note of convolutional neural networks

Slice the image into pieces.

2.1 Multiply each image pixel by the corresponding feature pixels.

2.2 Add the match result and get average

3.1. Try any possible features

3.2. Repeat 1. on other feature. = Convolution Layers.

Set window size and get the maximun in the window:


Goal: Get similar pattern, but smaller.

After training by training steps 1-4, we can form the Fully Connected Layer and use it to vote:

2.1 Use Backprop to select Parameters of Learning

2.2 Error = right answer - actual answer


2.3 Use Gradient Descent to minimize error

CNN can be only used for image like problems. (ex. sound, text)
<=> If the solution of the problem is the same after the data column changes, then the problem is not suitable to use CNN
(ex. customer information)

Image: Ok

Sound: Ok

Text: OK

Customer Data : X