Yann LeCun, one of the founders of Deep Learning, had large contribution on hand-written character recognition in early dates, and proposed CNN (Convolutional Neural Network), which drastically improved recognition capability for hand-written characters. CNN is now a critical key for Deep Learning. From Yann LeCun’s first proposal of LeNet, to those winning models in ImageNet, such as VGGNet, GoogLeNet, ResNet, etc. (Please refer to [Image Classification](https://github.com/PaddlePaddle/book/tree/develop/image_classification)Course) CNN achieved a series of astonishing results in Image Classification.
Yann LeCun, one of the founders of Deep Learning, had large contribution on hand-written character recognition in early dates, and proposed CNN (Convolutional Neural Network), which drastically improved recognition capability for hand-written characters. CNN is now a critical key for Deep Learning. From Yann LeCun’s first proposal of LeNet, to those winning models in ImageNet, such as VGGNet, GoogLeNet, ResNet, etc. (Please refer to [Image Classification](https://github.com/PaddlePaddle/book/tree/develop/image_classification)chapter) CNN achieved a series of astonishing results in Image Classification.
[LeNet-5](http://yann.lecun.com/exdb/lenet/) is one of the simplest Convolutional Neural Networks. Fig. 6. shows its architecture: 2 dimensional image input is fed into two sets of convolutional layer and pooling layer, then it is fed into fully connected layer and softmax classifier. The following three properties of convolution enable LeNet-5 to better recognize images than Multilayer fully-connected perceptrons:
- 3D properties of neurons: a convolutional layer is organized by width, height and depth. Neurons in each layer are connected to only a small region in previous layer. This region is called receptive field.
- Local connection: CNN utilizes local space correlation by connecting local neurons. This design guarantees learned filter has strong response to local input features. Stacking many such layers leads non-linear filter becomes more and more global. This allows the network to first obtain good representation for a small parts of input, then combine them to represent larger region.
- Sharing weights: In CNN, computation is iterated with shared parameters (weights and bias) to form afeature map. This means all neurons in the same depth of output respond to the same feature. This allows detecting a feature regardless of its position in the input, and enables a property of translation equivariance.
For more details of Convolutional Neural Network , please refer to [Stanford open course](http://cs231n.github.io/convolutional-networks/) and [Image Classification](https://github.com/PaddlePaddle/book/blob/develop/image_classification/README.md) chapter。