| notebook.community

notebook.community

Contents:

Lecture 2a - An overview of the main types of neural network architecture

Lecture 2b: Perceptrons: The first generation of neural networks

Lecture 2c: A geometrical view of perceptrons

Lecture 2d: Why the learning works

Lecture 2e: What perceptrons can't do

1

2

3

右边蓝色的字在讲什么？

4

好像是说红色箭头中的weights都是同一个值。关于Recurrent还要后面看了具体课程才行。（是的，是这个意思。）

5

6

7

8

这一页视频里没讲到

9

10

11

12

13

14

15

16

17

18

19

20

为什么the problem is convex。我的理解是，按凸集的定义，任意两点之间的连线都在集合内部。凸优化课程https://class.stanford.edu/courses/Engineering/CVX101/Winter2014/about

21

22

23

24

25

26

27

28

29

30

31

32



In [ ]: