Artificial Intelligence

Artificial Intelligence
Question 1
a) For a two input network with two hidden nodes and one output node with both layers using a
logistic activation function we have:
1 b
w w
x: x1 w1=[11 ⊔ 21] w2=[b2 W11 W12]
biz W12 W22
x2

and the Logistic function is ∶ W where B =1
0.4 0.1 – 0.2
x: w1= w2=[0.2 -0.5]
0.7 0.4 0.2
0.5
b1: b2 ⋮ [-0.6]
0.2
Calculate the output of the Network.
[13 Marks]
b) Describe and sketch the Perceptron and state Hebb’s training rule
[10 Marks]
c) Describe the two main training methods for Neural Networks?
[10 Marks]
Question 2
It is proposed to install a fuzzy speed cruise control system in an automobile. In order to check the efficiency
of the controller a simulation is to be undertaken.
The vehicle dynamics can be simulated using the recursive equations:
v(n) =1oov(n – 1) + 10ooTP – 0.5001 – 1)
In which v(n) is the current speed , v(n-l) is the value of speed at the previous calculation TP is the value of
the throttle position derived from the fuzzy cruise controller and 6(n-1) is the angle of the car – uphill
(positive) or downhill (negative)
The membership functions of the fuzzy speed controller are determined by the setting the cruise controller
for a particular speed. The setting to be considered is 50 mph and the appropriate controller fuzzy sets are
shown in figure Q1 below.
m(v> m(e> _m(TP
Low OK Hig Dow LIve Up 1.0
1:
45 50 55 -5 0 5 2 4 6 8 10
(mph) ⊖ (degrees) Throttle
Figure Q1
The Knowledge base for the cruise controller is shown in table Q1 below.
Up Level Down
Speed
LM LIVI Low
High
Table Q1
a) If the initial condition of speed is 52.5 mph and the angle of incline is -50 use the FAM bank to derive
only those rules, in their full “if .. then .. else” form, which contribute to the output of the Throttle
Position.
[10 Marks]
b) Using the rules derived in part (a) calculate the required position of the throttle, TP, as a fuzzy set,
using the max/min rule of composition. Use a sketch to show how you evaluate the output from
each rule and how you combine the output from each rule to form the output fuzzy set representing
the required throttle position.
[14 Marks]
c) Calculate the throttle position as a fuzzy singleton using the centre-of-gravity method on the output
fuzzy set representing throttle position calculated in part (b)
[10 Marks]
Question 3
a) A Genetic Algorithm (GA) in its simplest form involves three types of operators, selection, crossover
and mutation, choose two of them and briefly describe them.
[10 Marks]
b) Suppose you are given a clearly defined problem to be solved and a bit string representation for all
candidate solutions, list and discuss all the steps for a simple genetic algorithm.
[13 Marks]
c) Discuss the Roulette wheel selection method in GAs and provide an example.
[10 Marks]

Place this order with us and get 18% discount now! to earn your discount enter this code: special18 If you need assistance chat with us now by clicking the live chat button.