research in both domains, our comprehensive literature review…

神经与进化计算 · 计算机科学 2025-06-27 Marc Bara

We revisit two well-studied scheduling problems in the unrelated machines setting where each job can have a different processing time on each machine. For minimizing total weighted completion time we give a 1.45-approximation, which…

数据结构与算法 · 计算机科学 2022-11-21 Sungjin Im , Shi Li