I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
16
,
No
.
4
,
A
u
g
u
s
t
20
26
,
p
p
.
1
6
6
9
~
1
6
7
6
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
16
i
4
.
pp
1
6
6
9
-
1
6
7
6
1669
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
E
dito
r
ia
l
From da
ta to i
nte
llig
ence: fo
unda
ti
o
ns o
f
lea
rning
sy
stems,
represen
tatio
n,
a
nd com
putatio
na
l
perce
p
tion
T
o
le
Su
t
ik
no
1,
2
1
F
a
c
u
l
t
y
o
f
I
n
d
u
s
t
r
i
a
l
T
e
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
si
t
a
s A
h
ma
d
D
a
h
l
a
n
,
Y
o
g
y
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
2
Emb
e
d
d
e
d
S
y
st
e
m
a
n
d
P
o
w
e
r
El
e
c
t
r
o
n
i
c
s
R
e
sea
r
c
h
G
r
o
u
p
,
Y
o
g
y
a
k
a
r
t
a
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
K
ey
w
o
r
d
s
:
C
o
m
p
u
tatio
n
al
p
er
ce
p
tio
n
Data
to
in
tellig
en
ce
Dee
p
lear
n
in
g
I
n
tellig
en
t sy
s
tem
s
Ma
ch
in
e
in
tellig
en
ce
s
y
s
tem
s
R
ep
r
esen
tatio
n
lear
n
in
g
Th
e
ra
p
id
e
v
o
l
u
ti
o
n
o
f
in
telli
g
e
n
t
sy
ste
m
s
h
a
s
sh
ift
e
d
th
e
f
o
c
u
s
o
f
e
lec
tri
c
a
l
a
n
d
c
o
m
p
u
ter
e
n
g
in
e
e
rin
g
fr
o
m
iso
late
d
d
a
ta
p
ro
c
e
ss
in
g
to
wa
rd
in
teg
ra
ted
m
o
d
e
ls
o
f
m
a
c
h
i
n
e
c
o
g
n
it
i
o
n
.
Th
is
e
d
it
o
rial
in
tr
o
d
u
c
e
s
a
fo
u
n
d
a
ti
o
n
a
l
p
e
rsp
e
c
ti
v
e
o
n
m
a
c
h
in
e
in
tell
ig
e
n
c
e
sy
ste
m
s,
e
m
p
h
a
siz
in
g
t
h
e
tran
s
fo
rm
a
ti
o
n
fro
m
ra
w
d
a
ta
to
m
e
a
n
in
g
fu
l
in
telli
g
e
n
c
e
th
ro
u
g
h
lea
rn
in
g
sy
ste
m
s,
re
p
re
se
n
tatio
n
m
e
c
h
a
n
ism
s,
a
n
d
c
o
m
p
u
tati
o
n
a
l
p
e
rc
e
p
ti
o
n
.
I
n
c
o
n
tem
p
o
ra
ry
AI
-
d
riv
e
n
e
n
v
ir
o
n
m
e
n
ts,
i
n
telli
g
e
n
c
e
is
n
o
l
o
n
g
e
r
d
e
fin
e
d
so
lely
b
y
a
lg
o
ri
t
h
m
ic
p
e
rfo
rm
a
n
c
e
,
b
u
t
b
y
t
h
e
a
b
il
it
y
to
c
o
n
str
u
c
t
stru
c
tu
re
d
re
p
re
se
n
tatio
n
s
o
f
th
e
w
o
rld
a
n
d
in
ter
p
re
t
c
o
m
p
le
x
m
u
l
ti
m
o
d
a
l
sig
n
a
ls.
Lea
rn
in
g
sy
ste
m
s,
p
a
rti
c
u
larly
th
o
se
g
ro
u
n
d
e
d
in
m
a
c
h
in
e
lea
rn
i
n
g
a
n
d
d
e
e
p
lea
rn
in
g
p
a
ra
d
i
g
m
s,
se
rv
e
a
s
th
e
c
o
re
m
e
c
h
a
n
ism
e
n
a
b
li
n
g
t
h
is
tra
n
sfo
rm
a
ti
o
n
.
Re
p
re
se
n
tatio
n
lea
rn
in
g
p
r
o
v
id
e
s
th
e
b
r
id
g
e
b
e
twe
e
n
u
n
str
u
c
tu
re
d
d
a
ta
a
n
d
a
b
stra
c
t
k
n
o
wle
d
g
e
,
w
h
il
e
c
o
m
p
u
tati
o
n
a
l
p
e
rc
e
p
ti
o
n
e
n
a
b
les
m
a
c
h
in
e
s
to
in
terp
re
t
v
isu
a
l,
a
u
d
it
o
ry
,
a
n
d
se
n
s
o
r
-
b
a
se
d
i
n
fo
rm
a
ti
o
n
i
n
re
a
l
ti
m
e
.
To
g
e
t
h
e
r,
th
e
se
c
o
m
p
o
n
e
n
ts
f
o
rm
th
e
fo
u
n
d
a
ti
o
n
a
l
a
rc
h
it
e
c
tu
re
o
f
in
telli
g
e
n
t
sy
ste
m
s
th
a
t
u
n
d
e
r
p
in
e
m
e
rg
in
g
a
p
p
li
c
a
ti
o
n
s
i
n
e
n
g
i
n
e
e
rin
g
,
a
u
t
o
m
a
ti
o
n
,
a
n
d
c
y
b
e
r
-
p
h
y
sic
a
l
e
n
v
iro
n
m
e
n
ts.
Th
is
e
d
it
o
rial
se
ts
th
e
sta
g
e
fo
r
u
n
d
e
rsta
n
d
in
g
in
telli
g
e
n
c
e
a
s
a
n
e
m
e
rg
e
n
t
c
o
m
p
u
tat
i
o
n
a
l
c
o
n
stru
c
t,
h
i
g
h
l
ig
h
ti
n
g
it
s
ro
le
a
s
th
e
first
p
h
a
se
in
th
e
b
ro
a
d
e
r
c
o
g
n
it
iv
e
in
telli
g
e
n
c
e
s
y
ste
m
s
c
o
n
ti
n
u
u
m
t
h
a
t
p
ro
g
re
ss
e
s
to
wa
rd
a
d
a
p
ti
v
e
,
a
u
t
o
n
o
m
o
u
s,
a
n
d
so
c
io
-
c
o
g
n
it
iv
e
s
y
ste
m
s
in
fu
tu
re
re
se
a
rc
h
d
irec
ti
o
n
s.
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
T
o
le
Su
tik
n
o
Ma
s
ter
Pro
g
r
am
o
f
E
lectr
ical
E
n
g
in
ee
r
in
g
,
Facu
lty
o
f
I
n
d
u
s
t
r
ial
T
ec
h
n
o
lo
g
y
,
U
n
iv
er
s
itas
Ah
m
ad
Dah
lan
UAD
4
th
C
am
p
u
s
,
So
u
th
R
in
g
R
o
ad
,
T
am
an
a
n
,
B
an
g
u
n
tap
a
n
,
B
an
tu
l,
Yo
g
y
ak
ar
ta
5
5
1
6
6
,
I
n
d
o
n
esia
E
m
ail: to
le@
u
ad
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
ev
o
lu
tio
n
o
f
in
tellig
en
t
s
y
s
tem
s
m
ar
k
s
o
n
e
o
f
th
e
m
o
s
t
p
r
o
f
o
u
n
d
p
ar
ad
ig
m
s
s
h
if
ts
in
m
o
d
er
n
elec
tr
ical
an
d
co
m
p
u
te
r
en
g
in
e
er
in
g
.
Fo
r
d
ec
a
d
es,
co
m
p
u
tatio
n
h
as
b
ee
n
u
n
d
er
s
to
o
d
as
a
d
eter
m
in
is
tic
p
r
o
ce
s
s
in
wh
ich
ex
p
licitly
d
esig
n
ed
alg
o
r
ith
m
s
tr
an
s
f
o
r
m
p
r
e
d
ef
i
n
ed
in
p
u
ts
in
to
p
r
ed
ictab
le
o
u
tp
u
ts
.
W
ith
in
th
is
class
ical
p
ar
ad
ig
m
,
in
t
ellig
en
ce
was
lar
g
ely
p
er
ce
iv
ed
as
an
ad
d
itio
n
al
f
u
n
ctio
n
al
lay
er
im
p
lem
en
ted
th
r
o
u
g
h
h
an
d
cr
a
f
ted
r
u
les,
s
y
m
b
o
lic
r
ea
s
o
n
in
g
,
o
r
ca
r
e
f
u
lly
en
g
in
e
er
ed
d
ec
is
io
n
l
o
g
ic.
T
h
is
p
er
s
p
ec
tiv
e
h
as
s
h
ap
ed
g
en
er
atio
n
s
o
f
co
m
p
u
tatio
n
al
s
y
s
tem
s
wh
o
s
e
ca
p
ab
ilit
ies
u
ltima
t
ely
d
ep
en
d
ed
o
n
t
h
e
co
m
p
leten
ess
o
f
h
u
m
an
-
d
esig
n
ed
alg
o
r
ith
m
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
16
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
6
6
9
-
1676
1670
Ho
wev
er
,
d
esp
ite
th
e
r
em
ar
k
a
b
le
ad
v
a
n
ce
s
o
f
m
o
d
er
n
ar
tifi
cial
in
tellig
en
ce
,
th
e
f
u
n
d
am
e
n
tal
n
atu
r
e
o
f
m
ac
h
i
n
e
in
tellig
en
ce
r
em
ai
n
s
in
co
m
p
letely
u
n
d
er
s
to
o
d
.
C
o
n
tem
p
o
r
ar
y
in
tellig
en
t
s
y
s
t
em
s
ca
n
lear
n
f
r
o
m
ex
p
er
ien
ce
,
co
n
s
tr
u
ct
in
ter
n
al
r
ep
r
esen
tatio
n
s
,
g
en
e
r
alize
a
cr
o
s
s
d
iv
er
s
e
task
s
,
ad
ap
t
to
p
r
ev
io
u
s
ly
u
n
s
ee
n
s
itu
atio
n
s
,
an
d
g
en
er
ate
in
cr
ea
s
in
g
ly
s
o
p
h
is
ticated
b
eh
av
io
r
s
with
o
u
t
ex
p
licit
r
u
le
s
p
ec
if
icatio
n
.
T
h
ese
ac
h
iev
em
en
ts
h
a
v
e
tr
an
s
f
o
r
m
ed
n
u
m
er
o
u
s
en
g
i
n
ee
r
in
g
ap
p
licatio
n
s
a
n
d
d
em
o
n
s
tr
ated
u
n
p
r
ec
ed
e
n
ted
co
m
p
u
tatio
n
al
ca
p
a
b
ilit
ies.
Yet
th
ey
ar
e
s
till
p
r
ed
o
m
in
a
n
tly
ev
alu
ated
in
ter
m
s
o
f
p
r
ed
ictiv
e
ac
cu
r
ac
y
,
o
p
tim
izatio
n
p
er
f
o
r
m
a
n
ce
,
c
o
m
p
u
tatio
n
al
e
f
f
icien
cy
,
o
r
b
en
ch
m
ar
k
s
co
r
es,
r
ath
e
r
th
an
th
e
u
n
d
er
ly
in
g
p
r
in
cip
les
th
at
g
iv
e
r
is
e
to
in
t
ellig
en
ce
its
elf
.
C
o
n
s
eq
u
en
tly
,
cu
r
r
e
n
t
en
g
in
ee
r
in
g
p
e
r
s
p
ec
tiv
es
lar
g
ely
e
x
p
lain
h
o
w
in
tellig
en
t
s
y
s
tem
s
p
er
f
o
r
m
,
b
u
t
p
r
o
v
i
d
e
o
n
ly
lim
ited
in
s
ig
h
t
in
to
wh
y
in
tellig
en
t
b
eh
a
v
io
r
e
m
er
g
es
f
r
o
m
co
m
p
u
tatio
n
.
T
h
is
d
is
tin
ctio
n
s
u
g
g
ests
th
at
in
tellig
en
ce
s
h
o
u
ld
n
o
t
b
e
r
eg
a
r
d
ed
m
e
r
ely
as
a
m
o
r
e
ad
v
an
ce
d
f
o
r
m
o
f
co
m
p
u
tatio
n
,
b
u
t
as
a
n
em
er
g
en
t
c
o
g
n
itiv
e
p
r
o
ce
s
s
g
o
v
er
n
ed
b
y
th
e
d
y
n
a
m
ic
in
te
r
ac
tio
n
o
f
lear
n
in
g
,
r
ep
r
esen
tatio
n
,
a
n
d
p
e
r
ce
p
tio
n
.
T
ak
en
to
g
et
h
er
,
th
ese
o
b
s
er
v
atio
n
s
p
o
in
t
to
a
d
ee
p
er
s
cien
tific
ch
allen
g
e
th
at
ex
te
n
d
s
b
ey
o
n
d
im
p
r
o
v
in
g
th
e
p
er
f
o
r
m
a
n
ce
o
f
ar
tific
ial
in
tellig
en
ce
s
y
s
tem
s
.
T
h
ey
in
v
ite
a
m
o
r
e
f
u
n
d
am
e
n
tal
q
u
esti
o
n
:
Ho
w
d
o
es
in
tellig
en
ce
em
er
g
e
f
r
o
m
co
m
p
u
tatio
n
?
I
f
in
cr
ea
s
in
g
ly
p
o
we
r
f
u
l
p
r
o
ce
s
s
o
r
s
,
la
r
g
er
d
atasets
,
an
d
m
o
r
e
s
o
p
h
is
ticated
alg
o
r
ith
m
s
alo
n
e
ca
n
n
o
t
f
u
lly
ex
p
lain
in
tellig
en
t
b
eh
av
io
r
,
wh
at
f
u
n
d
am
e
n
tal
m
ec
h
an
is
m
s
en
ab
le
co
m
p
u
tatio
n
al
s
y
s
tem
s
to
lear
n
f
r
o
m
e
x
p
er
ien
ce
,
co
n
s
tr
u
c
t
m
ea
n
in
g
f
u
l
r
e
p
r
esen
tatio
n
s
,
p
er
ce
iv
e
c
o
m
p
lex
en
v
ir
o
n
m
en
ts
,
an
d
c
o
n
tin
u
o
u
s
ly
ad
ap
t
to
u
n
ce
r
tai
n
ty
?
Ad
d
r
ess
in
g
th
is
q
u
esti
o
n
r
eq
u
i
r
es
m
o
v
in
g
b
e
y
o
n
d
v
iewin
g
in
tellig
en
ce
as
th
e
o
u
tco
m
e
o
f
alg
o
r
ith
m
ic
ex
ec
u
tio
n
.
I
n
s
tead
,
in
tellig
en
ce
s
h
o
u
ld
b
e
u
n
d
er
s
to
o
d
as
a
co
g
n
itiv
e
p
r
o
ce
s
s
th
at
c
o
n
ti
n
u
o
u
s
ly
d
ev
elo
p
s
th
r
o
u
g
h
t
h
e
in
ter
ac
tio
n
o
f
lear
n
i
n
g
,
r
ep
r
esen
tatio
n
,
an
d
p
er
ce
p
tio
n
.
T
h
is
co
n
ce
p
tu
al
s
h
if
t
p
r
o
v
id
es
th
e
f
o
u
n
d
atio
n
f
o
r
r
e
d
ef
in
in
g
i
n
tellig
en
ce
as
a
d
y
n
am
ic
p
r
o
ce
s
s
o
f
co
g
n
itiv
e
o
r
g
an
izatio
n
r
ath
er
th
an
a
s
tatic
co
m
p
u
tatio
n
al
ca
p
ab
ilit
y
.
T
h
is
ed
ito
r
ial
d
ev
elo
p
s
a
u
n
if
ied
co
n
ce
p
tu
al
f
r
a
m
ewo
r
k
in
w
h
ich
m
ac
h
in
e
in
tellig
en
ce
is
u
n
d
er
s
to
o
d
n
o
t
as
a
co
m
p
u
tatio
n
al
ca
p
ab
ilit
y
em
b
ed
d
ed
with
in
alg
o
r
it
h
m
s
,
b
u
t
as
an
em
er
g
en
t
co
g
n
itiv
e
p
h
en
o
m
en
o
n
ar
is
in
g
f
r
o
m
th
e
c
o
n
tin
u
o
u
s
in
ter
ac
tio
n
o
f
lear
n
in
g
s
y
s
tem
s
,
r
ep
r
esen
tatio
n
lea
r
n
in
g
,
an
d
co
m
p
u
tatio
n
al
p
er
ce
p
tio
n
.
R
ath
er
th
an
o
p
e
r
atin
g
as
is
o
lated
co
g
n
itiv
e
m
ec
h
an
is
m
s
,
th
ese
co
m
p
le
m
en
tar
y
p
r
o
ce
s
s
es
co
llectiv
ely
ex
p
lain
h
o
w
r
aw
d
ata
ar
e
p
r
o
g
r
ess
iv
ely
ab
s
tr
ac
ted
in
to
m
ea
n
in
g
f
u
l
in
ter
n
al
r
ep
r
esen
tatio
n
s
th
at
s
u
p
p
o
r
t
k
n
o
wled
g
e
f
o
r
m
atio
n
,
ad
a
p
tiv
e
d
ec
is
io
n
-
m
ak
in
g
,
an
d
u
ltima
tely
th
e
em
er
g
en
ce
o
f
m
ac
h
i
n
e
in
tellig
en
ce
.
T
h
is
p
er
s
p
ec
tiv
e
estab
lis
h
es
th
e
co
n
ce
p
tu
al
f
o
u
n
d
atio
n
f
o
r
th
e
b
r
o
ad
er
I
J
E
C
E
2
0
2
6
e
d
ito
r
ial
tr
ajec
to
r
y
,
w
h
ich
f
o
llo
ws
th
e
ev
o
lu
tio
n
o
f
in
tellig
en
t
s
y
s
tem
s
f
r
o
m
f
o
u
n
d
atio
n
al
c
o
g
n
iti
o
n
to
wa
r
d
c
o
g
n
itiv
e
cy
b
er
-
p
h
y
s
ical
s
y
s
tem
s
an
d
au
to
n
o
m
o
u
s
s
o
cio
-
co
g
n
itiv
e
in
te
llig
en
ce
.
B
u
ild
in
g
u
p
o
n
th
is
p
er
s
p
ec
tiv
e,
th
e
f
o
llo
win
g
s
ec
tio
n
s
p
r
o
g
r
ess
iv
ely
d
ev
elo
p
th
e
ce
n
tr
al
ar
g
u
m
en
t
o
f
th
is
ed
ito
r
ial
b
y
tr
ac
in
g
th
e
tr
a
n
s
f
o
r
m
atio
n
f
r
o
m
d
ata
to
i
n
tellig
en
ce
.
T
h
e
d
is
cu
s
s
io
n
f
ir
s
t
ex
am
in
es
in
tellig
en
ce
as
a
h
ier
ar
ch
ical
ab
s
tr
ac
tio
n
p
r
o
ce
s
s
b
e
f
o
r
e
ex
p
lo
r
in
g
t
h
e
co
m
p
lem
e
n
tar
y
r
o
les
o
f
m
ac
h
in
e
lear
n
i
n
g
,
r
ep
r
esen
tatio
n
lear
n
in
g
,
an
d
c
o
m
p
u
tatio
n
al
p
er
ce
p
tio
n
in
th
e
f
o
r
m
atio
n
o
f
m
ac
h
in
e
co
g
n
it
io
n
.
T
o
g
eth
er
,
th
ese
in
ter
co
n
n
ec
ted
m
ec
h
an
is
m
s
estab
lis
h
th
e
in
tellectu
al
f
o
u
n
d
at
io
n
f
o
r
t
h
e
s
u
b
s
eq
u
en
t
e
v
o
l
u
ti
o
n
to
war
d
c
o
g
n
itiv
e
cy
b
er
-
p
h
y
s
ical
s
y
s
tem
s
an
d
u
ltima
tely
au
to
n
o
m
o
u
s
s
o
cio
-
co
g
n
itiv
e
s
y
s
tem
s
th
r
o
u
g
h
o
u
t
th
e
I
J
E
C
E
2
0
2
6
ed
ito
r
ial
tr
ajec
to
r
y
.
2
.
F
RO
M
DAT
A
T
O
I
N
T
E
L
L
I
G
E
NCE
Un
d
er
s
tan
d
in
g
h
o
w
in
tellig
en
ce
em
er
g
es
f
r
o
m
co
m
p
u
tatio
n
b
eg
in
s
with
re
-
ex
a
m
in
in
g
th
e
r
o
le
o
f
d
ata
its
elf
.
C
o
n
tr
ar
y
to
th
e
co
m
m
o
n
ass
u
m
p
tio
n
th
at
in
tellig
en
ce
n
atu
r
ally
in
c
r
ea
s
es
with
lar
g
er
v
o
lu
m
es
o
f
d
ata
o
r
g
r
ea
ter
co
m
p
u
tatio
n
al
p
o
wer
,
in
tellig
en
ce
d
o
es
n
o
t
ar
is
e
f
r
o
m
th
e
ac
cu
m
u
latio
n
o
f
d
at
a
alo
n
e.
R
ath
er
,
it
em
er
g
es
th
r
o
u
g
h
t
h
e
p
r
o
g
r
ess
iv
e
tr
an
s
f
o
r
m
atio
n
o
f
r
aw
o
b
s
er
v
atio
n
s
in
to
in
c
r
ea
s
in
g
ly
m
ea
n
in
g
f
u
l
a
b
s
tr
ac
tio
n
s
th
at
en
ab
le
s
y
s
tem
s
to
in
ter
p
r
et,
r
ea
s
o
n
,
an
d
ad
ap
t.
Fro
m
th
is
p
er
s
p
ec
tiv
e,
d
ata
s
h
o
u
ld
n
o
t
b
e
r
e
g
ar
d
e
d
as
th
e
en
d
p
o
i
n
t
o
f
co
m
p
u
tatio
n
,
b
u
t
as
th
e
co
g
n
itiv
e
s
u
b
s
tr
ate
f
r
o
m
wh
ich
in
f
o
r
m
atio
n
,
k
n
o
wle
d
g
e,
an
d
u
ltima
tely
in
tellig
en
ce
is
co
n
tin
u
o
u
s
ly
co
n
s
tr
u
cted
.
T
h
is
p
er
s
p
ec
tiv
e
r
ev
ea
ls
a
f
u
n
d
am
en
tal
m
is
co
n
ce
p
tio
n
th
at
h
as
ac
co
m
p
an
ied
th
e
r
ap
id
a
d
v
an
ce
m
en
t
o
f
ar
tific
ial
in
tellig
en
ce
.
T
h
e
u
n
p
r
ec
ed
e
n
ted
av
aila
b
ilit
y
o
f
la
r
g
e
-
s
ca
le
d
atasets
h
as
u
n
d
o
u
b
t
ed
ly
ac
ce
ler
ated
th
e
d
ev
elo
p
m
e
n
t
o
f
m
o
d
er
n
m
ac
h
i
n
e
lear
n
in
g
,
y
et
t
h
e
r
em
a
r
k
ab
l
e
ca
p
ab
ilit
ies
o
f
co
n
tem
p
o
r
ar
y
in
tellig
en
t
s
y
s
tem
s
ca
n
n
o
t
b
e
ex
p
lain
ed
s
im
p
ly
b
y
th
e
ab
u
n
d
a
n
ce
o
f
d
ata.
T
wo
c
o
m
p
u
tatio
n
al
s
y
s
tem
s
ex
p
o
s
ed
to
id
en
tical
d
atasets
m
ay
ex
h
i
b
it
s
u
b
s
tan
tially
d
if
f
e
r
en
t
lev
els
o
f
in
tellig
en
ce
d
ep
e
n
d
in
g
o
n
h
o
w
ef
f
ec
tiv
el
y
th
ey
o
r
g
an
ize,
r
ep
r
esen
t
,
an
d
in
ter
p
r
et
th
e
u
n
d
e
r
ly
in
g
i
n
f
o
r
m
atio
n
.
C
o
n
s
eq
u
e
n
tly
,
th
e
d
ef
in
in
g
ch
ar
a
cter
is
tic
o
f
in
t
ellig
en
ce
lies
n
o
t
in
ac
ce
s
s
to
d
ata
its
elf
,
b
u
t
in
th
e
ab
ilit
y
to
tr
an
s
f
o
r
m
d
ata
in
to
i
n
cr
ea
s
in
g
ly
in
f
o
r
m
ativ
e
an
d
s
em
an
tically
m
ea
n
in
g
f
u
l a
b
s
tr
ac
tio
n
s
.
T
h
e
ce
n
tr
al
p
r
o
p
o
s
itio
n
o
f
th
is
ed
ito
r
ial
is
th
at
in
tellig
en
ce
s
h
o
u
ld
b
e
u
n
d
er
s
to
o
d
f
u
n
d
am
e
n
tally
as
a
p
r
o
ce
s
s
o
f
h
ier
ar
ch
ical
a
b
s
tr
ac
tio
n
r
ath
er
th
an
o
n
e
o
f
d
ata
ac
cu
m
u
latio
n
.
Ab
s
tr
ac
tio
n
en
ab
les
co
m
p
u
tatio
n
a
l
s
y
s
tem
s
to
r
ed
u
ce
th
e
co
m
p
le
x
ity
o
f
th
e
ex
ter
n
al
wo
r
ld
wh
il
e
p
r
eser
v
in
g
its
ess
en
tial
s
tr
u
ctu
r
es,
r
elatio
n
s
h
ip
s
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
F
r
o
m
d
a
ta
to
i
n
tellig
en
ce
:
fo
u
n
d
a
tio
n
s
o
f le
a
r
n
in
g
s
ystems
,
r
ep
r
esen
ta
tio
n
,
a
n
d
…
(
To
le
S
u
tikn
o
)
1671
an
d
laten
t
r
e
g
u
lar
ities
.
I
n
s
te
ad
o
f
m
em
o
r
izin
g
in
d
iv
id
u
al
o
b
s
er
v
atio
n
s
,
i
n
tellig
en
t
s
y
s
tem
s
p
r
o
g
r
ess
iv
ely
co
n
s
tr
u
ct
co
m
p
ac
t
in
ter
n
al
r
e
p
r
esen
tatio
n
s
th
at
ca
p
t
u
r
e
s
tatis
tical
d
ep
en
d
en
cies,
s
em
an
ti
c
o
r
g
a
n
izatio
n
,
a
n
d
in
cr
ea
s
in
g
ly
ca
u
s
al
p
atter
n
s
ac
r
o
s
s
d
iv
er
s
e
en
v
ir
o
n
m
en
ts
.
I
n
tellig
en
ce
th
er
ef
o
r
e
em
er
g
es
n
o
t
f
r
o
m
t
h
e
ac
cu
m
u
latio
n
o
f
in
f
o
r
m
atio
n
,
b
u
t
f
r
o
m
t
h
e
co
n
tin
u
o
u
s
d
is
co
v
er
y
,
o
r
g
an
izatio
n
,
an
d
a
b
s
tr
ac
tio
n
o
f
m
ea
n
i
n
g
f
u
l
s
tr
u
ctu
r
es e
m
b
ed
d
e
d
with
in
in
f
o
r
m
atio
n
.
T
h
is
ab
s
tr
ac
tio
n
p
r
o
ce
s
s
ca
n
b
e
u
n
d
er
s
to
o
d
th
r
o
u
g
h
th
e
h
ier
ar
ch
ical
p
r
o
g
r
ess
io
n
f
r
o
m
d
ata
to
in
f
o
r
m
atio
n
,
k
n
o
wled
g
e,
a
n
d
in
tellig
en
ce
.
Data
co
n
s
is
ts
o
f
r
aw
o
b
s
er
v
atio
n
s
th
at
d
escr
ib
e
is
o
lated
ev
en
ts
with
o
u
t
co
n
tex
t
u
al
in
ter
p
r
etatio
n
.
I
n
f
o
r
m
atio
n
in
tr
o
d
u
ce
s
o
r
g
an
izatio
n
b
y
estab
lis
h
in
g
r
e
latio
n
s
h
ip
s
am
o
n
g
o
b
s
er
v
atio
n
s
,
w
h
ile
k
n
o
wled
g
e
ca
p
tu
r
es
s
tab
le
s
tr
u
ctu
r
es
th
at
en
a
b
le
g
e
n
er
aliza
tio
n
b
ey
o
n
d
in
d
iv
id
u
al
ex
am
p
les.
I
n
tellig
en
ce
r
e
p
r
esen
ts
th
e
h
ig
h
est
lev
el
o
f
th
i
s
h
ier
ar
ch
y
,
wh
er
e
s
y
s
tem
s
u
tili
ze
ac
cu
m
u
lated
k
n
o
wled
g
e
to
r
ea
s
o
n
u
n
d
er
u
n
ce
r
tain
t
y
,
p
r
ed
ict
u
n
s
ee
n
s
itu
atio
n
s
,
f
o
r
m
u
late
ad
a
p
tiv
e
d
ec
is
io
n
s
,
an
d
co
n
tin
u
o
u
s
ly
r
ef
in
e
t
h
eir
u
n
d
e
r
s
tan
d
in
g
th
r
o
u
g
h
ex
p
er
ien
ce
.
I
m
p
o
r
ta
n
tly
,
th
ese
f
o
u
r
lev
els
s
h
o
u
ld
n
o
t
b
e
in
ter
p
r
eted
as
in
d
ep
en
d
en
t
s
tag
es
b
u
t
as
co
n
tin
u
o
u
s
ly
in
ter
ac
tin
g
lay
er
s
with
in
an
e
v
o
lv
in
g
c
o
g
n
itiv
e
ar
ch
itectu
r
e.
Mo
d
er
n
i
n
tellig
en
t
s
y
s
tem
s
s
im
u
ltan
eo
u
s
ly
ac
q
u
ir
e
n
ew
d
ata,
r
eo
r
g
an
ize
i
n
f
o
r
m
a
tio
n
,
u
p
d
ate
in
te
r
n
al
k
n
o
wled
g
e
s
tr
u
ctu
r
es,
an
d
r
ev
is
e
th
ei
r
d
ec
is
io
n
-
m
ak
i
n
g
s
tr
ateg
ies.
I
n
tellig
en
ce
th
er
ef
o
r
e
em
er
g
es f
r
o
m
th
e
co
n
tin
u
o
u
s
in
ter
ac
tio
n
am
o
n
g
th
ese
lay
e
r
s
r
ath
er
th
an
f
r
o
m
a
s
eq
u
en
tial
p
r
o
ce
s
s
in
g
p
ip
elin
e.
T
h
is
p
er
s
p
ec
tiv
e
e
x
p
lain
s
w
h
y
m
o
d
er
n
m
ac
h
in
e
in
tell
ig
en
ce
ex
h
ib
its
a
d
ap
tiv
e
b
eh
av
io
r
ev
en
i
n
en
v
i
r
o
n
m
e
n
t
s
th
at
wer
e
n
ev
er
e
x
p
licitly
r
e
p
r
esen
ted
d
u
r
in
g
t
r
ain
in
g
.
T
h
e
co
m
p
u
tatio
n
al
r
ea
lizatio
n
o
f
th
is
ab
s
tr
ac
tio
n
h
ier
a
r
ch
y
i
s
m
ad
e
p
o
s
s
ib
le
th
r
o
u
g
h
lear
n
in
g
-
b
ased
p
ar
ad
ig
m
s
.
I
n
s
tead
o
f
r
ely
i
n
g
o
n
m
an
u
ally
d
esig
n
ed
s
y
m
b
o
lic
r
u
les,
co
n
tem
p
o
r
ar
y
i
n
tellig
en
t
s
y
s
tem
s
in
f
er
laten
t
s
tr
u
ctu
r
es
d
ir
ec
tly
f
r
o
m
d
ata
d
is
tr
ib
u
tio
n
s
u
s
in
g
s
tatis
tical
o
p
tim
izatio
n
an
d
r
ep
r
esen
tatio
n
lear
n
in
g
.
I
n
d
o
in
g
s
o
,
t
h
ey
g
r
ad
u
ally
c
o
n
s
tr
u
ct
in
ter
n
al
m
o
d
els
th
at
a
p
p
r
o
x
im
ate
th
e
u
n
d
er
ly
in
g
o
r
g
an
iz
atio
n
o
f
th
e
ex
ter
n
al
wo
r
ld
.
T
h
ese
lear
n
e
d
m
o
d
els
p
r
o
v
id
e
t
h
e
co
m
p
u
tatio
n
al
s
u
b
s
tr
ate
u
p
o
n
w
h
ich
r
ea
s
o
n
i
n
g
,
p
r
ed
ictio
n
,
an
d
ad
ap
tatio
n
b
ec
o
m
e
p
o
s
s
ib
le.
Per
h
ap
s
th
e
m
o
s
t
s
ig
n
if
ican
t
im
p
licatio
n
o
f
th
is
p
er
s
p
ec
tiv
e
is
th
at
in
tellig
en
ce
s
h
o
u
ld
n
ev
er
b
e
r
eg
ar
d
e
d
as a
f
in
al
co
m
p
u
tatio
n
al
o
u
tc
o
m
e.
Un
lik
e
c
o
n
v
e
n
ti
o
n
al
s
o
f
twar
e,
wh
o
s
e
f
u
n
ctio
n
ality
is
lar
g
ely
f
ix
e
d
o
n
ce
im
p
lem
e
n
ted
,
in
tellig
en
t
s
y
s
tem
s
co
n
tin
u
o
u
s
ly
r
ec
o
n
s
tr
u
ct
th
eir
in
ter
n
al
r
ep
r
e
s
en
tatio
n
s
as
n
ew
o
b
s
er
v
atio
n
s
b
ec
o
m
e
av
ailab
le
.
I
n
tellig
en
ce
is
th
e
r
ef
o
r
e
b
ette
r
u
n
d
er
s
to
o
d
as
a
n
e
v
o
lv
in
g
p
r
o
ce
s
s
o
f
k
n
o
wled
g
e
co
n
s
tr
u
ctio
n
th
an
as
a
s
tatic
co
m
p
u
tatio
n
al
ca
p
a
b
ilit
y
.
T
h
i
s
p
er
s
p
ec
tiv
e
im
m
ed
iately
r
aises
a
f
u
n
d
am
en
tal
q
u
esti
o
n
:
if
in
tellig
en
ce
em
er
g
es
th
r
o
u
g
h
h
ier
ar
ch
ical
ab
s
t
r
ac
tio
n
,
wh
at
co
m
p
u
tatio
n
al
m
ec
h
an
is
m
en
ab
les
th
ese
ab
s
tr
ac
tio
n
s
to
b
e
co
n
tin
u
o
u
s
ly
co
n
s
tr
u
cted
,
r
e
f
in
ed
,
a
n
d
r
eo
r
g
an
ized
t
h
r
o
u
g
h
o
u
t
ex
p
e
r
ien
ce
?
T
h
e
a
n
s
wer
lies
in
m
ac
h
in
e
lear
n
i
n
g
,
w
h
ich
p
r
o
v
id
es
th
e
ad
a
p
tiv
e
co
m
p
u
tatio
n
al
s
u
b
s
tr
ate
th
r
o
u
g
h
wh
ich
a
b
s
tr
ac
tio
n
b
ec
o
m
es o
p
e
r
atio
n
al
an
d
in
tellig
en
ce
p
r
o
g
r
ess
iv
ely
em
er
g
es f
r
o
m
d
ata.
3
.
M
ACH
I
N
E
L
E
AR
NING
AS
T
H
E
O
P
E
RA
T
I
O
N
AL
S
UB
ST
RA
T
E
O
F
I
NT
E
L
L
I
G
E
N
CE
I
f
h
ier
ar
ch
ical
ab
s
tr
ac
tio
n
d
e
f
in
es
th
e
co
n
ce
p
tu
al
o
r
ig
in
o
f
in
tellig
en
ce
,
an
eq
u
ally
f
u
n
d
am
en
tal
q
u
esti
o
n
im
m
e
d
iately
f
o
llo
ws:
h
o
w
ca
n
co
m
p
u
tatio
n
al
s
y
s
tem
s
co
n
tin
u
o
u
s
ly
c
o
n
s
tr
u
ct,
r
ef
in
e,
an
d
r
eo
r
g
a
n
ize
th
ese
ab
s
tr
ac
tio
n
s
th
r
o
u
g
h
e
x
p
er
ien
ce
?
T
h
e
an
s
wer
l
ies
in
m
ac
h
in
e
lear
n
in
g
,
wh
ich
p
r
o
v
id
es
th
e
ad
a
p
tiv
e
co
m
p
u
tatio
n
al
s
u
b
s
tr
ate
th
r
o
u
g
h
wh
ich
ab
s
tr
ac
tio
n
b
ec
o
m
e
s
o
p
er
atio
n
al.
R
ath
er
th
an
e
x
ec
u
tin
g
p
r
ed
ef
in
e
d
r
u
les,
lear
n
in
g
s
y
s
tem
s
p
r
o
g
r
e
s
s
iv
ely
m
o
d
if
y
th
eir
i
n
ter
n
al
m
o
d
els
in
r
esp
o
n
s
e
to
d
ata,
all
o
win
g
in
tellig
en
ce
to
em
er
g
e
as a
d
y
n
am
ic
co
m
p
u
ta
tio
n
al
p
r
o
ce
s
s
r
ath
er
t
h
an
a
f
ix
ed
alg
o
r
ith
m
ic
c
ap
ab
ilit
y
.
T
h
e
tr
an
s
f
o
r
m
atio
n
f
r
o
m
d
ata
in
to
in
tellig
en
ce
ca
n
n
o
t
o
cc
u
r
with
o
u
t
a
co
m
p
u
tatio
n
al
m
ec
h
an
is
m
ca
p
ab
le
o
f
co
n
tin
u
o
u
s
ly
d
is
c
o
v
er
in
g
,
r
e
f
in
in
g
,
an
d
r
e
o
r
g
a
n
izin
g
k
n
o
wled
g
e
f
r
o
m
e
x
p
e
r
ien
ce
.
W
h
ile
th
e
p
r
ev
io
u
s
s
ec
tio
n
estab
lis
h
ed
a
b
s
tr
ac
tio
n
as
th
e
d
ef
i
n
in
g
ch
ar
ac
ter
is
tic
o
f
in
tellig
en
ce
,
ab
s
tr
ac
tio
n
alo
n
e
r
e
m
ain
s
a
co
n
ce
p
tu
al
p
r
in
cip
le
u
n
til
it
ca
n
b
e
o
p
er
atio
n
alize
d
with
i
n
a
c
o
m
p
u
tatio
n
al
f
r
am
ewo
r
k
.
Ma
ch
in
e
lear
n
in
g
p
r
o
v
id
es
t
h
is
o
p
er
atio
n
al
s
u
b
s
tr
ate
b
y
en
a
b
lin
g
co
m
p
u
tatio
n
al
s
y
s
tem
s
to
c
o
n
s
tr
u
ct,
u
p
d
ate,
a
n
d
o
p
tim
ize
in
ter
n
al
m
o
d
els
d
ir
ec
tly
f
r
o
m
d
ata
r
ath
er
th
an
f
r
o
m
ex
p
licitly
p
r
o
g
r
a
m
m
ed
r
u
les.
I
n
th
is
s
en
s
e,
m
ac
h
in
e
lear
n
in
g
is
n
o
t
s
im
p
ly
an
o
th
er
c
o
m
p
u
tatio
n
al
tech
n
iq
u
e;
it
r
e
p
r
esen
ts
th
e
en
g
in
ee
r
in
g
r
ea
lizatio
n
o
f
a
d
ap
tiv
e
in
tellig
en
ce
.
T
h
is
p
er
s
p
ec
tiv
e
f
u
n
d
am
en
tall
y
r
ed
ef
in
es
co
m
p
u
tatio
n
its
elf
.
C
las
s
ical
co
m
p
u
tatio
n
al
s
y
s
tem
s
ex
ec
u
te
ex
p
licitly
d
esig
n
ed
alg
o
r
ith
m
s
wh
o
s
e
b
eh
av
io
r
r
em
ain
s
la
r
g
ely
u
n
ch
an
g
ed
a
f
ter
d
e
p
lo
y
m
en
t
b
ec
au
s
e
th
eir
co
m
p
u
tatio
n
al
lo
g
ic
is
p
r
ed
et
er
m
in
ed
d
u
r
in
g
s
y
s
tem
d
esig
n
.
L
ea
r
n
in
g
s
y
s
tem
s
,
b
y
co
n
tr
ast,
co
n
tin
u
o
u
s
ly
r
eo
r
g
a
n
ize
th
eir
in
ter
n
al
c
o
m
p
u
tatio
n
al
s
tr
u
ctu
r
es
in
r
esp
o
n
s
e
to
ex
p
er
ien
ce
,
all
o
win
g
c
o
m
p
u
tatio
n
its
elf
to
ev
o
lv
e
alo
n
g
s
id
e
ch
a
n
g
in
g
e
n
v
ir
o
n
m
e
n
ts
.
C
o
n
s
eq
u
en
tly
,
in
t
ellig
en
ce
is
n
o
lo
n
g
er
v
iewe
d
as
th
e
ex
ec
u
tio
n
o
f
p
r
ed
ef
in
e
d
in
s
tr
u
ctio
n
s
,
b
u
t
as
th
e
co
n
tin
u
o
u
s
r
eo
r
g
an
iza
tio
n
o
f
i
n
ter
n
al
co
m
p
u
tatio
n
al
m
o
d
els
th
r
o
u
g
h
in
ter
ac
tio
n
with
d
ata.
T
h
is
s
h
i
f
t
r
ep
r
esen
ts
o
n
e
o
f
th
e
m
o
s
t
s
ig
n
if
ican
t
co
n
ce
p
tu
al
tr
an
s
f
o
r
m
atio
n
s
in
m
o
d
e
r
n
elec
tr
ical
an
d
co
m
p
u
ter
en
g
in
ee
r
in
g
,
r
e
d
ef
in
in
g
co
m
p
u
tatio
n
f
r
o
m
s
tatic
alg
o
r
ith
m
ex
ec
u
tio
n
in
to
a
d
ap
tiv
e
k
n
o
wled
g
e
co
n
s
tr
u
ctio
n
.
T
h
e
d
ef
in
in
g
co
n
tr
ib
u
tio
n
o
f
m
ac
h
in
e
lear
n
in
g
is
th
er
ef
o
r
e
n
o
t
p
r
ed
ictio
n
its
elf
,
b
u
t
ad
ap
tiv
e
m
o
d
el
co
n
s
tr
u
ctio
n
.
Pre
d
ictio
n
is
m
er
ely
o
n
e
o
b
s
er
v
a
b
le
o
u
tco
m
e
o
f
a
m
u
ch
d
ee
p
er
p
r
o
ce
s
s
in
wh
ich
s
y
s
tem
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
16
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
6
6
9
-
1676
1672
co
n
tin
u
o
u
s
ly
esti
m
ate
u
n
d
er
l
y
in
g
s
tr
u
ctu
r
es,
i
n
f
er
r
elatio
n
s
h
ip
s
am
o
n
g
v
a
r
iab
les,
an
d
r
ef
in
e
th
eir
in
ter
n
al
r
ep
r
esen
tatio
n
o
f
r
ea
lity
.
T
h
e
tr
u
e
co
m
p
u
tatio
n
al
p
o
wer
o
f
m
ac
h
in
e
lear
n
in
g
lies
in
its
ab
ilit
y
to
tr
a
n
s
f
o
r
m
in
co
m
p
lete,
n
o
is
y
,
an
d
h
ig
h
-
d
i
m
en
s
io
n
al
o
b
s
er
v
atio
n
s
in
t
o
in
cr
ea
s
in
g
ly
co
h
er
en
t
m
o
d
els
th
a
t
s
u
p
p
o
r
t
r
ea
s
o
n
i
n
g
an
d
d
ec
is
io
n
-
m
ak
in
g
u
n
d
er
u
n
ce
r
tain
ty
.
Fr
o
m
th
is
p
er
s
p
ec
tiv
e,
lear
n
in
g
is
n
o
t
an
a
u
x
ili
ar
y
co
m
p
o
n
en
t
o
f
in
tellig
en
ce
; it
is
th
e
m
ec
h
an
is
m
th
r
o
u
g
h
wh
ic
h
in
tellig
en
ce
b
ec
o
m
es c
o
m
p
u
tatio
n
a
lly
r
ea
li
za
b
le.
Mo
d
er
n
m
ac
h
in
e
lear
n
in
g
e
n
co
m
p
ass
es
m
u
ltip
le
lear
n
in
g
p
ar
a
d
ig
m
s
th
at
c
o
llectiv
ely
en
ab
le
in
tellig
en
t
s
y
s
tem
s
to
co
n
s
tr
u
c
t
k
n
o
wled
g
e
f
r
o
m
e
x
p
er
ien
ce
.
So
m
e
p
ar
ad
i
g
m
s
lear
n
f
r
o
m
e
x
p
licit
s
u
p
er
v
is
io
n
,
o
th
er
s
d
is
co
v
er
laten
t
s
tr
u
ctu
r
es
with
o
u
t
p
r
ed
ef
in
ed
lab
els
,
wh
ile
o
th
er
s
ac
q
u
ir
e
ad
ap
tiv
e
b
eh
av
io
r
th
r
o
u
g
h
co
n
tin
u
o
u
s
in
ter
ac
tio
n
with
d
y
n
am
ic
en
v
ir
o
n
m
en
ts
.
Alth
o
u
g
h
alg
o
r
ith
m
ically
d
is
tin
ct,
th
ese
ap
p
r
o
ac
h
es
s
h
ar
e
a
co
m
m
o
n
o
b
jectiv
e:
p
r
o
g
r
ess
iv
ely
r
ef
in
in
g
in
te
r
n
al
co
m
p
u
tatio
n
al
m
o
d
els
th
r
o
u
g
h
ex
p
er
ien
ce
r
ath
er
t
h
an
ex
p
licit
in
s
tr
u
ctio
n
.
R
ath
er
th
a
n
r
ep
r
esen
tin
g
is
o
lated
tech
n
iq
u
es,
th
ese
co
m
p
lem
en
tar
y
p
ar
a
d
ig
m
s
co
llectiv
ely
d
em
o
n
s
tr
ate
th
at
in
tellig
en
ce
ca
n
em
e
r
g
e
th
r
o
u
g
h
m
u
ltip
le
f
o
r
m
s
o
f
lear
n
in
g
,
ea
ch
c
o
n
tr
ib
u
tin
g
u
n
iq
u
e
m
ec
h
an
is
m
s
f
o
r
c
o
n
s
tr
u
ctin
g
i
n
cr
ea
s
in
g
ly
ex
p
r
ess
iv
e
co
m
p
u
tatio
n
al
m
o
d
els o
f
t
h
e
ex
ter
n
al
wo
r
ld
.
Am
o
n
g
th
ese
p
a
r
ad
ig
m
s
,
d
ee
p
lear
n
in
g
h
as
s
ig
n
if
ican
tly
ex
p
an
d
ed
th
e
e
x
p
r
ess
iv
e
p
o
wer
o
f
m
ac
h
in
e
lear
n
in
g
b
y
in
tr
o
d
u
cin
g
h
ier
ar
ch
ical
co
m
p
u
tatio
n
al
ar
c
h
itectu
r
es
ca
p
ab
le
o
f
lear
n
in
g
m
u
ltip
le
lev
els
o
f
ab
s
tr
ac
tio
n
s
im
u
ltan
eo
u
s
ly
.
R
ath
er
th
an
r
ely
in
g
o
n
h
a
n
d
c
r
af
ted
f
ea
tu
r
es
d
esig
n
ed
b
y
h
u
m
an
e
x
p
er
ts
,
d
ee
p
n
eu
r
al
n
etwo
r
k
s
au
t
o
m
atica
lly
co
n
s
tr
u
ct
in
c
r
ea
s
in
g
ly
s
o
p
h
is
ticated
r
ep
r
esen
tatio
n
s
f
r
o
m
r
aw
s
en
s
o
r
y
in
p
u
ts
.
L
o
wer
n
etwo
r
k
lay
er
s
ca
p
tu
r
e
lo
ca
l
an
d
elem
en
tar
y
p
atter
n
s
,
in
ter
m
ed
iate
lay
er
s
id
en
tify
m
o
r
e
s
tr
u
ct
u
r
e
d
r
elatio
n
s
h
ip
s
,
an
d
d
ee
p
e
r
lay
er
s
en
co
d
e
h
ig
h
-
lev
el
s
em
an
tic
co
n
ce
p
ts
th
at
in
cr
ea
s
in
g
ly
r
esem
b
le
h
u
m
an
co
g
n
itiv
e
ab
s
tr
ac
tio
n
.
T
h
is
h
i
er
ar
ch
ical
o
r
g
a
n
izatio
n
en
ab
le
s
in
tellig
en
t
s
y
s
tem
s
to
b
r
id
g
e
th
e
en
o
r
m
o
u
s
g
ap
b
etwe
en
lo
w
-
lev
el
s
ig
n
als
an
d
co
n
ce
p
tu
al
u
n
d
er
s
tan
d
in
g
,
d
e
m
o
n
s
tr
atin
g
th
at
in
cr
ea
s
in
g
in
t
ellig
en
ce
is
ac
h
iev
ed
n
o
t m
er
ely
t
h
r
o
u
g
h
d
ee
p
er
c
o
m
p
u
tatio
n
,
b
u
t th
r
o
u
g
h
p
r
o
g
r
e
s
s
iv
ely
r
ich
er
in
ter
n
al
r
e
p
r
ese
n
tatio
n
s
.
Ma
ch
in
e
lear
n
in
g
ex
p
lain
s
h
o
w
in
tellig
en
t
s
y
s
tem
s
ac
q
u
ir
e
k
n
o
wled
g
e
f
r
o
m
ex
p
er
ien
ce
,
y
et
lear
n
in
g
alo
n
e
d
o
es
n
o
t
d
eter
m
in
e
t
h
e
q
u
ality
o
f
in
tellig
en
ce
th
at
u
ltima
tely
em
er
g
es.
T
h
e
ef
f
ec
t
iv
en
ess
o
f
lear
n
i
n
g
d
ep
en
d
s
f
u
n
d
am
en
tally
o
n
h
o
w
ac
q
u
ir
ed
k
n
o
wled
g
e
is
in
ter
n
ally
o
r
g
an
ize
d
,
s
tr
u
ctu
r
ed
,
an
d
m
ad
e
tr
an
s
f
er
ab
le
ac
r
o
s
s
d
if
f
er
en
t
c
o
n
tex
ts
.
L
ea
r
n
in
g
a
n
s
wer
s
h
o
w
in
tellig
en
t
s
y
s
tem
s
ad
ap
t,
b
u
t
an
o
th
er
e
q
u
ally
f
u
n
d
am
e
n
tal
q
u
esti
o
n
r
e
m
ain
s
:
h
o
w
is
ac
q
u
ir
ed
k
n
o
wled
g
e
r
ep
r
esen
te
d
s
o
th
at
it
s
u
p
p
o
r
ts
ab
s
tr
ac
t
io
n
,
g
en
er
aliza
tio
n
,
r
ea
s
o
n
in
g
,
an
d
tr
an
s
f
er
ac
r
o
s
s
d
iv
er
s
e
task
s
?
Ad
d
r
ess
in
g
th
is
q
u
esti
o
n
lead
s
n
atu
r
ally
to
r
e
p
r
esen
tatio
n
lear
n
in
g
,
wh
ich
p
r
o
v
id
es th
e
s
tr
u
ctu
r
al
o
r
g
an
izatio
n
u
p
o
n
wh
ich
ad
ap
tiv
e
in
tellig
en
ce
u
ltima
tely
d
e
p
en
d
s
.
4
.
R
E
P
R
E
SE
NT
AT
I
O
N
L
E
ARN
I
N
G
⎯
ST
R
UC
T
U
RI
N
G
I
N
T
E
L
L
I
G
E
N
CE
T
H
R
O
U
G
H
I
N
T
E
R
N
AL
K
N
O
WL
E
D
G
E
RE
P
RE
SE
NT
AT
I
O
N
S
T
h
e
p
r
ev
io
u
s
s
ec
tio
n
estab
lis
h
ed
th
at
m
ac
h
in
e
lear
n
i
n
g
p
r
o
v
id
es
th
e
ad
ap
tiv
e
m
ec
h
a
n
is
m
th
r
o
u
g
h
wh
ich
co
m
p
u
tatio
n
al
s
y
s
tem
s
ac
q
u
ir
e
k
n
o
wled
g
e
f
r
o
m
ex
p
er
ien
ce
.
Yet
ac
q
u
ir
in
g
k
n
o
wle
d
g
e
alo
n
e
d
o
es
n
o
t
f
u
lly
ex
p
lain
th
e
em
er
g
en
ce
o
f
in
tellig
en
ce
.
An
eq
u
ally
f
u
n
d
am
en
tal
q
u
esti
o
n
r
em
ain
s
:
h
o
w
d
o
es
ac
q
u
ir
ed
k
n
o
wled
g
e
b
ec
o
m
e
m
ea
n
in
g
f
u
l,
s
tr
u
ctu
r
ed
,
a
n
d
r
e
u
s
ab
le
ac
r
o
s
s
d
if
f
er
en
t
co
n
te
x
ts
?
T
h
e
an
s
wer
lies
in
r
ep
r
esen
tatio
n
lear
n
i
n
g
,
wh
ic
h
d
eter
m
in
es h
o
w
ex
p
er
ien
ce
is
in
ter
n
ally
o
r
g
an
ized
in
t
o
r
ep
r
esen
tatio
n
s
ca
p
ab
le
o
f
s
u
p
p
o
r
tin
g
a
b
s
tr
ac
tio
n
,
g
e
n
er
aliza
tio
n
,
r
ea
s
o
n
in
g
,
an
d
ad
a
p
tiv
e
b
eh
a
v
io
r
.
T
h
is
d
is
tin
ctio
n
m
ar
k
s
o
n
e
o
f
t
h
e
m
o
s
t
im
p
o
r
tan
t
c
o
n
ce
p
t
u
al
ad
v
an
ce
s
in
m
o
d
er
n
a
r
tific
ial
in
tellig
en
ce
.
E
ar
ly
co
m
p
u
tatio
n
al
s
y
s
tem
s
r
elied
h
ea
v
ily
o
n
h
a
n
d
cr
af
te
d
f
e
atu
r
e
en
g
in
ee
r
in
g
,
wh
e
r
e
h
u
m
a
n
ex
p
er
ts
ex
p
licitly
d
eter
m
in
ed
wh
ich
c
h
ar
ac
ter
is
tics
o
f
th
e
d
a
ta
wer
e
r
elev
an
t
f
o
r
a
p
ar
ticu
lar
task
.
Alth
o
u
g
h
ef
f
e
ctiv
e
f
o
r
r
elativ
el
y
s
im
p
le
p
r
o
b
lem
s
,
s
u
ch
ap
p
r
o
a
ch
es
em
b
ed
d
ed
h
u
m
an
ass
u
m
p
tio
n
s
d
ir
ec
tly
in
to
co
m
p
u
tatio
n
al
m
o
d
els,
lim
itin
g
th
eir
s
ca
lab
ilit
y
,
ad
ap
tab
ilit
y
,
an
d
ca
p
ac
ity
to
d
is
co
v
er
p
r
e
v
io
u
s
ly
u
n
k
n
o
wn
p
atter
n
s
.
As
en
g
in
ee
r
in
g
p
r
o
b
lem
s
b
ec
am
e
in
cr
ea
s
in
g
ly
co
m
p
lex
,
d
y
n
am
ic,
a
n
d
m
u
ltimo
d
al,
m
an
u
ally
d
esig
n
in
g
r
ep
r
esen
t
atio
n
s
p
r
o
v
ed
b
o
th
im
p
r
ac
tical
an
d
f
u
n
d
a
m
en
tally
r
estrictiv
e.
R
ep
r
esen
tatio
n
lear
n
in
g
f
u
n
d
a
m
en
tally
ch
an
g
es
th
is
p
ar
ad
ig
m
b
y
allo
win
g
co
m
p
u
tatio
n
al
s
y
s
tem
s
to
d
is
co
v
er
th
ei
r
o
w
n
in
ter
n
al
o
r
g
an
izatio
n
d
ir
ec
tly
f
r
o
m
d
at
a.
R
ath
er
th
a
n
r
ely
in
g
o
n
p
r
e
d
ef
in
ed
d
escr
ip
to
r
s
,
lear
n
in
g
al
g
o
r
ith
m
s
a
u
to
m
ati
ca
lly
id
en
tify
laten
t
v
ar
ia
b
les
th
at
b
est
ex
p
lain
th
e
s
tatis
ti
ca
l
s
tr
u
ctu
r
e
o
f
th
e
o
b
s
er
v
ed
en
v
ir
o
n
m
e
n
t.
T
h
ese
laten
t
r
ep
r
esen
tatio
n
s
o
f
ten
en
co
d
e
s
em
an
tic
r
elatio
n
s
h
ip
s
,
s
p
atial
o
r
g
a
n
izatio
n
,
tem
p
o
r
al
ev
o
lu
tio
n
,
an
d
co
n
t
ex
tu
al
d
ep
en
d
e
n
cies
th
at
ar
e
n
o
t
ex
p
licitly
v
is
ib
le
with
in
th
e
o
r
ig
in
al
d
ata.
C
o
n
s
eq
u
en
tly
,
r
ep
r
esen
tatio
n
lear
n
in
g
s
h
if
ts
in
tellig
en
ce
f
r
o
m
m
an
u
ally
en
g
in
ee
r
e
d
k
n
o
wled
g
e
to
war
d
co
m
p
u
tatio
n
ally
co
n
s
tr
u
cted
u
n
d
er
s
tan
d
in
g
.
T
h
e
ce
n
tr
al
ar
g
u
m
en
t
o
f
th
is
s
ec
tio
n
is
th
at
in
tellig
en
ce
is
d
eter
m
in
ed
less
b
y
th
e
s
o
p
h
is
ticatio
n
o
f
lear
n
in
g
al
g
o
r
ith
m
s
t
h
an
b
y
t
h
e
q
u
ality
o
f
t
h
e
in
ter
n
al
r
ep
r
esen
tatio
n
s
th
ey
p
r
o
d
u
ce
.
A
lear
n
in
g
alg
o
r
ith
m
m
ay
ac
h
iev
e
r
em
ar
k
a
b
le
p
r
ed
ictiv
e
ac
cu
r
ac
y
,
y
et
r
em
ain
f
u
n
d
am
en
tally
lim
ited
if
th
e
r
ep
r
esen
tatio
n
s
it
co
n
s
tr
u
cts
f
ail
to
ca
p
tu
r
e
th
e
ess
en
tial
s
tr
u
ctu
r
e
o
f
th
e
en
v
ir
o
n
m
e
n
t.
C
o
n
v
er
s
ely
,
r
o
b
u
s
t
r
ep
r
esen
tatio
n
s
o
f
ten
en
ab
le
r
elativ
ely
s
im
p
le
lear
n
in
g
al
g
o
r
ith
m
s
to
g
en
e
r
alize
ef
f
ec
tiv
ely
ac
r
o
s
s
d
iv
er
s
e
ta
s
k
s
.
Fro
m
th
is
p
er
s
p
ec
tiv
e,
r
ep
r
esen
tatio
n
q
u
ality
b
ec
o
m
e
s
a
m
o
r
e
f
u
n
d
am
en
tal
m
ea
s
u
r
e
o
f
in
tellig
en
ce
th
an
alg
o
r
ith
m
i
c
co
m
p
lex
ity
its
elf
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
F
r
o
m
d
a
ta
to
i
n
tellig
en
ce
:
fo
u
n
d
a
tio
n
s
o
f le
a
r
n
in
g
s
ystems
,
r
ep
r
esen
ta
tio
n
,
a
n
d
…
(
To
le
S
u
tikn
o
)
1673
T
h
e
ef
f
ec
tiv
en
ess
o
f
m
o
d
e
r
n
r
ep
r
esen
tatio
n
lear
n
in
g
lar
g
el
y
ar
is
es
f
r
o
m
its
h
ier
ar
ch
ical
o
r
g
an
izatio
n
.
R
ath
er
th
an
d
escr
ib
in
g
d
ata
at
a
s
in
g
le
lev
el
o
f
ab
s
tr
ac
tio
n
,
d
ee
p
n
eu
r
al
ar
ch
itectu
r
es
p
r
o
g
r
ess
iv
ely
co
n
s
tr
u
ct
m
u
ltip
le
lay
er
s
o
f
r
e
p
r
esen
t
atio
n
,
ea
ch
c
ap
tu
r
in
g
in
cr
ea
s
in
g
ly
ab
s
tr
ac
t
co
n
ce
p
ts
.
L
o
wer
lay
er
s
id
e
n
tify
elem
en
tar
y
v
is
u
al,
au
d
ito
r
y
,
o
r
n
u
m
er
ical
p
atter
n
s
,
in
ter
m
ed
i
ate
lay
er
s
co
m
b
in
e
th
ese
p
atte
r
n
s
in
to
m
ea
n
in
g
f
u
l
s
tr
u
ctu
r
es,
wh
ile
d
e
ep
er
lay
er
s
en
co
d
e
s
em
an
tic
co
n
ce
p
ts
t
h
at
s
u
p
p
o
r
t
r
ea
s
o
n
in
g
,
r
ec
o
g
n
itio
n
,
an
d
d
ec
is
io
n
-
m
ak
in
g
.
T
h
is
h
ier
ar
c
h
ical
ab
s
tr
ac
tio
n
en
ab
les
co
m
p
u
tatio
n
al
s
y
s
tem
s
to
b
r
id
g
e
th
e
en
o
r
m
o
u
s
g
ap
b
etwe
en
r
aw
s
en
s
o
r
y
o
b
s
er
v
atio
n
s
an
d
c
o
n
c
ep
tu
al
u
n
d
er
s
tan
d
in
g
.
I
m
p
o
r
ta
n
tly
,
h
ier
ar
c
h
ical
r
e
p
r
esen
tatio
n
s
also
ex
p
lain
o
n
e
o
f
t
h
e
d
ef
in
in
g
ch
ar
ac
ter
is
tics
o
f
in
tellig
en
ce
:
g
en
er
aliza
tio
n
.
An
in
tellig
en
t
s
y
s
tem
s
h
o
u
ld
n
o
t
m
er
ely
r
ep
r
o
d
u
ce
p
atter
n
s
o
b
s
er
v
ed
d
u
r
i
n
g
tr
ain
in
g
,
b
u
t
s
h
o
u
ld
ap
p
l
y
p
r
ev
io
u
s
ly
ac
q
u
ir
e
d
k
n
o
wled
g
e
to
s
itu
atio
n
s
it
h
as
n
ev
er
e
n
co
u
n
ter
e
d
b
ef
o
r
e.
Gen
er
aliza
tio
n
b
ec
o
m
es
p
o
s
s
ib
le
b
ec
au
s
e
in
ter
n
al
r
ep
r
ese
n
tatio
n
s
ca
p
tu
r
e
in
v
a
r
ian
t
s
tr
u
ctu
r
es
r
ath
er
th
an
is
o
lated
o
b
s
er
v
atio
n
s
.
B
y
o
r
g
a
n
izin
g
in
f
o
r
m
atio
n
a
r
o
u
n
d
u
n
d
er
ly
in
g
p
r
in
cip
les
in
s
tead
o
f
in
d
iv
id
u
al
e
x
a
m
p
les,
r
ep
r
esen
tatio
n
lear
n
in
g
en
a
b
l
es
s
y
s
tem
s
to
r
ec
o
g
n
ize
n
o
v
e
l
s
itu
atio
n
s
wh
ile
p
r
eser
v
in
g
co
h
er
en
t
r
ea
s
o
n
in
g
ac
r
o
s
s
ch
an
g
in
g
en
v
ir
o
n
m
e
n
ts
.
R
ep
r
esen
tatio
n
lear
n
in
g
also
i
n
tr
o
d
u
ce
s
a
n
o
th
e
r
f
u
n
d
am
e
n
ta
l
p
r
o
p
er
ty
o
f
i
n
tellig
en
ce
:
tr
an
s
f
er
ab
ilit
y
.
On
ce
m
ea
n
i
n
g
f
u
l
r
ep
r
esen
tatio
n
s
h
a
v
e
b
ee
n
lear
n
ed
,
th
e
y
c
an
b
e
r
e
u
s
ed
ac
r
o
s
s
m
u
ltip
le
t
ask
s
,
d
o
m
ain
s
,
an
d
ap
p
licatio
n
s
with
r
elativ
ely
lit
tle
ad
d
itio
n
al
tr
ain
in
g
.
T
h
is
ca
p
ab
ilit
y
s
ig
n
if
ican
tly
r
ed
u
ce
s
th
e
d
ep
en
d
e
n
ce
o
n
task
-
s
p
ec
if
ic
en
g
in
ee
r
in
g
an
d
en
ab
les
k
n
o
wled
g
e
ac
q
u
ir
ed
in
o
n
e
c
o
n
tex
t
to
ac
ce
le
r
ate
lear
n
in
g
in
an
o
th
e
r
.
T
r
an
s
f
er
ab
ilit
y
th
er
e
f
o
r
e
t
r
an
s
f
o
r
m
s
in
tellig
en
ce
f
r
o
m
a
c
o
llectio
n
o
f
is
o
lated
c
o
m
p
eten
cies
in
to
a
co
n
tin
u
o
u
s
ly
ex
p
an
d
i
n
g
b
o
d
y
o
f
r
e
u
s
ab
le
co
m
p
u
tatio
n
al
k
n
o
wled
g
e
.
B
ey
o
n
d
i
m
p
r
o
v
in
g
p
r
e
d
i
cti
v
e
p
e
r
f
o
r
m
a
n
ce
,
r
e
p
r
es
en
tat
io
n
l
ea
r
n
i
n
g
f
u
n
d
a
m
e
n
t
all
y
ch
an
g
es
h
o
w
co
m
p
u
tati
o
n
a
l
s
y
s
te
m
s
i
n
te
r
a
ct
wi
th
in
f
o
r
m
ati
o
n
its
elf
.
I
n
tel
li
g
e
n
c
e
n
o
l
o
n
g
e
r
r
esi
d
es
in
ex
p
l
icit
r
u
les
,
s
y
m
b
o
li
c
d
at
a
b
ases
,
o
r
h
a
n
d
c
r
a
f
t
ed
f
e
at
u
r
es,
b
u
t
i
n
t
h
e
c
o
n
ti
n
u
o
u
s
ly
e
v
o
l
v
i
n
g
i
n
t
er
n
al
s
t
r
u
ct
u
r
es
t
h
r
o
u
g
h
w
h
ic
h
s
y
s
te
m
s
in
t
er
p
r
et
r
ea
l
it
y
.
I
n
t
h
is
s
e
n
s
e
,
r
e
p
r
ese
n
t
ati
o
n
c
o
n
s
ti
tu
tes
t
h
e
i
n
te
r
n
al
la
n
g
u
a
g
e
o
f
i
n
t
ell
ig
en
ce
—
t
h
e
m
e
d
i
u
m
th
r
o
u
g
h
w
h
ic
h
d
a
ta
b
e
co
m
es
k
n
o
wle
d
g
e
a
n
d
k
n
o
wl
ed
g
e
b
ec
o
m
es
a
d
ap
ti
v
e
b
e
h
av
io
r
.
T
h
is
p
er
s
p
e
cti
v
e
e
x
p
lai
n
s
wh
y
r
ec
en
t
a
d
v
a
n
c
es
i
n
a
r
ti
f
i
ci
al
i
n
te
lli
g
e
n
ce
h
a
v
e
b
e
e
n
d
r
i
v
e
n
less
b
y
i
n
c
r
e
asi
n
g
l
y
c
o
m
p
l
ex
a
lg
o
r
it
h
m
s
t
h
a
n
b
y
in
c
r
ea
s
i
n
g
l
y
ex
p
r
ess
iv
e
r
e
p
r
es
en
t
ati
o
n
s
ca
p
a
b
l
e
o
f
ca
p
t
u
r
i
n
g
th
e
h
i
d
d
e
n
o
r
g
a
n
iz
ati
o
n
o
f
th
e
wo
r
l
d
.
R
ep
r
esen
tatio
n
lear
n
in
g
ex
p
lai
n
s
h
o
w
in
tellig
en
t
s
y
s
tem
s
o
r
g
an
ize
k
n
o
wled
g
e
in
ter
n
ally
.
Yet
in
ter
n
al
o
r
g
an
izatio
n
alo
n
e
ca
n
n
o
t
g
u
ar
an
tee
in
tellig
en
t
b
e
h
av
io
r
u
n
less
th
ese
r
ep
r
esen
tatio
n
s
r
e
m
ain
co
n
tin
u
o
u
s
ly
alig
n
ed
with
th
e
ex
ter
n
al
wo
r
ld
f
r
o
m
wh
ich
th
ey
a
r
e
d
er
iv
ed
.
I
n
tellig
en
ce
th
e
r
ef
o
r
e
r
eq
u
ir
es
n
o
t
o
n
l
y
m
ea
n
in
g
f
u
l
r
ep
r
esen
tatio
n
s
,
b
u
t
also
m
ec
h
an
is
m
s
th
at
co
n
ti
n
u
o
u
s
ly
u
p
d
ate
a
n
d
v
alid
ate
t
h
o
s
e
r
ep
r
esen
tatio
n
s
th
r
o
u
g
h
in
ter
ac
tio
n
with
r
ea
lit
y
.
T
h
is
o
b
s
er
v
atio
n
n
at
u
r
ally
l
ea
d
s
to
co
m
p
u
tatio
n
al
p
er
ce
p
t
io
n
,
wh
ich
g
r
o
u
n
d
s
in
ter
n
al
r
e
p
r
esen
tatio
n
s
in
s
en
s
o
r
y
e
x
p
er
ien
ce
an
d
clo
s
es
t
h
e
co
g
n
itiv
e
lo
o
p
b
etwe
en
co
m
p
u
tatio
n
an
d
th
e
p
h
y
s
ical
en
v
ir
o
n
m
en
t.
5
.
CO
M
P
UT
AT
I
O
NAL
P
E
RC
E
P
T
I
O
N
—
G
RO
UND
I
NG
I
NT
E
L
L
I
G
E
NC
E
I
N
T
H
E
P
H
YSI
CA
L
WO
RL
D
Hav
in
g
estab
lis
h
ed
lear
n
in
g
as
th
e
ad
ap
tiv
e
m
ec
h
an
is
m
o
f
in
tellig
en
ce
an
d
r
ep
r
esen
tatio
n
as
it
s
in
ter
n
al
co
g
n
itiv
e
s
tr
u
ct
u
r
e,
th
e
r
em
ain
in
g
c
h
allen
g
e
is
to
e
x
p
lain
h
o
w
th
ese
in
ter
n
al
co
g
n
iti
v
e
p
r
o
ce
s
s
es
r
em
ain
co
n
tin
u
o
u
s
ly
co
n
n
ec
ted
to
th
e
ex
ter
n
al
wo
r
ld
.
I
n
tellig
en
ce
c
an
n
o
t
e
m
er
g
e
s
o
lely
f
r
o
m
in
te
r
n
ally
co
n
s
tr
u
cted
r
ep
r
esen
tatio
n
s
,
r
eg
ar
d
less
o
f
h
o
w
ex
p
r
ess
iv
e
o
r
s
em
an
tically
r
ich
th
ey
b
ec
o
m
e.
W
ith
o
u
t
co
n
tin
u
o
u
s
in
ter
ac
tio
n
with
p
h
y
s
ical
r
ea
lity
,
ev
en
th
e
m
o
s
t
s
o
p
h
is
ticated
r
ep
r
esen
tatio
n
s
r
is
k
b
ec
o
m
in
g
d
e
tach
ed
f
r
o
m
th
e
en
v
ir
o
n
m
en
ts
th
ey
ar
e
in
ten
d
e
d
to
d
escr
ib
e.
C
o
m
p
u
tatio
n
al
p
er
ce
p
tio
n
p
r
o
v
id
es
th
e
g
r
o
u
n
d
in
g
m
ec
h
a
n
is
m
th
at
clo
s
es
th
is
co
g
n
iti
v
e
lo
o
p
b
y
co
n
tin
u
o
u
s
ly
lin
k
in
g
s
en
s
o
r
y
o
b
s
er
v
atio
n
s
with
ev
o
lv
in
g
in
t
er
n
al
r
ep
r
esen
tatio
n
s
.
As
illu
s
tr
ated
co
n
ce
p
tu
ally
in
Fig
u
r
e
1
,
lear
n
i
n
g
,
r
e
p
r
esen
tatio
n
,
an
d
p
e
r
ce
p
tio
n
d
o
n
o
t
o
p
er
ate
as
in
d
ep
en
d
e
n
t
co
m
p
u
t
atio
n
al
m
o
d
u
les
b
u
t
as
m
u
tu
ally
r
ein
f
o
r
cin
g
co
g
n
itiv
e
p
r
o
ce
s
s
es
th
at
co
n
tin
u
o
u
s
ly
s
h
ap
e
o
n
e
an
o
th
er
.
T
h
r
o
u
g
h
th
is
r
ec
u
r
s
iv
e
in
ter
ac
tio
n
,
s
en
s
o
r
y
ex
p
er
ien
c
e
is
p
r
o
g
r
ess
iv
ely
tr
an
s
f
o
r
m
ed
in
to
co
n
tex
tu
al
u
n
d
e
r
s
tan
d
in
g
,
en
a
b
lin
g
ab
s
tr
ac
t
co
m
p
u
tatio
n
to
ev
o
lv
e
in
to
s
it
u
ated
in
tellig
en
ce
th
at
r
em
ain
s
co
n
tin
u
o
u
s
ly
alig
n
ed
with
th
e
ex
ter
n
al
wo
r
l
d
.
T
h
is
p
er
s
p
ec
tiv
e
f
u
n
d
am
en
ta
lly
ch
an
g
es
th
e
r
o
le
o
f
p
er
ce
p
tio
n
with
in
in
tellig
en
t
s
y
s
tem
s
.
I
n
co
n
v
en
tio
n
al
en
g
in
e
er
in
g
,
p
er
ce
p
tio
n
h
as
o
f
te
n
b
ee
n
r
eg
ar
d
ed
as
an
in
p
u
t
-
p
r
o
ce
s
s
in
g
s
tag
e
r
esp
o
n
s
ib
le
f
o
r
f
ilter
in
g
s
ig
n
als,
ex
tr
ac
tin
g
f
ea
tu
r
es,
o
r
p
r
ep
ar
in
g
d
ata
f
o
r
s
u
b
s
eq
u
en
t
an
aly
s
is
.
Alth
o
u
g
h
s
u
c
h
o
p
er
atio
n
s
r
em
ain
co
m
p
u
tatio
n
ally
im
p
o
r
tan
t,
th
ey
d
o
n
o
t
f
u
lly
ex
p
lain
th
e
r
o
le
o
f
p
er
ce
p
tio
n
in
in
tellig
en
ce
.
Per
ce
p
tio
n
is
n
o
t
m
er
ely
th
e
ac
q
u
is
itio
n
o
f
s
en
s
o
r
y
in
f
o
r
m
ati
o
n
;
it
is
th
e
co
n
tin
u
o
u
s
co
n
s
tr
u
ctio
n
o
f
m
ea
n
in
g
f
u
l
in
ter
p
r
etatio
n
s
th
at
allo
w
in
tel
lig
en
t sy
s
tem
s
to
u
n
d
er
s
tan
d
a
n
d
in
ter
ac
t w
ith
th
eir
s
u
r
r
o
u
n
d
in
g
s
.
T
h
e
ce
n
tr
al
p
r
o
p
o
s
itio
n
o
f
th
i
s
s
ec
tio
n
is
th
at
p
e
r
ce
p
tio
n
c
o
n
s
titu
tes
th
e
g
r
o
u
n
d
in
g
m
ec
h
an
is
m
o
f
in
tellig
en
ce
.
L
ea
r
n
i
n
g
d
eter
m
i
n
es
h
o
w
s
y
s
tem
s
im
p
r
o
v
e
th
r
o
u
g
h
ex
p
e
r
ien
ce
,
wh
ile
r
ep
r
es
en
tatio
n
d
eter
m
i
n
es
h
o
w
k
n
o
wled
g
e
is
in
ter
n
ally
s
t
r
u
ctu
r
ed
.
Per
ce
p
tio
n
,
h
o
we
v
er
,
d
eter
m
in
es
wh
eth
er
th
o
s
e
lear
n
ed
r
ep
r
esen
tatio
n
s
r
em
ain
co
n
n
ec
ted
to
r
ea
lity
.
I
t
co
n
tin
u
o
u
s
ly
co
n
s
tr
ain
s
,
v
alid
ates,
an
d
u
p
d
ates
in
ter
n
al
co
g
n
itiv
e
m
o
d
els
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
16
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
6
6
9
-
1676
1674
ac
co
r
d
in
g
to
o
b
s
er
v
atio
n
s
o
f
t
h
e
ex
ter
n
al
en
v
ir
o
n
m
en
t,
en
s
u
r
in
g
t
h
at
in
tellig
en
ce
r
ef
lects t
h
e
wo
r
l
d
r
at
h
er
t
h
an
m
er
ely
d
escr
ib
in
g
s
tatis
tical
r
e
g
u
lar
ities
with
in
d
ata.
Fig
u
r
e
1
.
Fo
u
n
d
atio
n
al
co
g
n
itiv
e
in
tellig
en
ce
f
r
a
m
ewo
r
k
Mo
d
er
n
in
tellig
en
t
s
y
s
tem
s
ac
h
iev
e
th
is
ca
p
ab
ilit
y
th
r
o
u
g
h
th
e
in
teg
r
atio
n
o
f
m
u
ltip
le
s
en
s
o
r
y
m
o
d
alities
,
in
clu
d
in
g
v
is
u
al
in
f
o
r
m
atio
n
,
s
p
ee
ch
,
r
ad
ar
,
L
iD
AR
,
b
io
m
ed
ical
s
ig
n
als,
I
n
ter
n
et
o
f
T
h
in
g
s
(
I
o
T
)
d
ev
ices,
an
d
n
u
m
er
o
u
s
p
h
y
s
ical
s
en
s
o
r
s
d
is
tr
ib
u
ted
a
c
r
o
s
s
cy
b
er
-
p
h
y
s
ical
e
n
v
ir
o
n
m
en
ts
.
R
ath
er
th
a
n
p
r
o
ce
s
s
in
g
th
ese
h
eter
o
g
e
n
eo
u
s
in
p
u
ts
in
d
ep
en
d
e
n
tly
,
co
m
p
u
tatio
n
al
p
er
ce
p
tio
n
in
te
g
r
ates
th
em
in
to
co
h
e
r
en
t
en
v
ir
o
n
m
en
tal
r
e
p
r
esen
tatio
n
s
th
at
ca
p
tu
r
e
b
o
th
s
p
atial
an
d
tem
p
o
r
al
r
elatio
n
s
h
ip
s
.
T
h
is
m
u
ltimo
d
al
u
n
d
er
s
tan
d
i
n
g
en
a
b
les
in
tellig
en
t
s
y
s
tem
s
to
m
ain
tain
s
itu
atio
n
al
awa
r
en
ess
u
n
d
e
r
d
y
n
am
ic
an
d
o
f
ten
u
n
ce
r
tain
o
p
er
atin
g
c
o
n
d
itio
n
s
.
I
m
p
o
r
ta
n
tly
,
p
er
ce
p
tio
n
s
h
o
u
l
d
n
o
t
b
e
in
ter
p
r
eted
as
a
o
n
e
-
way
in
f
o
r
m
atio
n
f
lo
w
f
r
o
m
s
en
s
o
r
s
to
alg
o
r
ith
m
s
.
I
n
s
tead
,
p
e
r
ce
p
tio
n
o
p
er
ates
with
in
a
r
ec
u
r
s
iv
e
c
o
g
n
itiv
e
lo
o
p
in
wh
ich
o
b
s
er
v
atio
n
,
lear
n
in
g
,
an
d
r
ep
r
esen
tatio
n
c
o
n
tin
u
o
u
s
ly
in
f
lu
en
ce
o
n
e
an
o
t
h
er
.
I
n
co
m
in
g
s
en
s
o
r
y
i
n
f
o
r
m
atio
n
u
p
d
ates
in
ter
n
al
r
ep
r
esen
tatio
n
s
,
wh
ile
th
o
s
e
r
ep
r
esen
tatio
n
s
d
eter
m
in
e
w
h
ich
en
v
ir
o
n
m
en
tal
p
atter
n
s
ar
e
co
n
s
id
er
ed
r
elev
an
t
f
o
r
f
u
tu
r
e
p
er
ce
p
tio
n
.
I
n
tellig
e
n
ce
th
er
ef
o
r
e
e
m
er
g
es
th
r
o
u
g
h
an
o
n
g
o
i
n
g
d
ialo
g
u
e
b
etwe
en
th
e
ex
ter
n
al
wo
r
ld
an
d
th
e
s
y
s
tem
'
s
ev
o
lv
in
g
in
te
r
n
al
co
g
n
itiv
e
m
o
d
el.
T
h
is
r
ec
u
r
s
iv
e
in
ter
ac
tio
n
ex
p
lain
s
wh
y
in
tellig
en
t
s
y
s
tem
s
ar
e
ca
p
ab
le
o
f
ad
ap
tatio
n
b
e
y
o
n
d
th
eir
o
r
ig
in
al
tr
ai
n
in
g
co
n
d
itio
n
s
.
E
n
v
ir
o
n
m
en
tal
c
h
an
g
es
c
o
n
ti
n
u
o
u
s
ly
g
en
e
r
ate
n
ew
o
b
s
er
v
atio
n
s
th
at
ch
allen
g
e
ex
is
tin
g
r
ep
r
esen
tatio
n
s
,
f
o
r
ci
n
g
lear
n
in
g
m
ec
h
a
n
is
m
s
to
r
ef
in
e
p
r
ev
io
u
s
ly
ac
q
u
ir
e
d
k
n
o
wl
ed
g
e.
As
p
er
ce
p
tio
n
b
ec
o
m
es
in
cr
ea
s
in
g
ly
in
teg
r
a
ted
with
lear
n
in
g
,
in
tellig
en
t
s
y
s
tem
s
p
r
o
g
r
ess
iv
ely
im
p
r
o
v
e
n
o
t
o
n
ly
th
eir
p
r
ed
ictiv
e
ac
cu
r
ac
y
b
u
t
also
th
eir
co
n
tex
tu
al
u
n
d
er
s
tan
d
i
n
g
,
r
o
b
u
s
tn
ess
,
an
d
ca
p
ac
ity
to
o
p
er
a
te
u
n
d
er
u
n
ce
r
tain
ty
.
Fro
m
a
b
r
o
a
d
er
p
er
s
p
ec
tiv
e,
co
m
p
u
tatio
n
al
p
e
r
ce
p
tio
n
tr
an
s
f
o
r
m
s
in
tellig
en
ce
f
r
o
m
a
n
ab
s
tr
ac
t
co
m
p
u
tatio
n
al
ca
p
ab
ilit
y
i
n
to
an
em
b
o
d
ied
co
g
n
itiv
e
p
r
o
ce
s
s
.
I
n
tellig
en
ce
is
n
o
lo
n
g
er
co
n
f
in
ed
t
o
p
r
o
ce
s
s
in
g
s
y
m
b
o
lic
o
r
n
u
m
er
ical
in
f
o
r
m
atio
n
in
s
id
e
co
m
p
u
tatio
n
al
m
o
d
els;
in
s
tead
,
it
b
ec
o
m
es
an
ac
tiv
e
p
r
o
ce
s
s
o
f
in
ter
p
r
etin
g
,
v
alid
atin
g
,
an
d
r
e
s
p
o
n
d
in
g
to
co
n
tin
u
o
u
s
ly
ch
an
g
in
g
p
h
y
s
ical
en
v
ir
o
n
m
e
n
ts
.
Per
ce
p
tio
n
th
e
r
ef
o
r
e
s
er
v
es
as
th
e
b
r
id
g
e
th
r
o
u
g
h
w
h
ich
co
m
p
u
tatio
n
ac
q
u
ir
es
m
e
an
in
g
,
e
n
ab
lin
g
in
tellig
en
t
s
y
s
tem
s
to
m
o
v
e
f
r
o
m
ab
s
tr
ac
t r
ea
s
o
n
in
g
to
war
d
g
e
n
u
in
e
in
ter
ac
tio
n
with
t
h
e
r
ea
l
wo
r
ld
.
T
h
e
p
r
ec
e
d
in
g
d
is
cu
s
s
io
n
s
co
llectiv
ely
d
em
o
n
s
tr
ate
th
at
l
ea
r
n
in
g
,
r
ep
r
esen
tatio
n
,
an
d
p
er
ce
p
tio
n
s
h
o
u
ld
n
o
t
b
e
in
ter
p
r
eted
as
in
d
ep
en
d
en
t
ca
p
ab
ilit
ies
ad
d
ed
to
in
tellig
en
t
s
y
s
tem
s
.
V
iewe
d
in
is
o
latio
n
,
ea
ch
co
n
tr
ib
u
tes o
n
ly
a
p
ar
tial a
s
p
e
ct
o
f
in
tellig
en
ce
: le
ar
n
in
g
with
o
u
t p
e
r
ce
p
tio
n
p
r
o
d
u
ce
s
in
ter
n
ally
co
n
s
is
ten
t y
et
p
o
ten
tially
d
etac
h
ed
m
o
d
els,
p
er
ce
p
tio
n
with
o
u
t
lear
n
in
g
r
em
ain
s
r
ea
ctiv
e
a
n
d
i
n
ca
p
ab
le
o
f
s
u
s
tain
ed
ad
ap
tatio
n
,
wh
ile
r
e
p
r
esen
tatio
n
with
o
u
t
eith
er
lac
k
s
s
em
an
tic
o
r
g
an
izatio
n
an
d
lo
n
g
-
te
r
m
co
g
n
itiv
e
u
tili
ty
.
T
h
eir
tr
u
e
s
ig
n
if
ican
ce
em
er
g
es
o
n
ly
th
r
o
u
g
h
th
eir
co
n
tin
u
o
u
s
in
ter
ac
tio
n
,
wh
e
r
e
th
e
s
e
co
m
p
lem
en
tar
y
co
g
n
itiv
e
p
r
o
ce
s
s
es
r
ec
u
r
s
iv
ely
co
n
s
tr
ain
,
r
ein
f
o
r
ce
,
a
n
d
r
e
o
r
g
an
ize
o
n
e
an
o
th
er
th
r
o
u
g
h
o
u
t
s
y
s
tem
o
p
er
atio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
F
r
o
m
d
a
ta
to
i
n
tellig
en
ce
:
fo
u
n
d
a
tio
n
s
o
f le
a
r
n
in
g
s
ystems
,
r
ep
r
esen
ta
tio
n
,
a
n
d
…
(
To
le
S
u
tikn
o
)
1675
I
n
tellig
en
ce
th
e
r
ef
o
r
e
s
h
o
u
l
d
n
o
t
b
e
u
n
d
e
r
s
to
o
d
as
t
h
e
o
u
tco
m
e
o
f
an
y
s
in
g
le
co
m
p
u
tatio
n
a
l
f
u
n
ctio
n
,
b
u
t
as
an
em
er
g
en
t
s
y
s
tem
s
-
lev
el
p
r
o
p
er
ty
ar
is
in
g
f
r
o
m
th
e
r
ec
u
r
s
iv
e
in
ter
p
lay
am
o
n
g
lear
n
i
n
g
,
r
ep
r
esen
tatio
n
,
a
n
d
p
er
ce
p
tio
n
.
T
h
is
in
teg
r
ated
p
er
s
p
ec
tiv
e
n
atu
r
ally
lead
s
to
th
e
f
in
al
co
n
ce
p
tu
al
s
y
n
th
esi
s
d
ev
elo
p
ed
i
n
th
e
f
o
llo
win
g
s
ec
tio
n
,
wh
e
r
e
f
o
u
n
d
atio
n
al
co
g
n
itiv
e
in
tellig
en
ce
is
in
tr
o
d
u
ce
d
as
a
u
n
i
f
ied
co
g
n
itiv
e
ar
ch
itectu
r
e
r
ath
er
th
an
a
co
llectio
n
o
f
is
o
l
ated
co
m
p
u
tatio
n
al
tech
n
o
lo
g
i
es.
6
.
F
O
U
N
D
AT
I
O
NA
L
C
O
G
NIT
I
V
E
I
NT
E
L
L
I
G
E
N
CE
–
T
O
W
A
RD
AN
I
NT
E
G
R
AT
E
D
C
O
G
N
I
T
I
VE
A
R
C
H
I
T
E
CT
U
RE
T
h
e
p
r
ec
ed
in
g
d
is
cu
s
s
io
n
s
h
av
e
p
r
o
g
r
ess
iv
ely
an
s
wer
ed
th
e
ce
n
tr
al
q
u
esti
o
n
in
tr
o
d
u
c
ed
in
th
is
ed
ito
r
ial:
Ho
w
d
o
es
in
tellig
en
ce
em
er
g
e
f
r
o
m
co
m
p
u
tatio
n
?
T
h
e
an
s
wer
d
o
es
n
o
t
r
esi
d
e
in
an
y
in
d
iv
i
d
u
al
co
m
p
u
tatio
n
al
ca
p
a
b
ilit
y
co
n
s
id
er
ed
in
is
o
latio
n
.
R
ath
er
,
in
tel
lig
en
ce
em
er
g
es
th
r
o
u
g
h
t
h
e
r
e
cu
r
s
iv
e
in
ter
ac
tio
n
am
o
n
g
lear
n
in
g
,
r
ep
r
esen
tati
o
n
,
a
n
d
co
m
p
u
tatio
n
al
p
er
ce
p
tio
n
,
w
h
o
s
e
c
o
m
p
lem
en
ta
r
y
co
g
n
itiv
e
f
u
n
ctio
n
s
co
llectiv
ely
tr
an
s
f
o
r
m
d
ata
in
to
ad
ap
tiv
e,
m
ea
n
in
g
f
u
l,
a
n
d
co
n
tex
t
-
awa
r
e
b
eh
a
v
io
r
.
Fr
o
m
th
i
s
p
er
s
p
ec
tiv
e,
m
ac
h
in
e
in
tellig
en
ce
is
b
est
u
n
d
er
s
to
o
d
n
o
t
as
a
p
r
o
p
e
r
ty
o
f
alg
o
r
ith
m
s
,
b
u
t
as
an
em
er
g
en
t
p
r
o
p
e
r
ty
o
f
a
n
in
teg
r
ated
co
g
n
itiv
e
ar
c
h
itectu
r
e.
L
ea
r
n
in
g
en
a
b
les
co
m
p
u
tatio
n
al
s
y
s
tem
s
to
ad
ap
t
th
r
o
u
g
h
ex
p
er
ien
ce
,
r
ep
r
esen
tatio
n
o
r
g
an
izes
ac
q
u
ir
ed
k
n
o
wled
g
e
in
to
s
tr
u
c
tu
r
ed
in
ter
n
al
m
o
d
els,
an
d
c
o
m
p
u
tatio
n
al
p
e
r
ce
p
tio
n
co
n
tin
u
o
u
s
ly
g
r
o
u
n
d
s
th
o
s
e
m
o
d
els
in
o
b
s
er
v
a
b
le
r
ea
lity
.
I
n
d
iv
id
u
ally
,
th
ese
p
r
o
ce
s
s
es
p
r
o
v
id
e
o
n
ly
p
ar
tial
co
g
n
itiv
e
ca
p
ab
ilit
ies.
C
o
llectiv
ely
,
h
o
wev
e
r
,
t
h
ey
e
s
tab
lis
h
r
ec
u
r
s
iv
e
f
ee
d
b
ac
k
m
ec
h
an
is
m
s
th
r
o
u
g
h
wh
ich
in
t
er
n
al
k
n
o
wled
g
e
is
co
n
tin
u
o
u
s
ly
r
ef
in
ed
,
v
alid
ate
d
,
an
d
r
e
o
r
g
a
n
ized
.
As
illu
s
tr
ated
co
n
ce
p
t
u
ally
in
Fig
u
r
e
1
,
in
tellig
en
c
e
th
er
ef
o
r
e
em
er
g
es
n
o
t
f
r
o
m
co
m
p
u
tatio
n
al
co
m
p
lex
ity
alo
n
e,
b
u
t
f
r
o
m
th
e
o
r
g
an
izatio
n
o
f
th
ese
i
n
ter
ac
tin
g
c
o
g
n
itiv
e
p
r
o
ce
s
s
es
in
to
a
u
n
if
ied
co
g
n
i
tiv
e
ar
ch
itectu
r
e
ch
ar
ac
te
r
ized
b
y
h
ier
ar
c
h
ical
ab
s
tr
ac
tio
n
,
r
ec
u
r
s
iv
e
f
ee
d
b
ac
k
,
an
d
co
n
tin
u
al
en
v
ir
o
n
m
e
n
tal
g
r
o
u
n
d
in
g
,
r
ath
er
th
a
n
b
y
a
s
eq
u
en
tial p
r
o
ce
s
s
in
g
p
i
p
elin
e.
T
h
is
s
y
s
tem
s
-
lev
el
in
ter
p
r
eta
tio
n
f
u
n
d
am
e
n
tally
c
h
an
g
es
th
e
en
g
i
n
ee
r
in
g
p
h
ilo
s
o
p
h
y
u
n
d
er
ly
i
n
g
in
tellig
en
t
s
y
s
tem
s
.
R
ath
er
th
an
d
esig
n
in
g
f
ix
e
d
co
m
p
u
tatio
n
al
p
ip
elin
es
th
at
ex
ec
u
te
p
r
ed
ef
in
ed
alg
o
r
ith
m
s
,
en
g
in
ee
r
s
in
cr
ea
s
in
g
ly
d
ev
elo
p
ad
ap
tiv
e
ar
c
h
itectu
r
es
ca
p
ab
l
e
o
f
r
eo
r
g
an
izin
g
th
eir
in
ter
n
al
k
n
o
wled
g
e
t
h
r
o
u
g
h
co
n
tin
u
al
in
te
r
ac
tio
n
with
c
h
a
n
g
in
g
en
v
ir
o
n
m
en
ts
.
T
h
e
em
p
h
asis
th
er
ef
o
r
e
s
h
if
ts
f
r
o
m
ex
p
licitly
p
r
o
g
r
a
m
m
in
g
in
tellig
en
t
b
eh
av
io
r
to
war
d
cu
l
tiv
atin
g
in
tellig
en
ce
as
an
e
m
e
r
g
en
t
p
r
o
p
er
t
y
o
f
co
n
tin
u
o
u
s
ly
ev
o
lv
in
g
co
g
n
itiv
e
p
r
o
ce
s
s
es.
Su
ch
a
p
er
s
p
ec
tiv
e
also
p
r
o
v
id
es
a
m
o
r
e
u
n
if
ied
in
ter
p
r
etatio
n
o
f
r
ec
e
n
t
ad
v
an
ce
s
in
ar
tific
ial
in
tellig
en
ce
.
R
ec
en
t
ad
v
a
n
ce
s
in
f
o
u
n
d
atio
n
m
o
d
els,
m
u
lti
m
o
d
al
lear
n
i
n
g
,
s
elf
-
s
u
p
er
v
is
ed
lear
n
in
g
,
wo
r
l
d
m
o
d
els,
an
d
em
b
o
d
ied
i
n
tellig
en
ce
ca
n
all
b
e
in
ter
p
r
eted
as
ef
f
o
r
ts
to
s
tr
en
g
t
h
en
th
e
r
ec
u
r
s
iv
e
in
ter
ac
tio
n
a
m
o
n
g
lear
n
in
g
,
r
e
p
r
esen
tatio
n
,
an
d
p
er
ce
p
tio
n
,
r
ath
e
r
th
an
m
er
ely
i
m
p
r
o
v
i
n
g
in
d
iv
i
d
u
al
alg
o
r
ith
m
s
in
is
o
latio
n
.
Fro
m
th
is
v
iewp
o
in
t,
co
n
tem
p
o
r
ar
y
ar
tific
ial
in
tellig
en
ce
(
AI
)
r
e
s
ea
r
ch
is
g
r
ad
u
ally
m
o
v
in
g
b
ey
o
n
d
task
-
s
p
ec
if
ic
o
p
tim
izatio
n
to
war
d
th
e
d
ev
el
o
p
m
en
t
o
f
i
n
teg
r
ated
co
g
n
itiv
e
ar
ch
itectu
r
es
ca
p
a
b
le
o
f
ac
q
u
ir
in
g
in
cr
ea
s
in
g
l
y
g
en
er
al
f
o
r
m
s
o
f
in
tellig
en
ce
.
T
h
e
r
a
p
id
c
o
n
v
e
r
g
en
ce
o
f
th
es
e
r
esear
ch
d
ir
ec
tio
n
s
s
u
g
g
ests
th
at
f
u
tu
r
e
in
tellig
e
n
t
s
y
s
tem
s
wi
ll
b
e
d
ef
in
ed
less
b
y
is
o
lated
tech
n
o
lo
g
ical
b
r
ea
k
th
r
o
u
g
h
s
th
an
b
y
th
e
co
h
er
en
c
e
o
f
th
eir
co
g
n
itiv
e
o
r
g
an
izatio
n
.
Mo
r
e
im
p
o
r
tan
tly
,
th
is
f
o
u
n
d
atio
n
al
co
g
n
itiv
e
i
n
tellig
en
ce
p
a
r
ad
ig
m
estab
lis
h
es
th
e
co
n
ce
p
t
u
al
b
r
i
d
g
e
b
etwe
en
co
m
p
u
tatio
n
al
in
tellig
en
ce
a
n
d
h
ig
h
e
r
-
o
r
d
er
au
to
n
o
m
o
u
s
s
y
s
tem
s
.
On
ce
lear
n
in
g
co
n
tin
u
o
u
s
ly
r
e
f
in
es
k
n
o
wled
g
e,
r
e
p
r
esen
tatio
n
o
r
g
an
izes
ab
s
tr
ac
tio
n
,
an
d
p
er
ce
p
tio
n
g
r
o
u
n
d
s
co
g
n
itio
n
with
in
p
h
y
s
ical
en
v
ir
o
n
m
en
ts
,
in
tellig
en
t
s
y
s
te
m
s
ac
q
u
ir
e
th
e
ess
en
tial
ca
p
ab
ilit
ies
r
eq
u
ir
ed
f
o
r
co
n
tex
tu
al
r
ea
s
o
n
in
g
,
ad
ap
tiv
e
p
lan
n
in
g
,
an
d
au
to
n
o
m
o
u
s
d
ec
is
io
n
-
m
ak
in
g
.
Fo
u
n
d
atio
n
al
co
g
n
itiv
e
in
tellig
en
ce
s
h
o
u
ld
th
er
ef
o
r
e
b
e
u
n
d
er
s
to
o
d
n
o
t
as
th
e
f
in
al
o
b
j
ec
tiv
e
o
f
i
n
tellig
en
t
s
y
s
tem
d
e
v
elo
p
m
en
t,
b
u
t
as
th
e
ess
en
tial
co
g
n
itiv
e
s
u
b
s
tr
ate
u
p
o
n
wh
ich
in
cr
ea
s
in
g
ly
s
o
p
h
is
ticated
f
o
r
m
s
o
f
m
ac
h
i
n
e
in
t
ellig
en
ce
ca
n
em
er
g
e
.
T
h
is
p
e
r
s
p
ec
tiv
e
p
r
o
v
id
es
th
e
in
tellectu
al
f
o
u
n
d
atio
n
f
o
r
th
e
b
r
o
ad
er
I
J
E
C
E
2
0
2
6
e
d
ito
r
ial
tr
ajec
to
r
y
,
wh
er
e
co
g
n
itiv
e
in
tellig
en
ce
p
r
o
g
r
ess
iv
ely
e
v
o
lv
es
to
war
d
co
g
n
itiv
e
cy
b
er
-
p
h
y
s
ical
s
y
s
tem
s
,
au
to
n
o
m
o
u
s
r
ea
s
o
n
in
g
,
a
n
d
u
ltima
tely
s
o
cio
-
co
g
n
itiv
e
in
tellig
en
ce
ca
p
ab
le
o
f
co
llab
o
r
atin
g
with
h
u
m
an
s
i
n
co
m
p
le
x
r
ea
l
-
wo
r
l
d
ec
o
s
y
s
tem
s
.
7
.
F
RO
M
F
O
UNDA
T
I
O
NA
L
I
NT
E
L
L
I
G
E
NCE
T
O
AU
T
O
NO
M
O
US
CO
G
N
I
T
I
VE
E
C
O
SYST
E
M
S
T
h
e
ev
o
lu
tio
n
o
f
in
tellig
en
ce
in
c
o
m
p
u
tatio
n
al
s
y
s
tem
s
is
b
est
u
n
d
e
r
s
to
o
d
as
a
p
r
o
g
r
ess
io
n
ac
r
o
s
s
in
cr
ea
s
in
g
ly
co
m
p
lex
o
p
e
r
atio
n
al
co
n
tex
ts
.
T
h
ese
ed
ito
r
ial
p
o
s
itio
n
s
th
at
p
r
o
g
r
ess
io
n
as
th
e
f
ir
s
t
s
tag
e
o
f
a
b
r
o
ad
e
r
I
J
E
C
E
2
0
2
6
in
tellec
tu
al
tr
ajec
to
r
y
,
e
x
te
n
d
in
g
f
r
o
m
f
o
u
n
d
atio
n
al
c
o
g
n
itiv
e
ar
ch
itectu
r
es
to
war
d
au
to
n
o
m
o
u
s
co
g
n
itiv
e
ec
o
s
y
s
tem
s
.
R
ath
er
th
an
tr
ea
tin
g
in
tellig
en
ce
as
a
s
tatic
p
r
o
p
e
r
ty
,
th
e
f
r
am
ewo
r
k
em
p
h
asizes
its
co
n
tin
u
o
u
s
s
ca
lin
g
ac
r
o
s
s
ar
ch
itectu
r
al
an
d
en
v
ir
o
n
m
en
tal
b
o
u
n
d
ar
ies.
T
h
is
s
h
if
t
r
e
f
r
am
es
in
tellig
en
ce
as a
s
y
s
tem
-
lev
el
p
h
en
o
m
en
o
n
th
at
ev
o
lv
es th
r
o
u
g
h
in
ter
ac
tio
n
,
ab
s
tr
ac
tio
n
,
a
n
d
in
teg
r
atio
n
.
I
n
tellig
en
t
b
eh
av
io
r
f
u
n
d
am
e
n
tally
ar
is
es
f
r
o
m
th
e
in
ter
ac
tio
n
o
f
th
r
ee
co
r
e
m
ec
h
an
is
m
s
:
lear
n
in
g
,
r
ep
r
esen
tatio
n
,
an
d
co
m
p
u
tat
io
n
al
p
e
r
ce
p
tio
n
.
T
h
ese
m
ec
h
an
is
m
s
en
ab
le
s
y
s
tem
s
to
c
o
n
s
tr
u
ct
s
tr
u
ctu
r
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
16
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
6
6
9
-
1676
1676
in
ter
n
al
m
o
d
els o
f
ex
p
er
ien
ce
an
d
co
n
tin
u
o
u
s
ly
r
ef
in
e
th
em
t
h
r
o
u
g
h
e
x
p
o
s
u
r
e
to
d
ata.
T
o
g
e
th
er
,
th
ey
f
o
r
m
th
e
m
in
im
al
co
m
p
u
tatio
n
al
s
u
b
s
tr
ate
r
eq
u
ir
e
d
f
o
r
ad
a
p
tiv
e
b
eh
av
io
r
in
a
r
tific
ial
s
y
s
tem
s
.
I
m
p
o
r
t
an
tly
,
th
is
s
u
b
s
tr
ate
p
r
ec
ed
es a
n
y
em
b
o
d
im
en
t in
p
h
y
s
ical
en
v
ir
o
n
m
en
ts
o
r
i
n
ter
a
ctio
n
with
h
u
m
a
n
ag
e
n
ts
.
T
h
is
co
m
p
u
tatio
n
al
s
u
b
s
tr
ate
n
atu
r
ally
ex
te
n
d
s
in
to
co
g
n
itiv
e
cy
b
e
r
-
p
h
y
s
ical
s
y
s
tem
s
,
wh
er
e
in
tellig
en
ce
b
ec
o
m
es e
m
b
e
d
d
e
d
with
in
r
ea
l
-
wo
r
ld
o
p
er
atio
n
a
l lo
o
p
s
.
I
n
s
u
c
h
s
y
s
tem
s
,
lear
n
in
g
an
d
p
er
ce
p
tio
n
ar
e
tig
h
tly
in
te
g
r
ated
with
s
en
s
in
g
,
co
m
m
u
n
icatio
n
,
an
d
co
n
tr
o
l
m
ec
h
an
is
m
s
.
T
h
is
i
n
teg
r
atio
n
e
n
ab
les
co
n
tin
u
o
u
s
ad
ap
tatio
n
u
n
d
er
d
y
n
am
ic
an
d
u
n
ce
r
tain
p
h
y
s
ic
al
co
n
d
itio
n
s
.
As
a
r
esu
lt,
in
tellig
en
ce
tr
an
s
itio
n
s
f
r
o
m
a
n
in
ter
n
al
c
o
m
p
u
tatio
n
a
l p
r
o
ce
s
s
to
a
d
is
tr
ib
u
ted
p
r
o
p
er
ty
o
f
e
n
g
in
ee
r
e
d
cy
b
er
-
p
h
y
s
i
ca
l in
f
r
astr
u
ctu
r
es.
A
f
u
r
th
er
e
v
o
lu
tio
n
lead
s
to
a
u
to
n
o
m
o
u
s
s
o
cio
-
co
g
n
itiv
e
s
y
s
tem
s
o
p
er
atin
g
with
in
h
u
m
a
n
-
ce
n
ter
ed
an
d
m
u
lti
-
ag
en
t
e
n
v
ir
o
n
m
en
ts
.
I
n
th
is
r
e
g
im
e,
i
n
tellig
en
ce
m
u
s
t
ex
ten
d
b
ey
o
n
d
a
d
ap
tatio
n
to
in
clu
d
e
in
f
er
e
n
ce
o
f
in
ten
t,
co
n
tex
tu
al
r
ea
s
o
n
in
g
,
an
d
co
o
r
d
in
atio
n
ac
r
o
s
s
h
ete
r
o
g
en
e
o
u
s
ag
en
ts
.
Sy
s
tem
s
ar
e
th
er
ef
o
r
e
r
eq
u
ir
ed
to
o
p
er
ate
u
n
d
e
r
co
n
s
tr
ain
ts
o
f
tr
u
s
t,
in
ter
p
r
etab
ilit
y
,
an
d
s
o
cial
alig
n
m
en
t.
T
h
is
s
tag
e
m
ar
k
s
a
s
h
if
t
f
r
o
m
f
u
n
ctio
n
al
a
u
to
n
o
m
y
to
r
esp
o
n
s
ib
le
co
g
n
itiv
e
au
to
n
o
m
y
in
c
o
m
p
lex
s
o
cio
-
tech
n
ical
ec
o
s
y
s
tem
s
.
Acr
o
s
s
th
ese
lay
er
s
,
in
tellig
en
ce
ex
h
ib
its
a
cu
m
u
lativ
e
an
d
co
n
tin
u
o
u
s
s
ca
lin
g
b
eh
a
v
io
r
r
ath
er
th
an
d
is
cr
ete
s
tag
e
tr
an
s
itio
n
s
.
I
t
e
m
er
g
es
f
r
o
m
i
n
ter
n
al
r
ep
r
esen
tatio
n
,
ex
p
an
d
s
t
h
r
o
u
g
h
p
h
y
s
ical
em
b
o
d
im
en
t,
a
n
d
u
ltima
tely
s
tab
ilizes
with
in
s
o
cially
em
b
ed
d
ed
au
to
n
o
m
y
.
E
ac
h
s
tag
e
b
u
ild
s
u
p
o
n
an
d
am
p
li
f
ies
th
e
ca
p
ab
ilit
ies
o
f
th
e
p
r
e
v
io
u
s
o
n
e,
f
o
r
m
in
g
a
h
ier
ar
c
h
ical
co
n
tin
u
u
m
o
f
c
o
g
n
itiv
e
d
ev
elo
p
m
en
t.
T
h
is
c
o
n
tin
u
ity
h
ig
h
lig
h
ts
in
tellig
en
ce
as a
n
ev
o
l
v
in
g
ar
c
h
itectu
r
al
p
r
o
p
er
ty
r
ath
er
th
a
n
an
is
o
lated
co
m
p
u
tatio
n
al
o
u
tco
m
e.
T
h
e
tr
an
s
f
o
r
m
atio
n
o
f
in
tellig
en
ce
r
ef
lects
a
b
r
o
ad
er
p
ar
ad
ig
m
s
h
if
t
in
elec
tr
ical
an
d
co
m
p
u
ter
en
g
in
ee
r
in
g
.
I
n
tellig
en
t
s
y
s
tem
s
ar
e
in
cr
ea
s
in
g
ly
d
ef
in
ed
b
y
th
eir
ca
p
ac
ity
f
o
r
ad
a
p
tatio
n
,
co
n
tex
tu
al
awa
r
en
ess
,
an
d
au
t
o
n
o
m
o
u
s
o
p
er
atio
n
in
o
p
en
en
v
ir
o
n
m
en
ts
.
T
h
is
s
h
i
f
t
m
o
v
es
t
h
e
d
is
cip
lin
e
b
ey
o
n
d
alg
o
r
ith
m
-
ce
n
tr
ic
d
esig
n
to
war
d
s
y
s
tem
-
ce
n
tr
ic
co
g
n
itiv
e
en
g
in
ee
r
in
g
.
T
h
e
I
J
E
C
E
2
0
2
6
ed
ito
r
ial
s
er
ies
ar
ti
cu
late
th
is
tr
an
s
itio
n
as
a
u
n
if
ie
d
s
cien
tific
n
a
r
r
ati
v
e
co
n
n
ec
tin
g
ar
tific
ial
in
telli
g
en
ce
,
c
y
b
er
-
p
h
y
s
ical
s
y
s
tem
s
,
an
d
a
u
to
n
o
m
o
u
s
s
y
s
tem
d
esig
n
.
8
.
CO
NCLU
SI
O
N
T
h
e
em
er
g
en
ce
o
f
in
tellig
en
c
e
f
r
o
m
co
m
p
u
tatio
n
is
g
o
v
er
n
ed
b
y
th
e
r
ec
u
r
s
iv
e
in
ter
ac
ti
o
n
am
o
n
g
lear
n
in
g
,
r
ep
r
esen
tatio
n
,
a
n
d
co
m
p
u
tatio
n
al
p
er
ce
p
tio
n
.
T
h
is
in
ter
ac
tio
n
d
o
es
n
o
t
p
r
o
d
u
ce
in
tellig
en
ce
as
a
d
ir
ec
t
co
m
p
u
tatio
n
al
o
u
tp
u
t b
u
t
as
an
ev
o
lv
in
g
c
o
g
n
iti
v
e
p
r
o
ce
s
s
.
T
h
r
o
u
g
h
th
is
p
r
o
ce
s
s
,
s
y
s
tem
s
co
n
tin
u
o
u
s
ly
co
n
s
tr
u
ct,
o
r
g
a
n
ize,
an
d
r
ef
i
n
e
s
tr
u
ctu
r
ed
k
n
o
wled
g
e
f
r
o
m
ex
p
er
ien
ce
.
I
n
tellig
e
n
ce
is
th
er
ef
o
r
e
b
etter
u
n
d
er
s
to
o
d
as a
n
em
e
r
g
en
t
p
r
o
p
er
ty
o
f
ad
ap
tiv
e
co
m
p
u
tatio
n
al
o
r
g
an
izatio
n
.
T
h
is
p
er
s
p
ec
tiv
e
r
e
f
r
am
es
co
m
p
u
tatio
n
f
r
o
m
d
eter
m
i
n
is
tic
ex
ec
u
tio
n
to
war
d
co
n
tin
u
o
u
s
co
g
n
itiv
e
f
o
r
m
atio
n
.
I
n
tellig
en
ce
is
n
o
t
en
co
d
ed
in
alg
o
r
ith
m
s
alo
n
e
b
u
t
ar
is
es
f
r
o
m
th
e
s
tr
u
ctu
r
ed
alig
n
m
en
t
b
etwe
en
d
ata,
r
ep
r
esen
tatio
n
,
an
d
en
v
ir
o
n
m
en
tal
f
ee
d
b
ac
k
.
T
h
i
s
alig
n
m
en
t
en
a
b
les
s
y
s
tem
s
to
ev
o
lv
e
in
ter
n
al
m
o
d
els
th
at
r
em
ain
s
tab
le
y
et
ad
ap
ta
b
l
e
ac
r
o
s
s
ch
an
g
in
g
co
n
tex
ts
.
C
o
n
s
eq
u
en
tly
,
in
tellig
en
ce
is
d
ef
in
ed
b
y
its
ca
p
ac
ity
f
o
r
p
e
r
s
is
ten
t a
n
d
s
tr
u
ctu
r
ed
a
b
s
tr
ac
tio
n
.
T
h
e
im
p
licatio
n
s
o
f
th
is
v
iew
ar
e
f
u
n
d
am
e
n
tally
ar
ch
itectu
r
a
l in
n
atu
r
e.
Fu
tu
r
e
p
r
o
g
r
ess
in
in
tellig
en
t
s
y
s
tem
s
d
ep
en
d
s
less
o
n
is
o
lated
im
p
r
o
v
em
en
ts
in
m
o
d
el
s
ca
le
o
r
o
p
tim
izatio
n
tech
n
iq
u
es
an
d
m
o
r
e
o
n
t
h
e
co
h
er
en
ce
o
f
in
te
g
r
ated
c
o
g
n
i
tiv
e
ar
ch
itectu
r
es.
T
h
ese
ar
c
h
itectu
r
es
m
u
s
t
u
n
if
y
lear
n
in
g
,
r
ep
r
esen
tatio
n
,
a
n
d
p
er
ce
p
tio
n
in
t
o
co
n
tin
u
o
u
s
a
d
ap
tiv
e
lo
o
p
s
.
W
ith
o
u
t
s
u
ch
in
teg
r
atio
n
,
s
ca
lab
ilit
y
in
in
tellig
en
ce
r
em
ain
s
f
u
n
ctio
n
ally
lim
ited
.
R
ec
en
t
ad
v
an
ce
s
i
n
ar
tific
ial
i
n
tellig
en
ce
—
in
clu
d
in
g
f
o
u
n
d
a
tio
n
m
o
d
els,
m
u
ltimo
d
al
lear
n
in
g
,
s
elf
-
s
u
p
er
v
is
ed
lear
n
i
n
g
,
em
b
o
d
ie
d
in
tellig
en
ce
,
an
d
au
to
n
o
m
o
u
s
ag
en
ts
—
ca
n
b
e
in
ter
p
r
eted
with
in
th
is
u
n
if
ied
co
g
n
itiv
e
f
r
am
ewo
r
k
.
R
ath
er
th
an
r
e
p
r
esen
tin
g
in
d
ep
e
n
d
e
n
t
tech
n
o
l
o
g
ical
d
ir
ec
tio
n
s
,
t
h
ese
d
ev
elo
p
m
en
ts
r
ef
lect
co
n
v
er
g
en
t
attem
p
ts
to
ap
p
r
o
x
im
ate
s
tr
u
ctu
r
ed
an
d
co
n
tin
u
o
u
s
in
tellig
en
ce
.
T
h
eir
co
llectiv
e
s
ig
n
if
ican
ce
lies
in
th
e
g
r
ad
u
al
tr
an
s
itio
n
f
r
o
m
task
-
s
p
ec
if
ic
co
m
p
u
tatio
n
to
g
en
er
alize
d
c
o
g
n
itiv
e
ad
ap
ta
b
ilit
y
.
T
h
is
co
n
v
er
g
en
ce
r
ei
n
f
o
r
ce
s
th
e
a
r
c
h
itectu
r
al
n
atu
r
e
o
f
in
tellig
en
c
e.
Mo
r
e
b
r
o
ad
ly
,
th
is
co
n
ce
p
tu
al
f
o
u
n
d
atio
n
u
n
d
er
p
in
s
t
h
e
I
J
E
C
E
2
0
2
6
ed
ito
r
ial
s
er
ies
as
a
s
tr
u
ctu
r
ed
r
esear
ch
n
ar
r
ativ
e.
W
h
ile
th
is
ed
ito
r
ial
f
o
c
u
s
es
o
n
th
e
em
er
g
en
ce
o
f
in
tellig
en
ce
f
r
o
m
co
m
p
u
tatio
n
,
s
u
b
s
eq
u
en
t
co
n
tr
ib
u
tio
n
s
ex
ten
d
th
e
d
is
cu
s
s
io
n
to
war
d
em
b
o
d
ie
d
cy
b
er
-
p
h
y
s
ical
s
y
s
tem
s
an
d
au
to
n
o
m
o
u
s
s
o
cio
-
co
g
n
itiv
e
ec
o
s
y
s
tem
s
.
T
h
is
p
o
s
itio
n
in
g
estab
lis
h
es
th
e
p
r
esen
t
wo
r
k
a
s
a
f
o
u
n
d
atio
n
al
c
o
n
ce
p
tu
al
la
y
er
f
o
r
a
m
u
lti
-
s
tag
e
co
g
n
itiv
e
en
g
in
ee
r
in
g
f
r
am
e
wo
r
k
.
T
h
e
co
n
tin
u
ity
ac
r
o
s
s
ed
ito
r
ials
r
ef
lects
a
d
elib
er
a
te
ef
f
o
r
t
to
f
o
r
m
alize
in
tellig
en
ce
as a
n
ev
o
l
v
in
g
e
n
g
in
ee
r
in
g
c
o
n
s
tr
u
ct.
Ultim
ately
,
th
e
tr
ajec
to
r
y
o
f
el
ec
tr
ical
an
d
co
m
p
u
ter
e
n
g
in
ee
r
in
g
will
b
e
d
eter
m
in
ed
b
y
th
e
s
h
if
t f
r
o
m
co
m
p
u
tatio
n
al
ef
f
icien
c
y
to
w
ar
d
ar
ch
itectu
r
al
in
tellig
en
ce
.
Fu
tu
r
e
s
y
s
tem
s
will
b
e
ev
al
u
ated
n
o
t
o
n
ly
b
y
p
er
f
o
r
m
an
ce
m
et
r
ics
b
u
t
b
y
t
h
eir
ab
ilit
y
to
ad
ap
t,
g
en
e
r
alize
,
an
d
o
p
er
ate
r
esp
o
n
s
ib
ly
in
o
p
en
e
n
v
ir
o
n
m
en
ts
.
Ach
iev
in
g
t
h
is
r
eq
u
ir
es
a
tr
an
s
itio
n
f
r
o
m
alg
o
r
ith
m
-
ce
n
tr
ic
m
eth
o
d
o
lo
g
ies
to
war
d
in
teg
r
ate
d
co
g
n
itiv
e
s
y
s
tem
d
esig
n
.
I
n
t
h
is
co
n
tex
t,
in
tellig
en
ce
b
ec
o
m
es a
d
esig
n
p
r
i
n
cip
le
r
ath
er
th
an
a
co
m
p
u
ta
tio
n
al
b
y
p
r
o
d
u
ct.
Evaluation Warning : The document was created with Spire.PDF for Python.