6. 類神經網路
• 神經元
• 構成類神經網路的基本單位。
• 可用機器學習的方式,調整參數,控制其輸出值。
n
W1
W2
x1
x2
b
Wb
y
nin = w1x1 + w2x2 + wb
nout =
1
1 + e nin
nin
nout
y =
1
1 + e (w1x1+w2x2+wb)
7. 類神經網路
• 二元分類:AND
Gate
x1
x2
y
0
0
0
0
1
0
1
0
0
1
1
1
(0,0)
(0,1)
(1,1)
(1,0)
0
1
n
20
20
b
-‐30
y
x1
x2
y =
1
1 + e (20x1+20x2 30)
20x1 + 20x2 30 = 0
8. 類神經網路
• 類神經網路:由許多神經元組成,可模擬較複雜的函數。
x
y
n11
n12
n21
n22
W12,y
W12,x
b
W11,y
W11,b
W12,b
b
W11,x
W21,11
W22,12
W21,12
W22,11
W21,b
W22,b
z1
z2
Input
Layer
Hidden
Layer
Output
Layer
36. Reference
• Vector
Space
of
Semanrics
• Thomas
Mikolov
et
al.
Efficient
Estimation
of
Word
Representation
in
Vector
Space
• Recurrent
Neural
Networks
Language
Model
• Thomas
Mikolov
et
al.
Recurrent
Neural
Networks
based
language
model
• Convolutional
Neural
Networks
Sentence
Model
• Nal
Kalchbrenner
et
al.
A
Convolutional
Neural
Networks
for
Modeling
Sentences
• Chinese
Poetry
Generation
with
Recurrent
Neural
Networks
• Xingxing
Zhang
and
Mirella
Lapata.
Chinese
Poetry
Generation
with
Recurrent
Neural
Networks
37. Further
Reading
• Neural
Networks
Language
Models
• Training
Neural
Networks
• Training
Recurrent
Neural
Networks
Training