Slide 1

Slide 1 text

5 . 1 2

Slide 2

Slide 2 text

• : D !(#) 1 ∇!(#) • L 1 ) ) ( 1 S G G 1 & '()*+, = .(/ 012 .(⋯ .(/ 2 '()*+, + 5(2)))) 62 67 68 69 /(:) ⋯ ⋯ ⋯ ⋯ ⋯ ⋯ ;2 ;7 /(:<2) = − 1 = = + 1

Slide 3

Slide 3 text

. . ! ℎ($) ℎ(&) ℎ(') (($) ((&) ((') ℎ(')= ( ' ( & ( $ ! *+(,) *- = *+(,) *.(/) 0 *.(/) *.(1) 0 *.(1) *- •

Slide 4

Slide 4 text

. . ! ℎ($) ℎ(&) '($) '(&)

Slide 5

Slide 5 text

. .

Slide 6

Slide 6 text

No content

Slide 7

Slide 7 text

(

Slide 8

Slide 8 text

.( )

Slide 9

Slide 9 text

Slide 10

Slide 10 text

( )

Slide 11

Slide 11 text

2'+ )NN 2 #)0%&1&-" (3*,) .( !/$→ → Residual Connection, Batch Nomalization() ! Loss func ! Loss func

Slide 12

Slide 12 text

: Residual Connection –– F(x) (→-!()) F(x) + x → & " - Identity Mapping ': -*&%,+' ./$ # Identity – [1] He, Kaiming, et al. "Identity mappings in deep residual networks." European Conference on Computer Vision. Springer, Cham, 2016. . .

Slide 13

Slide 13 text

. . (2.33) (2.34)

Slide 14

Slide 14 text

0 1 . 2 C2 2 " 3 2 3 2 ) 2 2 ( 3 23 2 !"#$ !" %"&$ %"#$ %" %"&$ '() '() '() '*+, '*+, -"#$ = /(!"#$ ) -" -"&$ %" !" M I NR 2 '*+, O L '() : input P / L !" = '*+, 2 !"#$ + '() %" ,, L

Slide 15

Slide 15 text

2 . 3 !" #$% &% !" #$' !" #$( !% #$% !% #$' !% #$( !' #$% !' #$' !' #$( !( #$% !( #$' !( #$( &' &( )% )' )(

Slide 16

Slide 16 text

2 . 3 !" #$% &% !" #$' !" #$( !% #$% !% #$' !% #$( !' #$% !' #$' !' #$( !( #$% !( #$' !( #$( &' &( )% )' )(

Slide 17

Slide 17 text

2 . 3 !" #$% &% !" #$' !" #$( !% #$% !% #$' !% #$( !' #$% !' #$' !' #$( !( #$% !( #$' !( #$( &' &( )% )' )(

Slide 18

Slide 18 text

2 . 3 !" #$% &% !" #$' !" #$( !% #$% !% #$' !% #$( !' #$% !' #$' !' #$( !( #$% !( #$' !( #$( &' &( )% )' )( • 23 !* # 1

Slide 19

Slide 19 text

: !"#$ !%& '( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/

Slide 20

Slide 20 text

. - •

Slide 21

Slide 21 text

Slide 22

Slide 22 text

) (

Slide 23

Slide 23 text

8 99 2 :9.8 9 9 6 5 3 2 2 5 2 28 79 8 3 9 1 56 2 59 7 /0-

Slide 24

Slide 24 text

-5 1 02 1 25 58 8 ./ 8 .2 0 8

Slide 25

Slide 25 text

22/1 444 1 1 - 2 3--.-.3-. 11

Slide 26

Slide 26 text

http://deeplearning.stanford.edu/wiki/index .php/Feature_extraction_using_convolution

Slide 27

Slide 27 text

/885 6 0: 6. 5 5

Slide 28

Slide 28 text

Slide 29

Slide 29 text

RNN Vanishing/Exploding Gradient : !"#$ !%& '( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/