跳转至

吴恩达公开课-04

1. Motivations

1.1 Non-linear hypotheses

对于non-linear classification,尽管可以在logistic regression中添加多项式项来解决,但当feature较多时,很难列举全所有的多项式项,因此需要non-linear hypothesis

1.2 Neurons and the Brain

"one learning algorithm"

2. Neural Networks

2.1 Model Representation I

Dendrite -> cell body -> axon

  • input lalyer
  • hidden layer
  • output layer

a_i^{(j)}: activation of unit i in layer j

\theta^{(j)}: layer j to j+1

a_1^{(2)}=g(\theta_{10}^{(1)}x_0+\theta_{11}^{(1)}x_1+\theta_{12}^{(1)}x_2+\theta_{13}^{(1)}x_3)
a_2^{(2)}=g(\theta_{20}^{(1)}x_0+\theta_{21}^{(1)}x_1+\theta_{22}^{(1)}x_2+\theta_{23}^{(1)}x_3)
a_3^{(2)}=g(\theta_{30}^{(1)}x_0+\theta_{31}^{(1)}x_1+\theta_{32}^{(1)}x_2+\theta_{33}^{(1)}x_3)
h_\theta(x)=a_1^3=g(\theta_{10}^{(2)}a_0^{(2)}+\theta_{11}^{(2)}a_1^{(2)}+\theta_{12}^2a_{(2)}^{(2)}+\theta_{13}^{(2)}a_3^{(2)})
size(\theta^{(j)})=len(j+1)*[len(j)+1]

添加x_0=a_0^2=1,这里的a_0^2: bias unit

2.2 Model Representation II

vectorize

z^{(j+1)}=\theta^{(j)}a^{(j)}$$ $$a^{(j+1)}=g(\theta^{(j+1)})

等于拿a_{(2)}作为输入,进行logistic regression的求解

3. Applications

3.1 Examples and Intuitions I

AND: h_\theta(x)=g(20x_1+20x_2-30)
OR: h_\theta(x)=g(20x_1+20x_2-10)

3.2 Examples and Intuitions II

NOT: h_\theta(x)=g(10-20x)
((NOT\ x_1)\ AND\ (NOT\ x_2)): h_\theta(x)=g(10-20x_1-20x_2)

可以用AND, OR, NOT\ AND\ NOT组合XNOR

越多层网络可以表达越复杂的网络

3.3 Multiclass Classification