The hidden layers are either convolutional, pooling or fully connected.
https://en.wikipedia.org/wiki/Convolutional_neural_network
Convolutional layers apply a convolution operation to the input, passing the result to the next layer. The convolution emulates the response of an individual neuron to visual stimuli.[7]
Each convolutional neuron processes data only for its receptive field. Tiling allows CNNs to tolerate translation of the input image (eg. translation, rotation, perspective distortion) .[clarification needed]
Although fully connected feedforward neural networks can be used to learn features as well as classify data, it is not practical to apply this architecture to images. A very high number of neurons would be necessary even in a shallow architecture (opposite of deep). The convolution operation brings a solution to this problem as it reduces the number of free parameters, allowing the network to be deeper with fewer parameters.[8] In other words, it resolves the vanishing or exploding problems in training traditional multi-layer neural networks with many layers by using backpropagation.
最新文章
- shell 套用expect
- HashSet源码详解
- 谷歌开源项目Google Preview Image Extractor(PIEX) (附上完整demo代码)
- ios中的几种多线程实现
- [老老实实学WCF] 第三篇 在IIS中寄存服务
- C#中保留2位小数
- Android之HTTP网络通信--GET传递
- 原生态的ajax代码
- Django_ORM_字段属性
- UIManager
- Spark GraphX快速入门
- Sqlserver自动优化
- CentOS No manual entry for man 没有 xx 的手册页条目
- BugkuCTF 域名解析
- 自学Aruba1.4-Aruba体系结构-产品线
- 大津法---OTSU算法
- JS 8-2 再谈原型
- (转)ElasticSearch学习
- BZOJ4813或洛谷3698 [CQOI2017]小Q的棋盘
- MVC ---- EF高级增删改