Scribd
Upload
95 views18 pages

Artificial Neural Networks

The document discusses the McCulloch-Pitts neuron model, which was the first artificial neuron model (1). The MP neuron operates on a discrete time scale and uses binary inputs of 0 or 1 (2). Each neuron has a threshold and will output a 1 if the weighted sum of its inputs exceeds the threshold, otherwise it outputs a 0 (3). The MP neuron can implement basic logical functions like AND, OR, and NOT through appropriate setting of weights and thresholds.

Uploaded by

Anurag Lahkar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
95 views18 pages

Artificial Neural Networks

The document discusses the McCulloch-Pitts neuron model, which was the first artificial neuron model (1). The MP neuron operates on a discrete time scale and uses binary inputs of 0 or 1 (2). Each neuron has a threshold and will output a 1 if the weighted sum of its inputs exceeds the threshold, otherwise it outputs a 0 (3). The MP neuron can implement basic logical functions like AND, OR, and NOT through appropriate setting of weights and thresholds.

Uploaded by

Anurag Lahkar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 18

Part 2.

Artificial neural networks.

1
The McCulloch-Pitts Neuron
(1943).
McCulloch and Pitts demonstrated that
“…because of the all-or-none
character of nervous activity, neural events
and the relations among them can be
treated by means of the propositional logic”.

2
The McCulloch-Pitts Neuron –

discrete time
machine.

• Thus, the McCulloch-Pitts neuron operates on a


discrete time scale, t = 0,1,2,3,…

3
The McCulloch-Pitts Neuron –

discrete time
machine.
binary unit.

• The input values ait from the i-th presynaptic neuron


at any instant t may be equal either to 0 or 1 only

4
The McCulloch-Pitts Neuron –

discrete time
machine.

• The weights of connections wi are


+1 for excitatory type connection and
-1 for inhibitory type connection.

5
The McCulloch-Pitts Neuron –

discrete time
machine.

• There is an excitation threshold  associated with


the neuron.

6
The McCulloch-Pitts Neuron.
Output Xt+1 of the
neuron at the
following instant t+1
is defined according
to the rule:

X t 1
 1 if and only if S   wi a   ,
t t
i
i

while wi  0 ai  0.

7
The McCulloch-Pitts Neuron.

X t 1  1 if and only if
S t   wi ait   ,
i

while wi  0 ai  0.

• In the MP neuron, we shall call the instant total


input
St – instant state of the neuron.

8
The McCulloch-Pitts Neuron.

X t 1  1 if and only if
S t   wi ait   ,
i

while wi  0 ai  0.

• The statement “ while wi  0 ai  0 “ means that activity of


a single inhibitory input, i.e. input via a connection with
negative weight wi = -1, would absolutely prevents
excitation of the neuron at that instant.

9
Activation function.
• The output Xt+1 is function of the state St of the
neuron, therefore it also may be written as
function of discrete time
 t 
X t 1
 g ( S )  g   wi ai 
t

where  i 
g(St) is the threshold activation function

1, if S t  ;
g (S )  H (S   )  
t t

0, if S t  .

10
MP-neuron example.
  2;
w1  1,
w2  1,
w3  1.
X ?

11
MP-neuron example. Input 1.
  2;
w1  1,
w2  1,
w3  1.
X ?
1) a1=0, a2=0, a3=1
2) All inhibitory connections are silent
3) S = 0×(-1) + 0×1 + 1×1 = 1 < θ
4) S < θ => X=0
12
MP-neuron example. Input 2.
  2;
w1  1,
w2  1,
w3  1.
X ?
1) a1=0, a2=1, a3=1
2) All inhibitory connections are silent
3) S = 0×(-1) + 1×1 + 1×1 = 2 = θ
4) S = θ => X=1
13
MP-neuron example. Input 3.
  2;
w1  1,
w2  1,
w3  1.
X ?
1) a1=1, a2=1, a3=1
2) There is an inhibitory connection activated
3) X=0

14
MP-neuron as a binary unit.
• Simple logical functions can be implemented directly
with a single McCulloch-Pitts unit.
• The output value 1 can be associated with the logical
value true and 0 with the logical value false.
• Now, let us demonstrate how weights and thresholds
can be set to yield neurons which realise the logical
functions AND, OR and NOT.

15
MP-neuron logic.
a1 a2 “AND”

1 1 1
0 1 0
= “AND”
1 0 0
0 0 0

“AND” - the output fires if a1 and a2 both fire.

16
MP-neuron logic.
a1 a2 “OR”

1 1 1
0 1 1
= “OR”
1 0 1
0 0 0

“OR” - the output fires if a1 or a2 or both fire.

17
MP-neuron logic.
a1 “NOT”
1 0
= “NOT”
0 1

“NOT”: the output fires if a1 does NOT fire


and vice versa.
18

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy