Notes - deep learning context finishing: 2 loss function.

• Vein structure

1. 结构
2. 损失
3. 优化

---

Question:
Why softmax
existing problems softmax
cross entropy loss of meaning

• Digression: After a clear principle, it can be improved

使用 softmax 的时候，有一个默认的前提，就是每个物体只属于一类
比如人脸识别，每张脸只能对应一个人

---

Thinking:

1. sigmod binary classification of Loss, the difference between multi-classification Loss of softmax
2. The difference sigmod and softmax

---

Euclidean loss

---

---

---

---

• Loss weighting function

---

• Sample weights

---

• To improve softmax loss