Visual recognition _7.20

内容：http://cs231n.github.io/classification/

Image Classification: Data-driven Approach, k-Nearest Neighbor, train/val/test splits

• 图像分类可能遇到的challenge
• Nearest Neighbor Classifier
  
  • using pixel-wise differences to compare two images

Linear classification: Support Vector Machine, Softmax

• Interpreting a linear classifier
  
  • 高维空间的线性分类器
    
    • 
  • W is that each row of W corresponds to a template (or sometimes also called a prototype) for one of the classes. The score of each class for an image is then obtained by comparing each template with the image using an inner product (or dot product) one by one to find the one that “fits” best.
• bias trick：把常数项放到w中，在input_x的基础上增加1个维度
  
  •