526互联

Paper

[Keyence2019] Paper Cutting

Paper Cutting Luogu AT_keyence2019_f 题面翻译 有一个 \((H+1)\times(W+1)\) 的网格，网格中有 \(H\) 条水平线和 \(W\) 条竖直线。 你需要执行 \(K\) 次操作，每次沿一条水平线或竖直线将网格切开。定义一次操作的权值为切割后网格被 ......
Keyence Cutting Paper 2019

How to Read a Paper

paper.dvi http://ccr.sigcomm.org/online/files/p83-keshavA.pdf https://jyywiki.cn/ISER/2023/1-intro/index.html https://jyywiki.cn/ISER/2023/1-intro/ind ......
Paper Read How to

Paper Reading: Oversampling with Reliably Expanding Minority Class Regions for Imbalanced Data Learning

为了设计更有效的插值过采样算法，本文提出了一种新的插值过采样方法 OREM。OREM 在原始少数类样本周围找到候选少数类区域，然后利用这些候选区域识别不包含任何多数类样本的干净子区域。它们被认为是潜在的少数类区域，所以通过将合成样本填充到干净子区域可以增强少数类的表达能力。OREM 方法的思路很简单... ......
Oversampling Imbalanced Expanding Minority Learning

Guo_AD-NeRF_Audio_Driven_Neural_Radiance_Fields_for_Talking_Head_Synthesis_ICCV_2021_paper

可以看看这个向量场的虚拟人像的效果. 看论文第三章: 3.2: F_theta是一个神经网络, a是声音 d 是view direction, x是3d location. 普通的向量场是 F_theta: d,x > (c,σ) 表示d是一个方向, 表示观看者水平的偏移角度和数值的偏移角度. x是 ......
Guo_AD-NeRF_Audio_Driven_Neural_R adiance_Fields_for_Talking_Head_S ynthesis_ICCV ynthesis adiance

Paper Gestalt笔记

title: Paper Gestalt笔记 banner_img: https://cdn.studyinglover.com/pic/2023/07/5deff473fdf93539d3952d3d6894add3.png date: 2023-7-27 10:57:00 Paper Gesta ......
Gestalt 笔记 Paper

Paper Reading: Deep Forest

本文使用不可微模块实现深度学习进行的探索，提出了一种非 DNN 的深度森林算法 gcForest(多粒度级联森林)。gcForest 具有级联结构，可以通过森林进行表示学习。它的表征学习能力可以通过多粒度扫描进一步增强，从而可能使 gcForest 具有上下文或结构感知能力。级联的级别可以自动确定，... ......
Reading Forest Paper Deep

Literature Survey Slides of Paper Learning Dexterous In-Hand Manipulation

This is the tutorial slides about a literature survey of paper Learning Dexterous In-Hand Manipulation. ......
Manipulation Literature Dexterous Learning In-Hand

Paper Reading: A hybrid deep forest-based method for predicting synergistic drug combinations

为了解决联合用药数据的不平衡、高维、样本数量有限的问题，本文首先构建了一个由药物的物理、化学和生物特性组成的特征集，包括了丰富的生物学信息。特征空间的每个维度都有特定的含义，便于进行可解释性分析，找出预测过程中的关键特征。针对这种不平衡的高维中型数据集，提出了一种改进的基于 Deep Forest ... ......
combinations forest-based synergistic predicting Reading

Paper Reading: WCDForest: a weighted cascade deep forest model toward the classifcation tasks

针对 gcForest 存在的一些缺点，本文提出了一种 WCDForest 模型来提高小样本分类数据集的准确率。为了提高 WCDForest 的特征提取能力，提出了一种等量多粒度扫描模块，可以平等地扫描边缘特征。提出了类向量加权模块和特征增强模块，它们重新评估了 RF 在多粒度扫描和级联森林阶段的分... ......
160 classifcation WCDForest weighted Reading

Proj CDeepFuzz Paper Reading: POLYCRUISE: A Cross-Language Dynamic Information Flow Analysis

Abstract 本文： PolyCruise Method: 跨编程语言的holistic dynamic information flow analysis(DIFA) use a light language-specific analysis和language-agnostic online ......
Cross-Language Information POLYCRUISE CDeepFuzz Analysis

Paper Reading: Sample and feature selecting based ensemble learning for imbalanced problems

为了克服现有集成方法的缺点，本文提出一种新的混合集成策略——样本和特征选择混合集成学习 SFSHEL。SFSHEL 考虑基于聚类的分层对大多数样本进行欠采样，并采用滑动窗口机制同时生成多样性的特征子集。然后将经过验证训练的权重分配给不同的基学习器，最后 SFSHEL 通过加权投票进行预测。SFSHE... ......
imbalanced selecting ensemble learning problems

Paper Reading: Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold

为了实现基于 GAN 的交互式的基于点的操作，本文提出了 DragGAN，它解决了监督手柄点向目标移动和跟踪手柄点两个子问题，以便在每个编辑步骤中知道它们的位置。本文模型是建立在 GAN 的特征空间具有足够的区分力以实现运动监督和精确点跟踪的特性之上的，运动监督通过优化潜在代码的移位特征损失来实现的... ......
Manipulation Interactive Point-based Generative Manifold

Paper Reading: DBC-Forest: Deep forest with binning confidence screening

针对 gcForestcs 受高置信度但精度较低的实例影响的问题，本文提出了一种深度分箱置信度筛选森林算法。该算法采用基于置信度对实例进行分箱，这种方式可以检测到分区错误的实例，将更精确的实例传递到后续层次。实验结果表明，对于相同的训练超参数，DBC-Forest 模型比 gcForest 和 gc... ......
DBC-Forest confidence screening Reading binning

Paper Reading: Learning from Weak-Label Data: A Deep Forest Expedition

目录研究动机文章贡献本文方法标签补码结构标签频率估计与补码标志机制LCForest 整体框架实验结果实验设置基因功能分析任务实验文本分类任务实验场景分类任务实验医学自然语言处理实验优点和创新点 Paper Reading 是从个人角度进行的一些总结分享，受到个人关注点的侧重和实力所限，可能有理解不到 ......
Expedition Weak-Label Learning Reading Forest

Proj CDeepFuzz Paper Reading: NYX: Greybox Hypervisor Fuzzing using Fast Snapshots and Affine Types

Abstract 背景：hypervisor(virtual machine monitor, VMM) 保障了不同虚拟机之间的安全隔离(security boundaries) 用户：攻击场景：在云服务上运行自身的VM instances, 提升权限 本文：Nyx 目的：coverage guid ......
Hypervisor CDeepFuzz Snapshots Greybox Fuzzing

ACL2022 paper1 CAKE: A Scalable Commonsense-Aware Framework for Multi-View Knowledge Graph Completion

CAKE:用于多视域知识图谱补全的可扩展常识感知框架 ACL2022 Abstract 知识图谱存储大规模事实三元组，然而不可避免的是图谱仍然具有不完整性。（问题）以往的只是图谱补全模型仅仅依赖于事实域数据进行实体之间缺失关系的预测，忽略了宝贵的常识知识。以往的知识图嵌入技术存在无效负抽样和事实域链 ......
Commonsense-Aware Commonsense Completion Multi-View Framework

Paper reading: Improving Deep Forest by Exploiting High-order Interactions

为了对深度森林设计出信息量更大、计算成本更低的特征表示，本文提出了一种新的深度森林模型——高阶交互深度森林(hiDF)，利用输入特征的稳定高阶交互来生成信息丰富且多样化的特征表示。具体而言，本文设计了一个广义版本的随机交叉树(gRIT)来发现稳定的高阶相互作用，并应用激活线性组合(ALC)将这些相互... ......
Interactions Exploiting High-order Improving reading

Proj. CRR Paper Reading: Optimal Speedup of Las Vegas Algorithms, Adaptive restart for stochastic synthesis

Title Adaptive restart for stochastic synthesis PLDI 2021 Task Distribute the power between multiple runs in stochastic program synthesis to accelerat ......
Algorithms stochastic synthesis Adaptive Optimal

Paper Reading: Hashing-Based Undersampling Ensemble for Imbalanced Pattern Classification Problems

针对欠采样方法会丢弃大量多数类样本导致信息缺失的问题，本文提出了基于哈希的欠采样集成 HUE 模型，它利用 Bagging 和多数类样本的分布特征来构建多样化的训练子集。首先 HUE 通过散列将大多数类样本划分为不同的特征子空间，然后使用所有少数样本和主要从同一哈希子空间中提取的部分多数样本来构建训... ......
Classification Hashing-Based Undersampling Imbalanced Ensemble

Proj CDeepFuzz Paper Reading: Metamorphic Testing of Deep Learning Compilers

## Abstract 背景：Compiling DNN models into high-efficiency executables is not easy: the compilation procedure often involves converting high-level model ......
Metamorphic CDeepFuzz Compilers Learning Reading

Paper: Informer

# Informer 时间序列模型 ## 1 Introduction ### 3 significant limitations in LSTF LSTF(Long sequence time-series forecasting) 1. **The quadratic computation o ......
Informer Paper

Proj CDeepFuzz Paper Reading: A Comprehensive Study of Deep Learning Compiler Bugs

## Abstract 背景：深度学习编译器处理的深度学习模型与命令式程序有根本的不同，因为深度学习模型中的程序逻辑是隐式的。（the DL models processed by DL compilers differ fundamentally from imperative programs ......
Comprehensive CDeepFuzz Compiler Learning Reading

Proj CDeepFuzz Paper Reading: DeepMutation: Mutation Testing of Deep Learning Systems

## Abstract 本文：DeepMutation Github: https://github.com/berkuva/mutation-testing-for-DNNs Task: mutation testing framework specialized for DL systems t ......
DeepMutation CDeepFuzz Mutation Learning Reading

Proj CDeepFuzz Paper Reading: Testing Deep Neural Networks

## Abstract 本文:DeepCover Github: https://github.com/TrustAI/DeepCover Task: propose 4 novel test criteria to test DNNs Method: inspired by MC/DC cover ......
CDeepFuzz Networks Reading Testing Neural

Proj CDeepFuzz Paper Reading: TensorFlow: a system for Large-Scale machine learning

## Abstract 本文:Tensorflow Github: https://github.com/tensorflow/tensorflow Task: Detail on Tensorflow dataflow model 特点: 1. operates at large scale an ......
Large-Scale TensorFlow CDeepFuzz learning Reading

Proj CDeepFuzz Paper Reading: SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks

## Abstract 本文：SparseProp Github: https://github.com/IST-DASLab/sparseprop Task: a back-propagation algo for sparse training data, a fast vectorized i ......
Backpropagation SparseProp CDeepFuzz Efficient Networks

Proj CDeepFuzz Paper Reading: PyTorch: an imperative style, high-performance deep learning library

## Abstract 本文： PyTorch Task: detail the implementation and architecture of PyTorch Github: https://github.com/pytorch/pytorch 特点： 1. PyTorch同时关注可用性和速 ......
high-performance performance imperative CDeepFuzz learning

Proj CDeepFuzz Paper Reading: Software Testing with Large Language Model: Survey, Landscape, and Vision

## Abstract 本文: Task: Review on the use of LLMs in software testing Method: 1. analyzes 52 relevant studies ## 1. Intro ![](https://img2023.cnblogs.co ......
CDeepFuzz Landscape Language Software Reading

Proj CDeepFuzz Paper Reading: PELICAN: Exploiting Backdoors of Naturally Trained Deep Learning Models In Binary Code Analysis

## Abstract 背景： 1. 本文研究的不是被恶意植入的后门，而是products of defects in training 2. 攻击模式: injecting some small fixed input pattern(backdoor) to induce misclassifi ......
Exploiting CDeepFuzz Backdoors Naturally Analysis

Proj CDeepFuzz Paper Reading: Decompiling x86 Deep Neural Network Executables

## Abstract 本文: BTD github: https://github.com/monkbai/DNN-decompiler/ Task: a decompiler for DNN models to output DNN specifications including: opera ......
Decompiling Executables CDeepFuzz Network Reading
共82篇  :1/3页 首页上一页1下一页尾页