我是wangxiao-23158_高分内容_个人页-阿里云开发者社区

发表了文章 2017-12-25

一文读懂深度强化学习算法 A3C （Actor-Critic Algorithm）

一文读懂深度强化学习算法 A3C （Actor-Critic Algorithm） 2017-12-25 16:29:19 　　对于 A3C 算法感觉自己总是一知半解，现将其梳理一下，记录在此，也给想学习的小伙伴一个参考。

发表了文章 2017-12-21

18 Issues in Current Deep Reinforcement Learning from ZhiHu

深度强化学习的18个关键问题 from: https://zhuanlan.zhihu.com/p/32153603 85 人赞了该文章深度强化学习的问题在哪里？未来怎么走？哪些方面可以突破？这两天我阅读了两篇篇猛文A Brief Survey of Deep Reinforcement Learning 和 Deep Reinforcement Learning: An Overview ，作者排山倒海的引用了200多篇文献，阐述强化学习未来的方向。

发表了文章 2017-12-17

（转）ResNet, AlexNet, VGG, Inception: Understanding various architectures of Convolutional Networks

ResNet, AlexNet, VGG, Inception: Understanding various architectures of Convolutional Networks by KOUSTUBH 　　this blog from:　http://cv-tricks.

发表了文章 2017-12-10

深度强化学习之：模仿学习（imitation learning）

深度强化学习之：模仿学习（imitation learning） 2017.12.10 　　　　本文所涉及到的模仿学习，则是从给定的展示中进行学习。机器在这个过程中，也和环境进行交互，但是，并没有显示的得到 reward。

发表了文章 2017-12-08

论文笔记之：Collaborative Deep Reinforcement Learning for Joint Object Search

Collaborative Deep Reinforcement Learning for Joint Object Search CVPR 2017 Motivation：　　传统的 bottom-up object region proposals 的方法，由于提取了较多的 proposal，导致后续计算必须依赖于抢的计算能力，如 GPU 等。

发表了文章 2017-11-28

论文笔记之：Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach

Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach 2017.11.28 Introduction：　　人脸属性的识别在社会交互，提供了非常广泛的信息，包括：the person’s ...

发表了文章 2017-11-22

到底什么是 ROI Pooling Layer ???

到底什么是 ROI Pooling Layer ??? 只知道 faster rcnn 中有 ROI pooling, 而且其他很多算法也都有用这个layer 来做一些事情，如：SINT，检测的文章等等。

发表了文章 2017-10-25

论文笔记：Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments 2017-10-25 16:38:23 　【Project Page】https://blog.

发表了文章 2017-10-18

论文笔记： Dual Deep Network for Visual Tracking

论文笔记： Dual Deep Network for Visual Tracking 2017-10-17 21:57:08 　　先来看文章的流程吧。。。　　　　　　可以看到，作者所总结的三个点在于：　　1. 文章将边界和形状信息结合到深度网络中。

发表了文章 2017-10-16

(zhuan) Attention in Neural Networks and How to Use It

Adam Kosiorek About Attention in Neural Networks and How to Use It this blog comes from: http://akosiorek.

发表了文章 2017-09-15

论文笔记：Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking

Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking 本文目标在于 tracking performance 和 efficiency 之间达到一种平衡。

发表了文章 2017-08-31

(转) The care and maintenance of your adviser

The care and maintenance of your adviser Ever since the advent of graduate school, students have complained about their advisers.

发表了文章 2017-08-17

Basic Mathematics You Should Mastered

Basic Mathematics You Should Mastered 2017-08-17 21:22:40 1. Statistical distance In statistics, probability theory, and information theory, ...

发表了文章 2017-08-17

(zhuan) Building Convolutional Neural Networks with Tensorflow

Ahmet Taspinar Home About Contact Building Convolutional Neural Networks with Tensorflow Posted on augustus 15, 2017 adminPosted in c...

发表了文章 2017-08-13

Some tutorials and conclusions about deep learning framework ---- 【pytorch】

1. install the pytorch version 0.1.11 ## Version 0.1.11 ## python2.7 and cuda 8.0 pip install http://download.

发表了文章 2017-08-08

Ubuntu yindaoxiufu 引导修复（Boot Repair)

Ubuntu yindaoxiufu 引导修复（Boot Repair) from: http://blog.csdn.net/piaocoder/article/details/50589667 1.

发表了文章 2017-08-02

Tutorials on training the Skip-thoughts vectors for features extraction of sentence.

Tutorials on training the Skip-thoughts vectors for features extraction of sentence. 　　1. Send emails and download the training dataset.

发表了文章 2017-07-29

(zhuan) Variational Autoencoder: Intuition and Implementation

Agustinus Kristiadi's Blog TECH BLOG TRAVEL BLOG PORTFOLIO CONTACT ABOUT Variational Autoencoder: Intuition and Implementation There are two...

发表了文章 2017-07-20

(zhuan) 资源|TensorFlow初学者必须了解的55个经典案例

资源|TensorFlow初学者必须了解的55个经典案例 2017-05-27 全球人工智能 >>>>>>欢迎投稿：news@top25.cn

发表了文章 2017-07-20

(zhuan) 自然语言处理中的Attention Model：是什么及为什么

自然语言处理中的Attention Model：是什么及为什么 2017-07-13 张俊林待字闺中要是关注深度学习在自然语言处理方面的研究进展，我相信你一定听说过Attention Model（后文有时会简称AM模型）这个词。

发表了文章 2017-07-18

NLP--- How to install the tool NLTK in Ubuntu ?

NLP--- How to install the tool NLTK in Ubuntu ? 1. open the website of NLTK and download it. 　　https://pypi.

发表了文章 2017-07-11

Paper Reading: Perceptual Generative Adversarial Networks for Small Object Detection

Perceptual Generative Adversarial Networks for Small Object Detection 2017-07-11 19:47:46 CVPR 2017 　　This paper use GAN to handle the issue of s...

发表了文章 2017-07-10

论文笔记之：Natural Language Object Retrieval

论文笔记之：Natural Language Object Retrieval 2017-07-10 16:50:43 　　本文旨在通过给定的文本描述，在图像中去实现物体的定位和识别。大致流程图如下：　　　　此处，作者强调了一点不同之处：　　Natural language ob...

发表了文章 2017-07-02

Paper Reading: In Defense of the Triplet Loss for Person Re-Identification

In Defense of the Triplet Loss for Person Re-Identification 2017-07-02 14:04:20 This blog comes from: http://blog.csdn.net/shuzfan/article/details/70069822 Paper: https://arxiv.org/abs/1703.07737 Github: https://github.com/VisualComputingInstitute/triplet-reid Introduction Re-ID和图像检索有点类似。

发表了文章 2017-07-01

(zhuan) Attention in Long Short-Term Memory Recurrent Neural Networks

Attention in Long Short-Term Memory Recurrent Neural Networks by Jason Brownlee on June 30, 2017 in Deep Learning The Encoder-Decoder architecture i...

发表了文章 2017-06-28

论文笔记之：Deep Attributes Driven Multi-Camera Person Re-identification

Deep Attributes Driven Multi-Camera Person Re-identification 2017-06-28 21:38:55 　【Motivation】　　本文的网络设计主要分为三个部分：　　　　Stage 1: Fully-supervised ...

发表了文章 2017-06-26

NLP related basic knowledge with deep learning methods

NLP related basic knowledge with deep learning methods 2017-06-22 　　First things first >>>>>>>>>>>>>>>>>>>>>>>> Some great blogs: 　　1.

发表了文章 2017-06-21

论文笔记之：Optical Flow Estimation using a Spatial Pyramid Network

　　Optical Flow Estimation using a Spatial Pyramid Network spynet 　　本文将经典的 spatial-pyramid formulation 和 deep learning 的方法相结合，以一种 coarse to fine approach，进行光流的计算。

发表了文章 2017-06-19

（转）Introductory guide to Generative Adversarial Networks (GANs) and their promise!

Introductory guide to Generative Adversarial Networks (GANs) and their promise! Introduction Neural Networks have made great progress.

发表了文章 2017-06-12

论文笔记之：DualGAN: Unsupervised Dual Learning for Image-to-Image Translation

DualGAN: Unsupervised Dual Learning for Image-to-Image Translation2017-06-12 21:29:06 　　引言部分：　　本文提出一种对偶学习模式的 GAN 网络结构来进行 image to image translation。

发表了文章 2017-06-11

论文笔记之 SST: Single-Stream Temporal Action Proposals

SST: Single-Stream Temporal Action Proposals2017-06-11 14:28:00 　　本文提出一种时间维度上的 proposal 方法，进行行为的识别。

发表了文章 2017-06-06

论文笔记之：Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning

论文笔记之：Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning 2017-06-06 21:43:53 　　这篇文章的 Motivation 来自于 MDNet：　　　本文所...

发表了文章 2017-06-02

Tutorial: Generate BBox or Rectangle to locate the target obejct

Tutorial: Generate BBox or Rectangle to locate the target obejct 　　 1 clc;close all;clear all; 2 Img=imread('/home/wangxiao/Documents/files/Vis...

发表了文章 2017-05-15

关于 Image Caption 中测试时用到的 beam search算法

关于beam search 之前组会中没讲清楚的 beam search，这里给一个案例来说明这种搜索算法。在 Image Caption的测试阶段，为了得到输出的语句，一般会选用两种搜索方式，一种是贪心采样的方法（sample），即：每个时刻都选择输出概率最大的那个单词，作为当前时刻的输出。

发表了文章 2017-05-10

论文阅读: End-to-end Learning of Action Detection from Frame Glimpses in Videos

End-to-End Learning of Action Detection from Frame Glimpses in Videos CVPR 2016 　　Motivation: 　　　本文主要是想借助空间的 attention model 来去协助进行行人识别的工作。

发表了文章 2017-05-09

（转）Awesome Courses

Awesome Courses Introduction There is a lot of hidden treasure lying within university pages scattered across the internet.

发表了文章 2017-05-08

Sample Classification Code of CIFAR-10 in Torch

Sample Classification Code of CIFAR-10 in Torch from: http://torch.ch/blog/2015/07/30/cifar.html require 'xlua' require 'optim' require 'nn' require 'image' local c = require 'trepl.

发表了文章 2017-05-03

(转) Learning Deep Learning with Keras

Learning Deep Learning with Keras Piotr Migdał - blog Projects Articles Publications Resume About Photos Learning Deep Learning with Keras 30 Apr...

发表了文章 2017-05-02

(zhuan) Recurrent Neural Network

Recurrent Neural Network 2016年07月01日 Deep learning Deep learning 字数:24235 this blog from: http://jxgu.

发表了文章 2017-04-28

论文阅读：Prominent Object Detection and Recognition: A Saliency-based Pipeline

论文阅读：Prominent Object Detection and Recognition: A Saliency-based Pipeline 如上图所示，本文旨在解决一个问题：给定一张图像，我们最应该关注哪些区域？怎么将其分割出来？这是一个什么东东？这三个子问题为一体。

发表了文章 2017-04-27

物体检测算法 SSD 的训练和测试

物体检测算法 SSD 的训练和测试 GitHub：https://github.com/stoneyang/caffe_ssd Paper： https://arxiv.org/abs/1512.

发表了文章 2017-04-27

Deep Learning framework --- MexNet 安装，测试，以及相关问题总结

Deep Learning framework --- MexNet 安装，测试，以及相关问题总结一、安装：参考博文：http://www.open-open.com/lib/view/open1448030000650.html Note： gcc g++ 需要 4.8 版本。

发表了文章 2017-04-18

Install and Compile MatConvNet: CNNs for MATLAB --- Deep Learning framework

Install and Compile MatConvNet: CNNs for MATLAB --- Deep Learning framework 2017-04-18 10:19:35 If you want to use matlab convnet, you just install according to the following tutorials: 1.

发表了文章 2017-04-11

论文笔记之：Learning Cross-Modal Deep Representations for Robust Pedestrian Detection

Learning Cross-Modal Deep Representations for Robust Pedestrian Detection 2017-04-11 19:40:22 Motivation：　　本文主要是考虑了在光照极端恶劣的情况下，如何充分的利用 thermal data 进行协助学习提升可见光图像的特征表达能力，而借鉴了 ICCV 2015 年的一个文章，称为：监督迁移的方法，以一种模态的特征为 label，以监督学习的方式实现无监督学习。

发表了文章 2017-04-10

Latex 经常见到的问题和解决方法

Latex 经常见到的问题和解决方法 2017-04-10 22:05:48 1. IEEE 模板添加通信作者的时候，总是无法正常显示（脚注无法正常显示）：　　因为 IEEE默认是屏蔽了这个功能，需要在编辑的 .

发表了文章 2017-04-08

The frequent used operation in Linux system

The frequently used operation in Linux system 2017-04-08 12:48:09 1. mount the hard disk: 　　#: fdisk -l %% use this operation to check how many and what disk it found in the computer.

发表了文章 2017-04-07

(zhuan) Speech and Natural Language Processing

Speech and Natural Language Processing obtain from this link: https://github.com/edobashira/speech-language-processing A curated list of speech and natural language processing resources.

发表了文章 2017-04-01

Optical Flow related Tutorials

Optical Flow related Tutorials 2017-04-01 10:50:55 Reference: 1. http://blog.csdn.net/carson2005/article/details/7581642 2.

发表了文章 2017-03-30

The issus in Age Progression/Regression by Conditional Adversarial Autoencoder (CAAE)

The issus in Age Progression/Regression by Conditional Adversarial Autoencoder (CAAE) Today I tried a new project named: Face-Aging-CAAE Paper Name...

发表了文章 2017-03-26

(转) 干货 | 图解LSTM神经网络架构及其11种变体（附论文）

干货 | 图解LSTM神经网络架构及其11种变体（附论文） 2016-10-02 机器之心选自FastML 作者：Zygmunt Z. 机器之心编译参与：老红、李亚洲就像雨季后非洲大草原许多野生溪流分化成的湖泊和水洼，深度学习已经分化成了各种不同的专门架构。

热门

活动广场

任务中心

开发者评测

高校计划

乘风者计划

训练营

阿里云MVP

话题

直播

下载

镜像站

技术资料

插件

我是wangxiao-23158_个人页

个人介绍

擅长的技术

一文读懂 深度强化学习算法 A3C （Actor-Critic Algorithm）

18 Issues in Current Deep Reinforcement Learning from ZhiHu

（转）ResNet, AlexNet, VGG, Inception: Understanding various architectures of Convolutional Networks

深度强化学习之：模仿学习（imitation learning）

论文笔记之：Collaborative Deep Reinforcement Learning for Joint Object Search

论文笔记之：Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach

到底什么是 ROI Pooling Layer ???

论文笔记：Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

论文笔记： Dual Deep Network for Visual Tracking

(zhuan) Attention in Neural Networks and How to Use It

论文笔记：Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking

(转) The care and maintenance of your adviser

Basic Mathematics You Should Mastered

(zhuan) Building Convolutional Neural Networks with Tensorflow

Some tutorials and conclusions about deep learning framework ---- 【pytorch】

Ubuntu yindaoxiufu 引导修复（Boot Repair)

Tutorials on training the Skip-thoughts vectors for features extraction of sentence.

(zhuan) Variational Autoencoder: Intuition and Implementation

(zhuan) 资源|TensorFlow初学者必须了解的55个经典案例

(zhuan) 自然语言处理中的Attention Model：是什么及为什么

NLP--- How to install the tool NLTK in Ubuntu ?

Paper Reading: Perceptual Generative Adversarial Networks for Small Object Detection

论文笔记之：Natural Language Object Retrieval

Paper Reading: In Defense of the Triplet Loss for Person Re-Identification

(zhuan) Attention in Long Short-Term Memory Recurrent Neural Networks

论文笔记之：Deep Attributes Driven Multi-Camera Person Re-identification

NLP related basic knowledge with deep learning methods

论文笔记之：Optical Flow Estimation using a Spatial Pyramid Network

（转）Introductory guide to Generative Adversarial Networks (GANs) and their promise!

论文笔记之：DualGAN: Unsupervised Dual Learning for Image-to-Image Translation

论文笔记之 SST: Single-Stream Temporal Action Proposals

论文笔记之：Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning

Tutorial: Generate BBox or Rectangle to locate the target obejct

关于 Image Caption 中测试时用到的 beam search算法

论文阅读: End-to-end Learning of Action Detection from Frame Glimpses in Videos

（转）Awesome Courses

Sample Classification Code of CIFAR-10 in Torch

(转) Learning Deep Learning with Keras

(zhuan) Recurrent Neural Network

论文阅读：Prominent Object Detection and Recognition: A Saliency-based Pipeline

物体检测算法 SSD 的训练和测试

Deep Learning framework --- MexNet 安装，测试，以及相关问题总结

Install and Compile MatConvNet: CNNs for MATLAB --- Deep Learning framework

论文笔记之：Learning Cross-Modal Deep Representations for Robust Pedestrian Detection

Latex 经常见到的问题和解决方法

The frequent used operation in Linux system

(zhuan) Speech and Natural Language Processing

Optical Flow related Tutorials

The issus in Age Progression/Regression by Conditional Adversarial Autoencoder (CAAE)

(转) 干货 | 图解LSTM神经网络架构及其11种变体（附论文）

一文读懂 深度强化学习算法 A3C （Actor-Critic Algorithm）

18 Issues in Current Deep Reinforcement Learning from ZhiHu

（转）ResNet, AlexNet, VGG, Inception: Understanding various architectures of Convolutional Networks

深度强化学习之：模仿学习（imitation learning）

论文笔记之：Collaborative Deep Reinforcement Learning for Joint Object Search

论文笔记之：Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach

到底什么是 ROI Pooling Layer ???

论文笔记：Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

论文笔记： Dual Deep Network for Visual Tracking

(zhuan) Attention in Neural Networks and How to Use It

论文笔记：Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking

(转) The care and maintenance of your adviser

Basic Mathematics You Should Mastered

一文读懂深度强化学习算法 A3C （Actor-Critic Algorithm）

一文读懂深度强化学习算法 A3C （Actor-Critic Algorithm）