The McCulloch -pitts Neural Model

• The earliest artificial neural model was proposed by

McCulloch and Pitts in 1943.
• Following fig .depicts its structure .
• Its consists of number of inputs units connected to a
single output unit.
• The interconnected links are unidirectional.
• There are two kinds of inputs, namely
i) Excitatory input and
ii) Inhibitory inputs.
Fig.:Structure of a McCulloch-Pitts neuron

x1 X1 w
.

xm Xm
w

. Y y_out

xm+1 Xm+1

-v

xm+n Xm+n

-v
Features of the McCulloch -Pitts artificial neuron
• There are two kinds of inputs , excitatory and inhabitory.
• In fig. excitatory inputs are shown as a inputs X1...........Xm.
• Inhibitory inputs are connected Xm+1.................Xm+n.
• The excitatory inputs are connected to the output unit
through positively weighted links.
• Inhibitory inputs have negative weights on their connecting
paths to the output unit.
• All excitatory weights have teh same positive magnitude w
and all inhibitory weights have the same negative magnitude
-v.
Features of the McCulloch -Pitts artificial neuron

• The activation y_out =f(y_in ) is binary that is either 1( in case the

neuron fires) or 0 (in case the neuron does not fire.
• The activation function is a binary step function. It is 1 if the net input
y_in is greater than or equal to a given threshold value θ and 0
otherwise.
• The inhabition is absolute. A single inhibitory input threshold
prevent the neuron from firing irrespective of the number of
active excitatory inputs.
 Implementation of logical AND-NOT with McCulloch
-pitts Neural Model

• a) Truth Table
X1 X2 x1 AND (NOTx2)
0 0 0
0 1 0
1 0 1
1 1 0
 Implementation of logical AND-NOT with
McCulloch -pitts Neural Model
• b)
x1 X1
1
Y y_out
x2 X2

-1

Fig.: Neural Structure

Implementation of logical AND-NOT with
McCulloch -pitts Neural Model
• c) y_in =x1-x2

1 ,if y_in≥1
y_out=f(y_in)={
0, otherwise

(c) Activation Function.

Implementation of logical AND-NOT with McCulloch -pitts Neural Model

• The logical AND-NOT operation is

symbolically expressed as x1,x2,or x1AND
(NOT x2).
• Its produceds a 1 at the out put only when
x1 is 1 and x2 is 0.
 Implementation of logical XOR with McCulloch -pitts Neural Model

• a) Truth Table
X1 X2 x1 XOR x2
0 0 0
0 1 1
1 0 1
1 1 0
Implementation of logical XOR with McCulloch -pitts Neural Model

1
• X1 -1 Y1
1

Z
-1
X2 Y2 1
+1

Fig. Neural Structure.

Implementation of logical XOR with McCulloch -pitts Neural Model

1 ,if net_in≥1
f(net_in)={
0, otherwise

(c) Activation Function.

Any Question
THANK YOU