2
1
Neuron Model
and
Network Architectures
Docsity.com
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Guidelines and tips
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Neuron Model - Banking - Lecture Slides, Slides of Banking and Finance
Banking is an ever green field of study. In these slides of Banking, the Lecturer has discussed following important points : Neuron Model, Network Architectures, Input Neuron, General Neuron, Transfer Functions, Linear Transfer Function, Limit Transfer Function, Layer of Neurons, Abbreviated Notation, Multilayer Network
Typology: Slides
2012/2013
1 / 11
This page cannot be seen from the preview
Don't miss anything!
Related documents
Partial preview of the text
Download Neuron Model - Banking - Lecture Slides and more Slides Banking and Finance in PDF only on Docsity!
Neuron Model
and
Network Architectures
Docsity.co
a
f ( wp
b
)
General Neuron
a
n
Inputs
AA
b
p
w
AAAA
f
Single-Input Neuron
Docsity.co
Transfer Functions
1
1
n
0
b/w
p
0
AAAA
a = logsig
(^) (n)
Log-Sigmoid Transfer Function
a = logsig
(^) (wp
(^) b)
Single-Input
logsig
Neuron
a
a
Docsity.co
Multiple-Input Neuron
Multiple-Input Neuron
p
1
a
n
Inputs
b
p
2
p
3
p
R
w
1, (^) R
w
1, (^1)
AAAA
a
f (^) ( Wp
(^) b
)
AAAA
f
AAAAAA
f
Multiple-Input Neuron
a
f (^) ( Wp
(^) b
)
p
a
n
AA
W
AAAA
b
R (^) x (^1)
1 (^) x (^) R
1 (^) x (^1)
1 (^) x (^1)
1 (^) x (^1)
Input
R
Abreviated Notation
Docsity.co
Abbreviated Notation
AAAAAA
f
Layer of
S
Neurons
a
f ( Wp
(^) b
p
a
n
A
W
AA
b
R (^) x (^1)
S (^) x (^) R
S (^) x (^1)
S (^) x (^1)
S (^) x (^1)
Input
R
S
W
w
1 1 ,
w
1 2 ,
…
w
1
R
,
w
2 1 ,
w
2 2 ,
…
w
2
R
,
w
S^
1
,
w
S
2
,
…
w
S R^ ,
=
b
S 2 1
=
b b b
p
p 1
p 2
p
R^
=
a
a 1
a 2
a S
=
Docsity.co
Multilayer Network
First Layer
a 1 =
f 1 (^ W
1 p (^) +
(^) b 1 ) a 2 = f 2
(^ W
2 a 1 +^ (^) b
2 ) a 3 = f 3
(^ W
3 a 2 +^ (^) b
3 )
AAAA
f 1
AAAA
f 2
AA
f 3
Inputs
a 3 2
n 3 2
w
3 S (^) 3 , S (^) 2
w
3 1,
b 3 2
b 3 1
b 3 S (^) 3
a 3 S (^) 3
n 3 S (^) 3
a 3 1
n 3 1
1 1 1
1 1 1
1 1 1
p 1
a 1 2
n 1 2
p 2
p 3
p R
w
1 S 1 , R
w
1 1,
a 1 S (^) 1
n 1 S (^) 1
a 1 1
n 1 1
a 2 2
n 2 2
w
2 S 2 , S
1
w
2 1,
b 1 2
b 1 1
b 1 S (^) 1
b 2 2
b 2 1
b 2 S (^) 2
a 2 S (^) 2
n 2 S 2
a 2 1
n 2 1
AAAA
Σ
AA
Σ
AAAA
Σ
AAAA
Σ
AA
Σ
AAAA
Σ
AAAA
Σ
AA
Σ
AAAA
Σ
AA
f 1
AAAA
f 1
AAAA
f 2
AAAA
f 2
A
f 3
AA
f 3
a 3 =
f 3 (^ W
3 f 2 (^ W
2 f 1 (^ W
1 p (^) +
(^) b 1 ) (^) +
(^) b
2 ) (^) +
(^) b
3 )
Third Layer
Second Layer
Docsity.co
Delays and Integrators
AAAA
D
a
( t )
u
( t )
a
(0)
a
( t ) =
u
( t (^) -
Delay
a
( t )
a
(0)
Integrator
u
( t )
a
( t ) =
u ( τ ) d τ + a
0 t
Docsity.co
Recurrent Network
Sym. Sat. Linear Layer
AA A
R (^) x (^1)
S (^) x (^) R
S (^) x (^1)
S (^) x (^1)
S (^) x (^1)
Initial
Condition
p
a
( t (^) +
n
( t (^) +
W
b
S
S
AAAA
D
AAAAAA
a
( t )
a
(0)
p
a
( t (^) +
satlin
Wa
t ) (^) +
(^) b
S (^) x (^1)
a
2
(
)
satlins Wa
1
(
)
b
(
)
=
a
1
(
)
satlins Wa
0
(
)
b
(
)
satlins Wp
b
(
)
=
=
Docsity.co