Why CNN for Image Some patterns are much smaller than the whole image A neuron does not have to see the whole image to discover the pattern. Connecting to small region with less parameters “beak"detector
Why CNN for Image • Some patterns are much smaller than the whole image A neuron does not have to see the whole image to discover the pattern. “beak” detector Connecting to small region with less parameters
Why CNN for Image The same patterns appear in different re gions. “upper-left beak"detector Do almost the same thing They can use the same set of parameters. “middle beak” detector
Why CNN for Image • The same patterns appear in different re gions. “upper-left beak” detector “middle beak” detector They can use the same set of parameters. Do almost the same thing
Why CNN for Image Subsampling the pixels will not change the obiaed bird subsampling We can subsample the pixels to make image smaller Less parameters for the network to process the image
Why CNN for Image • Subsampling the pixels will not change the object subsampling bird bird We can subsample the pixels to make image smaller Less parameters for the network to process the image
The whole cat dog Convolution Max Pooling Can repeat Fully Connected many times Feedforward network Convolution Max Pooling Flatten
The whole CNN Fully Connected Feedforward network cat dog …… Convolution Max Pooling Convolution Max Pooling Flatten Can repeat many times
Convolutional Neural Network Stes 1 Step 3. define a Step 2: pick the Convolutional goodness best Neural Network of function function +“monkey"←→0 “cat'"←→1 CNN →“dog→可 Convolution,Max target Pooling,fully connected Learning:Nothing special,just gradient descent
Convolutional Neural Network Learning: Nothing special, just gradient descent …… CNN “monkey” “cat” “dog” Convolution, Max Pooling, fully connected 1 0 0 … … target Step 1: define a set of function Step 2: goodness of function Step 3: pick the best function Convolutional Neural Network