深度学习应用干货奉上:
1、自然语言处理(1):Word Embedding--介绍
zouxy9的博客:Deep Learning(深度学习):学习笔记整理,一共八篇,是很基础的内容
http://blog.csdn.net/zouxy09/article/details/8775360/
有趣的机器学习:最简明入门指南
http://blog.jobbole.com/67616/
深度学习如何入门?
http://www.zhihu.com/question/26006703
Residual Networks :
介绍一下2015 ImageNet中分类任务的冠军——MSRA何凯明团队的Residual Networks
http://blog.csdn.net/abcjennifer/article/details/50514124
image classification with deep learning常用模型
image classification常用的cnn模型,针对cifar10(for 物体识别),mnist(for 字符识别)& ImageNet(for 物体识别)做一个model 总结 介绍了一下这些网络的结构
http://blog.csdn.net/abcjennifer/article/details/42493493
HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection 论文讲解,Faster-rcnn中的proposal提取网络RPN由于特征图的粗糙,在小目标及大IOU阈值情况下的检测率低。论文提出了HyperNet,综合低层,中间层和高层特征获得了较高的recall率http://blog.csdn.net/cv_family_z/article/details/51135025
目标检测“A MultiPath Network for Object Detection”
对Fast-RCNN方法做了三个小的修改:(1)检测器能够访问多层特征,(2)foveal结构多尺度提取目标上下文信息,(3)在多个IOU下优化损失函数
http://blog.csdn.net/cv_family_z/article/details/51159619
跟踪“Visual Tracking with Fully Convolutional Networks”
对VGG16特征分析
http://blog.csdn.net/cv_family_z/article/details/50748236
Going deeper with convolutions
Googlenet,22层的深度网络。充分利用了网络中的计算资源,通过增加网络的宽度及深度实现。
http://blog.csdn.net/cv_family_z/article/details/50603406
SSD: Single Shot MultiBox Detector
本文算是 Faster R-CNN, YOLO 算法的改进版吧,它将检测和分类融合到一起去了,对每个可能的检测框赋予一个类别的概率。
http://blog.csdn.net/cv_family_z/article/details/50474679
Striving for Simplicity: The All Convolutional Net :全卷积网络
http://blog.csdn.net/cv_family_z/article/details/50403365
From Facial Parts Responses to Face Detection: A Deep Learning Approach:公开代码,用CNN进行人脸局部属性检测,然后各个部件综合起来得到人脸检测结果。
http://blog.csdn.net/cv_family_z/article/details/50233481
论文提要 Deep Face Recognition:公开代码
http://blog.csdn.net/cv_family_z/article/details/49868979
DeepID-Net:multi-stage and deformable deep CNNs for object detection:Rcnn改进
http://blog.csdn.net/cv_family_z/article/details/49588969
行人检测“Pedestrian Detection with Unsupervised Multi-Stage Feature Learning”
http://blog.csdn.net/cv_family_z/article/details/49276833
车型识别“Vehicle Type Classification Using a Semisupervised Convolutional Neural Network"
http://blog.csdn.net/cv_family_z/article/details/49154585
论文提要“Learning Deepface Representation”
http://blog.csdn.net/cv_family_z/article/details/48975027
论文提要“Taking a Deeper Look at Pedestrians”
http://blog.csdn.net/cv_family_z/article/details/48053535
论文提要“Pedestrian Detection aided by Deep Learning Semantic Tasks”
http://blog.csdn.net/cv_family_z/article/details/47259677
如何简单形象又有趣地讲解神经网络是什么?
http://daily.zhihu.com/story/4424412
深度学习笔记1(卷积神经网络)
http://blog.csdn.net/lu597203933/article/details/46575779
DeepLearnToolBox中CNN源码解析
http://blog.csdn.net/lu597203933/article/details/46576017
CNN(卷积神经网络)、RNN(循环神经网络)、DNN(深度神经网络)的内部网络结构有什么区别
https://www.zhihu.com/question/34681168
针对Faster RCNN具体细节以及源码的解读之SmoothL1Loss层
http://blog.csdn.net/xyy19920105/article/details/50421225
归一化化定义
http://www.cnblogs.com/njustyxy/archive/2011/06/10/2077926.html
UFLDL中文教程
http://ufldl.stanford.edu/wiki/index.php/UFLDL教程
介绍:使用卷积神经网络的图像缩放.
http://engineering.flipboard.com/2015/05/scaling-convnets/
归一化化定义
http://www.cnblogs.com/njustyxy/archive/2011/06/10/2077926.html
基于Theano的深度学习(Deep Learning)框架Keras学习随笔-12-核心层
如何在Caffe中配置每一个层的结构
http://demo.netfoucs.com/danieljianfeng/article/details/42929283
本文来源:
人工智能大数据与深度学习
领取专属 10元无门槛券
私享最新 技术干货