PG-Msc.AI S2, Soft Computing, First Internal Examination, February 2024

Section A

Answer any 4 questions. Weight 1 each.

1.    Write a short note on hybrid systems

Hybrid Systems computing uses more than one computational technique to solve various real world problems. This integration of multiple systems in one enables us to get highly intelligent results. These results are potent as well as adaptive to any new environment.

2.    Describe the structure of an artificial neuron

3.    Compare supervised and unsupervised learning approaches in ANN.

Supervised Learning	Unsupervised Learning
Supervised learning algorithms are trained using labeled data.	Unsupervised learning algorithms are trained using unlabeled data.
Supervised learning model takes direct feedback to check if it is predicting correct output or not.	Unsupervised learning model does not take any feedback.
Supervised learning model predicts the output.	Unsupervised learning model finds the hidden patterns in data.
In supervised learning, input data is provided to the model along with the output.	In unsupervised learning, only input data is provided to the model.
The goal of supervised learning is to train the model so that it can predict the output when it is given new data.	The goal of unsupervised learning is to find the hidden patterns and useful insights from the unknown dataset.
Supervised learning needs supervision to train the model.	Unsupervised learning does not need any supervision to train the model.
Supervised learning can be categorized in Classification and Regression problems.	Unsupervised Learning can be classified in Clustering and Associations problems.
Supervised learning can be used for those cases where we know the input as well as corresponding outputs.	Unsupervised learning can be used for those cases where we have only input data and no corresponding output data.

 

4.    Differentiate between Hard Computing and Soft Computing.

5.    Define linear separability.

Linear separability is an important concept in machine learning, particularly in the field of supervised learning. It refers to the ability of a set of data points to be separated into distinct categories using a linear decision boundary. In other words, if there exists a straight line that can cleanly divide the data into two classes, then the data is said to be linearly separable.

                                                                                     (4 x 1= 4 weightage)

Section B

Answer any 3 questions. Weight 2 each.

                                              

6.    Using the linear separability concept, obtain the response for the OR function. (Take

    bipolar inputs and bipolar targets).

    Refer text book page no:33

7.    Illustrate the use of activation functions and their types.

Types of Activation Functions

1. Sigmoid Function

In an ANN, the sigmoid function is a non-linear AF used primarily in feedforward neural networks. It is a differentiable real function, defined for real input values, and containing positive derivatives everywhere with a specific degree of smoothness. The sigmoid function appears in the output layer of the deep learning models and is used for predicting probability-based outputs. The sigmoid function is represented as:

Tanh Function

The activation that consistently outperforms sigmoid function is known as tangent hyperbolic function.

ReLU (Rectified Linear Unit) Activation Function

Currently, the ReLU is the activation function that is employed the most globally. Since practically all convolutional neural networks and deep learning systems employ it.

Softmax Function

Although it is a subclass of the sigmoid function, the softmax function comes in handy when dealing with multiclass classification issues.

8.    Implement the AND function using the McCulloch-Pitts neuron model. (Use binary

data representation).

Refer pageno.30

9.    Demonstrate the Hebb training algorithm.

                (3 x 2= 6 weightage)

Section C

Answer any 1 question. Weight 5 each.

10.  Explain basic models of ANN based on the types of connections.

Single layer feed forward

Multilayer feed forward

Single node with its feedback

Single layer recurrent

Multilayer recurrent

11.  Design a Hebb net to implement AND function. (take bipolar inputs and bipolar targets).

                                               Refer page no.34

                                                                                                             (1 x 5 = 5 weightage)