Page 200 - AI Computer 10

Scenario:

All family members are free to travel. X1 = 8
Expenses for vacation affordable. X2 = 5
Weather at the destination is cloudy but pleasant. X3 = 6
Travel and stay arrangements confirmed. X4 = 5

Bias, b = 1.0
Z = X1W1 + X2W2 + X3W3 + X4W4 + b

= (8)(0.8) + (5)( –0.6) + (6)(0.7) + (5)(0.6) + 1.0
= 6.4 – 3 + 4.2 + 3.0 + 1.0 = 11.6
Since, 11.6 > 10, thus, the output is 1. Hence, the family decides to go on the vacation.
F. Long answer type questions.

1. Explain the key differences between Artificial Intelligence, Machine Learning, and Deep Learning.
Ans. Artificial Intelligence (AI) is a broad field that encompasses the development of systems capable of
performing tasks that typically require human intelligence. This includes aspects such as reasoning,
problem-solving, perception, and language understanding. An example of AI in action is an automated
customer support chatbot, which uses predefined rules or intelligent models to engage with users.
Within AI, Machine Learning (ML) represents a subset focused on the idea that systems can learn
from data, identify patterns, and make decisions with minimal human intervention. Machine Learning
operates through various algorithms that can improve their performance as they are exposed to more
data. For instance, recommendation systems such as those used by Netflix and Amazon rely heavily on
ML algorithms to suggest content based on user interactions.

Deep Learning (DL) is a further subset of Machine Learning that utilises multi-layered neural networks
to process large volumes of data. Deep Learning requires vast datasets and substantial computational
power to train models that can automatically identify features from raw data. An example includes self-
driving cars, which utilise deep learning to understand and interpret vast amounts of visual information
from their surroundings.

2. Describe the importance of data in AI modelling. What are data features, and how do they contribute to
the development of machine learning models?
Ans. Data serves as the backbone of AI modelling. Without high-quality, well-structured data, AI models will
fail to deliver accurate predictions or insights. Data can be categorised as raw facts or figures that, when
processed, help in building models capable of making informed decisions.
Data features refer to individual measurable properties or characteristics that are used as inputs in
machine learning models. In essence, features are the columns within a dataset that provide specific
information about each observation. For example, in a dataset defining houses for sale, features might
include square footage, number of bedrooms, location, and age of the property.
The quality and relevance of data features are crucial to the development of robust machine learning
models, thereby directly impacting their effectiveness and reliability.
3. Explain the differences between Supervised and Unsupervised learning. Give examples of applications
for each type.
Ans. Supervised and Unsupervised learning are two principal methodologies employed in machine learning,
each serving unique purposes based on the nature of the dataset.

66
66