Professional Documents
Culture Documents
Pattern association
Pattern recognition
Function approximation
Filtering
Beam forming
Identification and Control
x1
(vk )
x2
vk
wkj
-1
dk
yk
ek
xm
Where n=1,2, is the iteration number, x j j 1,2,..., m is
the input, is the learning rate parameter, vk (n) is the net
activity of the neuron k, (vk (n)) yk (n) is the out put of
the neuron k, d k is the desired response, ek (n) is the error
between the output and the desired response of the neuron k
and wkj (n) is the correction applied to the synaptic
weight between the neuron k and the input node j=1,2, ,
m. There will be no weight correction for the cases were the
actual response and the desired response is equal.
Example
Consider a single perceptron with the set of input training
vectors (samples) and initial weight vector
1
0
1
1
2
1.5
1
1
, x3 ; w (1)
x1 , x 2
0
0.5
0.5
0
1
1
1
0.5
for
0.2
0
0 0
0.5
1 0.7
0
0.5 0.1
0.7
1 0.5
or
performance
index.
Since
we
are
(w ) 12 (ek 2 )
1
1
(d k y k ) 2 (d k (vk ))2
2
2
Where w [ wkj ] . The cost function (w ) denotes
the instantaneous energy, which can be used to make
the necessary changes in the synaptic weights. This
10
,
, ,
wmk
w1k w2 k
and
( w )
,
, ,
w
2k
mk
1k
(w )
(d k (vk )) ' (vk )
wkj
Since the minimization of the error requires the
changes in weight to be in the negative gradient
direction, we have
11
Exapmple:
Consider the set of input training vectors and initial
weight vector
1
0
1
1
2
1.5
1
1
1
, x3 ; w
x1 , x 2
0
0.5
0.5
0
1
1
1
0.5
d1 1, d 2 1, and d3 1,
respectively.
(v k )
1 e vk
1 e vk
2e vk
1
' (v k )
(1 2 (vk ))
(1 e vk ) 2 2
Such an activation function is continuous and bipolar.
Here the slope of activation function is expressed in
terms the output signal of the neuron. For the given
learning rate parameter the delta rule training can be
summarized as follows:
12
0.974
0.948
0
.
526
Step 2
We will present
vk2 ( w 2 )T x 2 1.948
yk2 (vk2 ) 0.75
' (vk2 )
1
[1 2 (vk2 )] 00.218
2
13
0.974
0.956
0
.
531
v k3 (w 3 ) T x 3 2.46
y k3 (v k3 ) 0.842
1
2
' (v k3 ) [1 2 (v k3 )] 0.145
0.947
0.929
w 4 w 3 0.1[d 3 (v k3 )] ' (v k3 ) x 3
0.016
0
.
505
14
Example:
Consider a single perceptron with the set of input
training vectors (samples) and initial weight vector
1
1
0
1
2
0.5
1
1
, x3 ; w(1)
x1 , x 2
1.5
2
1
0
0
1.5
1.5
0.5
0.5
av
( v ) tan h
2
1 e av
2
1
av
1 e av 1 e
This is bipolar continuous activation function lies
between 1 and 1 as a .
15
4. Hebbian learning
To Donald Hebb in his famous book organizational
behavior (1949)
When an axon of cell A is near enough to excite a cell
B and repeatedly or persistently takes part in firing it,
some growth process or metabolic change takes place
in one or both cells such that A's efficiency, as one of
the cells firing B, is increased.
The above statement is in a neurobiological sense. For
more complex kinds of learning, almost every learning
modal that has been proposed, involves both output activity
and input activity in the learning rule. The essential idea is
that the amount of synaptic change is a function of both
pre-synaptic and post-synaptic activity. Based on the above
fact, Hebbian learning is the oldest and most famous of all
learning rules
The above statement is made in a neurobiological context.
We may expand and rephrase it as a two part rule
16
17
OR
w jk
xj
Pre-synaptic N. j
yk
Post-synaptic N. k
18
19
20
w kj (n)
w kj (n)
g ( x j (n))
(balance point)
(max. depression)
21
,
, ,
w
1
2
m
( w )
,
, ,
w
2
m
1
w (n 1) w (n) (w )
w (n 1) w (n) w (n)
w (n) (w )
22
23
When
becomes unstable.
1 if vk vi for all
yk 0 otherwise
i, i k
wkj 1
i
for all k
wkj 0
if neuron k losses the compition
O1
Ok
Op
24
w ji e j xi and
w ji y j xi
e j xi
25
w kj (n)
w kj (n)
g ( x j (n))
(balance point)