4 Atlas8346

尚未进行身份认证

暂无相关简介

等级
TA的排名 23w+

【论文精读】Learn from Neighbour: A Curriculum that Train Low Weighted Samples By Imitation

Learn from Neighbour: A Curriculum that Train Low Weighted Samples By Imitation原文地址:Learn from Neighbour: A Curriculum that Train Low Weighted Samples By Imitation这篇文章提出了一种新的课程学习的策略(见论文第4节),主要思想就是,一...

2018-10-09 16:13:45

【论文精读】Select Via Proxy: Efficient Data Selection For Training DeepNetworks

Select Via Proxy: Efficient Data Selection For Training DeepNetworks2019ICLR的文章,介绍了Select Via Proxy(SVP)通过较小规模的模型来确定样本的uncertainty进而决定复杂模型训练使用样本的策略。原文地址:Select Via Proxy: Efficient Data Selection Fo...

2018-10-08 13:18:16

【论文精读】Improving Simple Models with Confidence Profiles

Improving Simple Models with Confidence Profiles原文地址:Improving Simple Models with Confidence ProfilesAbstract用ProWeight方法进行模型迁移,使用linear probes通过flattened intermediate representations生成confidence s...

2018-10-03 14:54:01

【论文精读】Learning Bounds for Importance Weighting

Learning Bounds for Importance Weighting原论文地址:Learning Bounds for Importance WeightingAbstract1 Introduction现实世界中机器学习训练数据和测试数据样本的分布会有偏差。一个常见的修正方法叫做importance weighting,它通过给不同的训练样本的带价值赋予权重来平衡这种偏差。一...

2018-10-02 15:01:29

【论文精读】Curriculum Learning

CurriculumLearning论文原文:CurriculumLearning课程学习(CurriculumLearning)由Montreal大学的Bengio教授团队在2009年的ICML会议上提出,主要思想是模仿人类学习的特点,由简单到困难来学习课程(在机器学习里就是容易学习的样本和不容易学习的样本),这样容易使模型找到更好的局部最优,同时加快训练的速度。Abstract人...

2018-10-01 08:56:57

【论文精读】MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels

MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels原文地址:MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels补充证明:Su...

2018-08-10 11:26:49

【论文精读】Knowledge Transfer with Jacobian Matching

Knowledge Transfer with Jacobian Matching原文链接:Knowledge Transfer with Jacobian Matching

2018-08-09 19:38:29

【论文精读】Deep Learning and the Information Bottleneck Principle

DeepLearningandtheInformationBottleneckPrinciple原文链接:DeepLearningandtheInformationBottleneckPrinciple上次读了《DeepLearningunderPrivilegedInformationUsingHeteroscedasticDropout》这篇文章,...

2018-07-28 11:15:06

【论文精读】Dropout: A Simple Way to Prevent Neural Networks from Overfitting

Dropout:ASimpleWaytoPreventNeuralNetworksfromOverfitting原文链接:Dropout:ASimpleWaytoPreventNeuralNetworksfromOverfitting来填坑了,上次读了《DeepLearningunderPrivilegedInformationUsingHe...

2018-07-26 22:41:29

【论文精读】Deep Learning under Privileged Information Using Heteroscedastic Dropout

Deep Learning under Privileged Information Using Heteroscedastic Dropout原文链接:Deep Learning under Privileged Information Using Heteroscedastic Dropout模型和代码:Learned models and the source code这篇文章发...

2018-07-21 21:43:20

【论文精读】3D Shape Segmentation

3D Shape Segmentation with Projective Convolutional Networks原文地址:3D Shape Segmentation with Projective Convolutional Networks数据和代码:Data and codeAbstract这篇文章介绍了一种分割3D物体的深度架构,此架构结合了Fully Convo...

2018-07-18 14:28:36

【论文精读】Multi-view Convolutional Neural Networks for 3D Shape Recognition

Multi-view Convolutional Neural Networks for 3D Shape Recognition原文地址:Multi-view Convolutional Neural Networks for 3D Shape Recognition 代码和数据:Code and data这篇文章使用三维物体Multi-view(多视角)的二位渲染图片作为训练数据,基...

2018-07-14 11:04:33

【论文精读】A Support Vector Clustering Method

A Support Vector Clustering Method原文地址:A Support Vector Clustering Method本文介绍了一种支持向量聚类的方法。Abstract本文展示了使用支持向量进行数据聚类的方法,使用核技巧将数据从低维映射到高维,在高维空间中,边界是超球面,低维中边界显示为不规则的几何形状。Describing Cluster ...

2018-07-12 10:52:45

【论文精读】SVM for Clustering

A Support Vector Method for Clustering原文地址:A Support Vector Method for Clustering本文介绍了一种基于SVM的聚类方法,核心思想是用高斯核的SVM找到多个能够包围数据的半径最小的超球。使用此方法不用预先确定类别的结构和个数。Abstract聚类问题可以用参数化或非参数化的方法处理。参数化方法往往限制于其表...

2018-07-11 12:02:54

【李宏毅深度学习】Tips for Training Deep Neural Network

李宏毅深度学习_Tips for Training Deep Neural Network本文是李宏毅深度学习 (2015)的学习笔记,主要介绍了在训练DNN过程中的不同阶段用到的一些技巧。本文所用到的图示主要来自课堂ppt。原视频地址:李宏毅深度学习 (2015)概述想要提高深度学习的效率和收获比较好的结果,可以从以上五部分入手,下面分别从每个部分入手,介绍一些常用于深度...

2018-05-25 10:20:46

【李宏毅深度学习】Backpropagation

本文是李宏毅深度学习 (2015)的学习笔记,主要介绍了神经网络Backpropagation算法的推导过程。本文所用到的图示均来自课堂ppt。原视频地址:[李宏毅深度学习 (2015)][1]

2018-05-23 12:01:20
勋章 我的勋章
  • 持之以恒
    持之以恒
    授予每个自然月内发布4篇或4篇以上原创或翻译IT博文的用户。不积跬步无以至千里,不积小流无以成江海,程序人生的精彩需要坚持不懈地积累!