Deep Many hidden layers 152 layers Special structure 3.57% 7.3% 6.7% 16.4% AlexNet VGG GoogleNet Residual Net (2012) (2014) (2014) (2015) 4口◆4⊙t1三1=，￥9QC
. .. .. .. .. .. .. .. .. .. .. .. .. .. .. .. .. .. .. ..
Output Layer Probability: Softmax layer as the output layer ■1>y:>0 ■∑yi=1 Softmax Layer e 20 0.88 2 0.12 e ◆2=e 0.05 =0 口卡+8·三色，进分双0
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Output Layer
Table of Contents 深度学习简介 Neural Network Goodness of Function Pick the Best Function 前馈神经网络 Tips for Deep Learning 卷积神经网络(Convolutional Neural Network,.CNN) 循环神经网络(Recurrent Neural Network,RNN Keras CNN in Keras RNN in Keras 4口卡404三·1怎生0C
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Table of Contents 深度学习简介 Neural Network Goodness of Function Pick the Best Function 前馈神经网络 Tips for Deep Learning 卷积神经网络（Convolutional Neural Network, CNN） 循环神经网络（Recurrent Neural Network, RNN） Keras CNN in Keras RNN in Keras
Three Steps for Deep Learning Step 1:define a set of function Step 2:goodness of function Step 3:pick the best function 口·三4，进分双C
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Three Steps for Deep Learning
Training Data Preparing training data:images and their labels "3 The learning target is defined on the training data. 4口◆4⊙t1三1=，￥9QC
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Training Data