Convolutional Neural Networks(2):Sparse Interactions, Receptive Field and Parameter Sharing
Sparse Interactions, Receptive Field and Parameter Sharing是整个CNN深度网络的核心部分,我们用本文来具体分析其原理。
首先我们考虑Feedforward Neural Network,L层的输出矩阵,等于L层的输入矩阵与L层的权重矩阵做矩阵乘法,而后进行非线性变换。也就是说,L层的每一个输出数据,与L层的每一个输入数据都有关系。若输入数据是m维,输出数据是n维,则存在m*n个权重项来表征输入与输出间的关系。所以,Forward-propagation的时间复杂度是O(m*n)。
根据在机器学习方面的实际经验看来,weight过多导致的问题主要有:难以训练,overfitting等。所以CNN引入Sparse Interactions来解决稠密权重(Dense Weight)的问题。以一个核宽度为3的网络来举例:下一层的输出S3,只与3个输入x2,x3,x4有关。

x2,x3,x4称为s3的Receptive Field,这其实是一个从神经科学舶来的概念。这里引用wikipedia关于Receptive Field的一段原文吧:
“Work by Hubel and Wiesel in the 1950s and 1960s showed that cat and monkey visual cortexes contain neurons that individually respond to small regions of the visual field. Provided the eyes are not moving, the region of visual space within which visual stimuli affect the firing of a single neuron is known as its receptive field. Neighboring cells have similar and overlapping receptive fields. Receptive field size and location varies systematically across the cortex to form a complete map of visual space. The cortex in each hemisphere represents the contralateral visual field.”
在位于枕叶(Occiptal Lobe)的大脑视觉皮质(Visual Cortex)中,存在一些神经元,每个单独的神经元对应一个Receptive Field。这也是Biological Neural Network在图像处理方面启发Artificial Neural Network的地方。如果仅仅到此为止,我们的确降低了模型的复杂度,并且把Weight Matrix缩小至k*n,k是kernel的大小。也就是说,在下一层中共有n个neurons,每一个neuron仅仅与上一层的k个值有关。
但Weight Sharing概念的引入,则将模型进一步简化,从而达到:weight的个数仅仅与kernel的大小有关。对于Kernel 和 Weight Sharing,可以这样理解:L层与L-1层之间并没有固定的连接线,而是采取动态绑定,在两层之间存在一个小小的window,称为kernel。透过该窗口可以看到原图像的一小部分,随着窗口不断从左到右,从上到下滑动,整个图片都被扫描。而扫描到的图片区,和kernel来做卷积,生成feature map。而整张图片,共享的weight其实就是kernel的值,如果kernel改变,整张图的扫描结果(feature map)将会改变。过程如下图:


另一种理解方式如下图,实际情况也非动态扫描,而是存在权重相同的通路:

Convolutional Neural Networks(2):Sparse Interactions, Receptive Field and Parameter Sharing的更多相关文章
- [转]An Intuitive Explanation of Convolutional Neural Networks
An Intuitive Explanation of Convolutional Neural Networks https://ujjwalkarn.me/2016/08/11/intuitive ...
- An Intuitive Explanation of Convolutional Neural Networks
https://ujjwalkarn.me/2016/08/11/intuitive-explanation-convnets/ An Intuitive Explanation of Convolu ...
- Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
Understanding the Effective Receptive Field in Deep Convolutional Neural Networks 理解深度卷积神经网络中的有效感受野 ...
- 机器视觉:Convolutional Neural Networks, Receptive Field and Feature Maps
CNN 大概是目前 CV 界最火爆的一款模型了,堪比当年的 SVM.从 2012 年到现在,CNN 已经广泛应用于CV的各个领域,从最初的 classification,到现在的semantic se ...
- 卷积神经网络用于视觉识别Convolutional Neural Networks for Visual Recognition
Table of Contents: Architecture Overview ConvNet Layers Convolutional Layer Pooling Layer Normalizat ...
- 卷积神经网络LeNet Convolutional Neural Networks (LeNet)
Note This section assumes the reader has already read through Classifying MNIST digits using Logisti ...
- [C6] Andrew Ng - Convolutional Neural Networks
About this Course This course will teach you how to build convolutional neural networks and apply it ...
- A Beginner's Guide To Understanding Convolutional Neural Networks(转)
A Beginner's Guide To Understanding Convolutional Neural Networks Introduction Convolutional neural ...
- (转)A Beginner's Guide To Understanding Convolutional Neural Networks Part 2
Adit Deshpande CS Undergrad at UCLA ('19) Blog About A Beginner's Guide To Understanding Convolution ...
随机推荐
- C#设计模式:命令模式(Command Pattern)
一,什么是命令模式(Command Pattern)? 命令模式:将请求封装成命令对象,请求的具体执行由命令接收者执行: 二,如下代码 using System; using System.Colle ...
- spark复习笔记(2)
之前工作的时候经常用,隔了段时间,现在学校要用学的东西也忘了,翻翻书谢谢博客吧. 1.什么是spark? Spark是一种快速.通用.可扩展的大数据分析引擎,2009年诞生于加州大学伯克利分校AMPL ...
- 剑指offer学习--实现单例模式
只能生成一个实例的类是为了实现单例模式的类型. 加同步锁前后两次判断实例是否已存在 我们只是在实例还没有创建之前加锁操作,以保证只有一个线程创建出实例.而当实例已经创建之后,我们已经不需要再做加锁操作 ...
- python OpenCV视频的读取及保存
import cv2 cap = cv2.VideoCapture('rtsp://admin:hik12345@192.168.3.160/Streaming/Channels/1') fourcc ...
- Docker实战部署应用——Tomcat
Tomcat 部署 拉取tomcat镜像 docker pull tomcat:8 创建tomcat容器 创建tomcat容器用于 Web应用,并且进行目录映射 docker run -id --na ...
- JSZip
/*! JSZip - A Javascript class for generating and reading zip files<http://stuartk.com/jszip> ...
- Maya2014下载安装与激活
目录 1. 更多推荐 2. 下载地址 2.1. OneDrive 2.2. 其他下载地址 3. 激活步骤 1. 更多推荐 其他Maya版本的下载与激活:https://www.cnblogs.com/ ...
- union 横向组合
select sum(zs) zs,sum(zl) zl,sum(ts) ts,sum(lxcbw) lxcbw,sum(bz) bz,sum(sfzqt) sfzqtfrom (select cou ...
- pwd 显示当前所在的工作路径
1.功能说明 pwd命令是“print working directory ”首字母缩写,显示当前目录的绝对路径. 2.语法格式 pwd [option] pwd 选项 3.命令参数 参数 参数说明 ...
- 【LeetCode】动态规划(下篇共39题)
[600] Non-negative Integers without Consecutive Ones [629] K Inverse Pairs Array [638] Shopping Offe ...