McCulloch-Pitts Neuron
Dr. Pravat Kumar Rout
Department of EEE, ITER, SOA University
Theory
Warren S. McCulloch
The McCulloch-Pitts Neuron was the
earliest neural network discovered in
1943.
The weights associated with
communication links may be
excitatory (weights are positive) or
inhibitory (weights are negative)
A threshold activation function plays
a major role in the M-P neuron. If the
net input is greater than the sum of
the input signals, the neuron fires.
Mostly used in the logic functions.
The activation of M-P neuron is
always binary in nature.
It consists of a number of input units
connected to a single output unit.
Salient features of McCulloch-Pitts artificial neuron
Architecture
Q1. For the network shown in Figure 1, calculate the weights are net input to the output neuron.
Solution: The given neural net consists of three input neurons and one output neuron. The inputs
and weights are
[𝑥1, 𝑥2, 𝑥3] = [0.3,0.5,0.6]
𝑤1, 𝑤2, 𝑤3 = [0.2,0.1, −0.3]
The net input can be calculated as
𝑦𝑖𝑛 = 𝑥1𝑤1 + 𝑥2𝑤2 + 𝑥3𝑤3
= 0.3 × 0.2 + 0.5 × 0.1 + 0.6 × −0.3
= 0.06 + 0.05 − 0.18 = −0.07
Example-1
Q2. Calculate the net input for the network shown in Figure 2 with bias included in the network.
Solution: The given net consists of two input neurons a bias and an output neuron. The inputs are
x1, x2 = 0.2,0.6 and the weights are [w1, w2]=[0.3,0.7]. Since the bias is included b=0.45 and bias
input x0is equal to 1. The net input is calculated as
yin= b + x1w1 + x2w2
= 0.45 + 0.2 × 0.3 + 0.6 × 0.7
= 0.45 + 0.06 + 0.42 = 0.93
Therefore, yin = 0.93is the net input.
Example-2
Q3. Obtain the output of the neuron Y for the network shown in Figure 3 using activation function
as: (1)binary sigmoidal and (ii) bipolar sigmoidal.
Solution: The given network has three neurons with bias and output neuron. These form a single layer
network. The inputs ere given as x1, x2, x3 = 0.8,0.6,0.4 and the weights are [w1, w2, w3]=[0.1,0.3,-0.2]
with bias b=0.35 (its input is always 1). The net input to the output neuron is
𝑦𝑖𝑛 = 𝑏 + ෍
𝑖=1
𝑛
𝑥𝑖𝑤𝑖
[n=3, because only 3 input neurons are given]
= b + x1 w1 + x2w2 + x3w3
= 0.35 + 0.8 × 0.1 + 0.6 × 0.3 + 0.4 × −0.2
= 0.35 + 0.08 + 0.18 − 0.08 = 0.53
(i)For binary sigmoidal activation function,
𝑦 = 𝑓 𝑦𝑖𝑛 =
1
1+𝑒−𝑦𝑖𝑛
=
1
1+𝑒−0.53 = 0.625
(ii) For bipolar sigmoidal activation function,
𝑦 = 𝑓 𝑦𝑖𝑛 =
2
1+𝑒−𝑦𝑖𝑛
− 1 =
2
1+𝑒−0.53 − 1 = 0.259
Example-3
Example-4: M-P Neuron to implementation the
logical AND operation
Example-5: M-P Neuron to implementation
the logical OR operation
Example-6: M-P Neuron to implementation the
logical AND-NOT operation
Example-7: M-P Neuron to implementation
the logical XOR operation
Assignment
Write down a suitable MATLAB program for implementing logic functions using M-P
neuron?
Mc culloch pitts neuron

Mc culloch pitts neuron

  • 1.
    McCulloch-Pitts Neuron Dr. PravatKumar Rout Department of EEE, ITER, SOA University
  • 2.
  • 4.
    Warren S. McCulloch TheMcCulloch-Pitts Neuron was the earliest neural network discovered in 1943. The weights associated with communication links may be excitatory (weights are positive) or inhibitory (weights are negative) A threshold activation function plays a major role in the M-P neuron. If the net input is greater than the sum of the input signals, the neuron fires. Mostly used in the logic functions. The activation of M-P neuron is always binary in nature. It consists of a number of input units connected to a single output unit.
  • 5.
    Salient features ofMcCulloch-Pitts artificial neuron
  • 6.
  • 8.
    Q1. For thenetwork shown in Figure 1, calculate the weights are net input to the output neuron. Solution: The given neural net consists of three input neurons and one output neuron. The inputs and weights are [𝑥1, 𝑥2, 𝑥3] = [0.3,0.5,0.6] 𝑤1, 𝑤2, 𝑤3 = [0.2,0.1, −0.3] The net input can be calculated as 𝑦𝑖𝑛 = 𝑥1𝑤1 + 𝑥2𝑤2 + 𝑥3𝑤3 = 0.3 × 0.2 + 0.5 × 0.1 + 0.6 × −0.3 = 0.06 + 0.05 − 0.18 = −0.07 Example-1
  • 9.
    Q2. Calculate thenet input for the network shown in Figure 2 with bias included in the network. Solution: The given net consists of two input neurons a bias and an output neuron. The inputs are x1, x2 = 0.2,0.6 and the weights are [w1, w2]=[0.3,0.7]. Since the bias is included b=0.45 and bias input x0is equal to 1. The net input is calculated as yin= b + x1w1 + x2w2 = 0.45 + 0.2 × 0.3 + 0.6 × 0.7 = 0.45 + 0.06 + 0.42 = 0.93 Therefore, yin = 0.93is the net input. Example-2
  • 10.
    Q3. Obtain theoutput of the neuron Y for the network shown in Figure 3 using activation function as: (1)binary sigmoidal and (ii) bipolar sigmoidal. Solution: The given network has three neurons with bias and output neuron. These form a single layer network. The inputs ere given as x1, x2, x3 = 0.8,0.6,0.4 and the weights are [w1, w2, w3]=[0.1,0.3,-0.2] with bias b=0.35 (its input is always 1). The net input to the output neuron is 𝑦𝑖𝑛 = 𝑏 + ෍ 𝑖=1 𝑛 𝑥𝑖𝑤𝑖 [n=3, because only 3 input neurons are given] = b + x1 w1 + x2w2 + x3w3 = 0.35 + 0.8 × 0.1 + 0.6 × 0.3 + 0.4 × −0.2 = 0.35 + 0.08 + 0.18 − 0.08 = 0.53 (i)For binary sigmoidal activation function, 𝑦 = 𝑓 𝑦𝑖𝑛 = 1 1+𝑒−𝑦𝑖𝑛 = 1 1+𝑒−0.53 = 0.625 (ii) For bipolar sigmoidal activation function, 𝑦 = 𝑓 𝑦𝑖𝑛 = 2 1+𝑒−𝑦𝑖𝑛 − 1 = 2 1+𝑒−0.53 − 1 = 0.259 Example-3
  • 11.
    Example-4: M-P Neuronto implementation the logical AND operation
  • 12.
    Example-5: M-P Neuronto implementation the logical OR operation
  • 13.
    Example-6: M-P Neuronto implementation the logical AND-NOT operation
  • 14.
    Example-7: M-P Neuronto implementation the logical XOR operation
  • 15.
    Assignment Write down asuitable MATLAB program for implementing logic functions using M-P neuron?