k-Nearest Neighbor

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/bryant_meng/article/details/83478386

CS231n课程笔记翻译：图像分类笔记（上）
CS231n课程笔记翻译：图像分类笔记（下）

---

---

1 With N examples, how fast are training and prediction?

• Train O(1)
• predict O(N)

This is bad: we want classifiers that are fast at prediction; slow for training is ok.

2 hyper-parameters（choices about the algorithm that we set rather than learn）

• What is the best distance to use?
• What is the best value of k to use?

3 k-Nearest Neighbor on images never used

• Very slow at test time

• Distance metrics on pixels are not informative
  

• Curse of dimensionality（维数灾难）
  维数越高，需要填充的样本指数级增长
  

4 Difference between L1 and L2

demo: http://vision.stanford.edu/teaching/cs231n-demos/knn/

机器学习中的范数规则化之（一）L0、L1与L2范数

5 Algorithm

The kNN classifier consists of two stages:

• During training, the classifier takes the training data and simply remembers it
• During testing, kNN classifies every test image by comparing to all training images and transfering the labels of the k most similar training examples
• The value of k is cross-validated

5.1 下载数据集

apt-get install wget
cd cs231n/datasets/
sh get_datasets.sh

数据集构成

Training data shape:  (50000, 32, 32, 3)
Training labels shape:  (50000,)
Test data shape:  (10000, 32, 32, 3)
Test labels shape:  (10000,)

Database of deep learning（Classification and Object detection ）