Page 203 - AI Computer 10

H. Assertion and Reason-based questions.

In the following questions, a statement of Assertion (A) is followed by a statement of Reason (R). Study both
the statements and give the answer as:

(a) if both Assertion and Reason are correct and Reason is the correct explanation of Assertion.
(b) if both Assertion and Reason are correct but Reason is not the correct explanation of Assertion.
(c) if Assertion is True but Reason is False.
(d) if Assertion is False but Reason is True.

1. Assertion (A): Unsupervised Learning is a type of learning without any guidance.
Reasoning (R): Unsupervised learning models work on unlabeled datasets, where the data fed into the
machine is random and the person training the model may not have any prior information about it.
2. Assertion (A): Information processing in a neural network relies on weights and biases assigned to nodes.
Reasoning (R): These weights and biases determine how strongly a node is influenced by its inputs and
its overall contribution to the next layer.
3. Assertion (A): Rule-based AI models are more adaptable than learning-based AI models.

Reason (R): Rule-based AI models rely on predefined logic and cannot adjust to new data without manual
intervention.

4. Assertion (A): Convolutional Neural Networks (CNNs) are widely used for image processing.
Reason (R): CNNs use convolutional layers that use simple rules to process input and produce output
based on the rules.
Answers
1. (a) 2. (a) 3. (d) 4. (c)
I. Case-study based questions.

1. Sachin works as the head of the IT department in a leading hospital chain that provides healthcare
solutions for various diseases. The hospital keeps a record of all past scans such as X-rays, MRI, ultrasounds,
etc. Keeping in times with the technological updates, the hospital management wants to develope an
AI system to detect lung diseases from chest X-rays. They asked Sachin to propose a suitable machine
learning model for the same.

Answer the following questions in context of the above information.
a. Which model, out of traditi onal machine learning models or CNNs, would Sachin propose for the AI
system?
b. What are the advantages of using a CNN over traditi onal machine learning models for image-based
disease detecti on?

c. Why might the hospital need a large labelled dataset to train the CNN eff ecti vely?
Ans:
a. Sachin should propose a CNN for the AI system as it is more efficient in image recognition, object
classification, and object localisation in digital images such as X-rays.
b. The advantage of using CNNs is that these can automatically extract spatial features from images,
reducing the need for manual feature engineering.
c. Deep learning models, such as CNNs, require extensive labelled data to learn complex patterns and
generalise well to solve complex imaging-based problems.

69
69