Genetic Algorithm Optimization Questions

1. Using the Genetic Algorithm, maximize the function f(x) = x^3 with x in the interval
[0, 50], where x = 0, 1, 2, ..., 50.

2. Apply the Genetic Algorithm to minimize the function f(x) = (x - 10)^2 for x in the
range [0, 31], where x = 0, 1, 2, ..., 31.

3. Using the Genetic Algorithm, find the maximum value of the function f(x) = 2x + x^2
for x in the range [0, 20], where x = 0, 1, 2, ..., 20.

4. Use the Genetic Algorithm to find the value of x that minimizes f(x) = |x - 15| for x in
the set {0, 1, 2, ..., 31}.

5. Using the Genetic Algorithm, maximize the function f(x) = 5sin(x) + x^2 for x in the
interval [0, 40], where x = 0, 1, 2, ..., 40.

Discrete Hopfield Network Questions

1. For a system with an input vector given by [1, -1, 1, -1]:

i) Construct an auto-associative Discrete Hopfield Network.

ii) Test the Discrete Hopfield Network when the third and fourth components of
the stored vector are missing.

2. Given the stored pattern [1, 1, -1, -1, 1], perform the following:

i) Construct a Discrete Hopfield Network.

ii) Test the network when the second and fifth components of the stored vector are
missing.

3. A Discrete Hopfield Network stores the pattern [-1, 1, 1, -1, -1]. Perform the
following:

i) Construct the weight matrix for the Hopfield Network.

 ii) Test the network when the first and last components of the stored vector are
missing.

4. Consider a Discrete Hopfield Network with the stored pattern [1, -1, -1, 1]:

i) Construct the Hopfield Network and determine its weight matrix.

ii) Test the network when the second and third components are missing.

5. For the input pattern [-1, -1, 1, 1, -1, 1], perform the following:

i) Design an auto-associative Discrete Hopfield Network.

ii) Test the network with missing values in the first and fourth components of the
stored vector.

Auto-Associative Network Training and Testing Questions

1.
a) Train the Auto-associative network for the input vector [1, -1, 1, -1].

b) Test the network for the following:

i) The same input vector.
ii) One missing entry in the test vector.
iii) Two mistaken entries in the test vector.

2.

a) Train an Auto-associative network using the input vector [1, 1, -1, 1, -1].
b) Evaluate the network by testing:
i) The same input vector.
ii) A test vector with one missing component.
iii) A test vector with two incorrect values.

3. a) Construct an Auto-associative network trained with the input pattern [-1, -1, 1, 1, 1].
b) Test the trained network under the following conditions:
 i) Using the same stored vector.
ii) With one missing entry in the test vector.
iii) With two incorrect components in the test vector.

4. a) Train an Auto-associative network using the stored pattern [1, -1, -1, 1, 1].
b) Validate the network's performance by testing:
i) With the original input pattern.
ii) With one missing element in the test vector.
iii) With two incorrect values in the test vector.

5. a) Implement an Auto-associative network trained on the input vector [-1, 1, -1, 1, 1].
b) Test the network under different scenarios:

i) Using the same input vector.

ii) With one missing value in the test vector.
iii) With two mistaken values in the test vector.

Bidirectional Auto-associative Network (BAM) Questions

1. Construct and test a Bidirectional Auto-associative Network (BAM) to associate letters

A and B with sample bipolar Input-Output vectors. The target output for A is (-1, -1) and
for B is (1, -1). The display Matrix size is 4x3 input patterns.

2. Implement a BAM network to associate letters C and D using bipolar Input-Output

vectors. The target output for C is (-1, 1) and for D is (1, -1). The display matrix should
have a 6x3 pattern size.

3. Design and test a Bidirectional Associative Memory (BAM) to store and recall letters
X and Y with given bipolar Input-Output vectors. Target output for X is (1, -1) and for Y
is (-1, 1). The display matrix size should be 5x4 input patterns.
4. Construct a BAM model to associate letters M and N with bipolar Input-Output
representations. The expected output for M is (-1, -1) and for N is (1, 1). Use a display
matrix of size 5x3.

5. Develop and verify a Bidirectional Associative Memory (BAM) network for

associating letters G and H with bipolar Input-Output vectors. The target output for G is
(-1, 1) and for H is (1, -1). The input display matrix should have 6x3 dimensions.

ADELINE algorithm

1. Use the ADELINE algorithm to train the NAND function with bipolar inputs and
outputs. Perform a single epoch for this training.
2. Implement the ADELINE algorithm to train the NOR function using bipolar
inputs and outputs. Train the model for one epoch and observe the weight
updates.
3. Train an ADELINE network to learn the XOR function with bipolar input-output
pairs. Carry out a single training epoch and analyze the weight adjustments.
4. Apply the ADELINE algorithm to train the XNOR function with bipolar
representations. Perform only one epoch and check the learning progress.
5. Use ADELINE to train the OR function using bipolar inputs and outputs. Conduct
a single epoch and examine the network’s weight updates.

Linear Discriminant Projection Questions

1. Compute the Linear Discriminant Projection for the following 2-dimensional

dataset:

 Class w₁: W = (x₁, x₂) = {(1,2), (3,4), (5,6), (2,1), (3,5)}

 Class w₂: W = (x₁, x₂) = {(7,8), (9,10), (8,6), (10,9), (7,5)}
 2. Determine the optimal linear discriminant projection for the given 2D dataset:

 Class w₁: W = (x₁, x₂) = {(2,3), (4,5), (1,1), (3,4), (2,2)}

 Class w₂: W = (x₁, x₂) = {(6,7), (8,9), (7,5), (9,6), (10,8)}

3. Compute the Fisher's Linear Discriminant projection for the 2D dataset:

 Class w₁: W = (x₁, x₂) = {(3,5), (5,7), (6,8), (4,6), (7,9)}

 Class w₂: W = (x₁, x₂) = {(10,12), (9,11), (12,10), (11,13), (10,9)}

4. Calculate the Linear Discriminant function for the following data points:

 Class w₁: W = (x₁, x₂) = {(4,2), (5,3), (3,4), (2,2), (6,4)}

 Class w₂: W = (x₁, x₂) = {(8,9), (9,7), (7,10), (6,8), (10,6)}

6. Perform Linear Discriminant Analysis (LDA) and find the projection direction for
the following dataset:

 Class w₁: W = (x₁, x₂) = {(2,1), (3,3), (4,2), (3,4), (5,2)}

 Class w₂: W = (x₁, x₂) = {(7,8), (9,6), (8,7), (6,5), (10,9)}

Fuzzy C-Means Clustering:

1. Perform Fuzzy C-Means Clustering for the given data points:
{(2,4),(3,6),(5,7),(8,9),(9,10)}

2. Apply Fuzzy C-Means Clustering to group the following dataset into clusters:
{(1,2),(3,5),(4,6),(7,8),(8,10)}

3. Use the Fuzzy C-Means algorithm to classify the given data points:
{(2,3),(4,5),(5,6),(7,8),(9,11)}

4. Implement Fuzzy C-Means Clustering on the dataset:

{(1,4),(3,7),(6,9),(8,10),(10,12)}.

5. Cluster the given points using the Fuzzy C-Means algorithm:

{(2,3),(4,6),(6,8),(7,9),(9,10)}