lecture 3,Loss Function and Optimization

1，處理指數計算問題時，爲了防止overflow 的處理方法（我還是存在疑問，這相當與求超級大的數的導數）：

f = np.array([123, 456, 789]) # example with 3 classes and each having large scores
p = np.exp(f) / np.sum(np.exp(f)) # Bad: Numeric problem, potential blowup

# instead: first shift the values of f so that the highest number is 0:
f -= np.max(f) # f becomes [-666, -333, 0] 
p = np.exp(f) / np.sum(np.exp(f)) # safe to do, gives the correct answer

2,關於LR爲凸函數，可以保證最值（中科大面試時被問到）？？？

3，svm的代碼復現，看了很多遍svm的思路，也被面試問到過svm，不如嘗試復現一次或者trvarse吧。。。