Page 195 - AI Computer 10

● Digital recognition typically refers to the use of neural networks to recognise various forms of data such as
images, audio, and text.
● Image recognition involves identifying and classifying objects within images. For example, face recognition
is the task of comparing an input face to a database of multiple face identities.
● Machine Learning is a subfield of AI, whereas Deep Learning is the subfield of Machine Learning.

● Data are the raw facts or figures that are collected and stored in various forms.
● Data Labeling is the process of adding meaningful tags or labels to various elements within a dataset, so that
machine learning models can learn from it.
● A Training dataset is a subset of data used to train a machine learning model.
● A Testing dataset is a subset of data used to evaluate the performance and generalisation ability of a trained
machine learning model.
● AI Modelling refers to the process of creating algorithms and models that allow machines to mimic human
cognition and perform tasks involving understanding, reasoning, and learning from data.
● AI Modelling techniques can be broadly classified into two approaches: Machine Learning and Deep Learning
● Learning based approach, or Adaptive Intelligence Approach, refers to the model where relationship or
patterns in the data are not defined by the developer.
● Supervised Learning and Unsupervised Learning are two primary approaches in machine learning, each
serving different purposes and applied in various scenarios.
● Regression in machine learning is a fundamental technique for predicting continuous outcomes based on
input features.

● Deep Learning enables software to autonomously learn how to perform tasks using large volumes of data.
● Artificial Neural Networks (ANN) and Convolutional Neural Networks (CNN) are the two main types of deep
learning models.
● Neural networks are widely used in pattern recognition, facial recognition, customer support chatbot,
vegetable price prediction, etc.

S Solvedolved QQuestionsuestions

A. Tick () the correct answer.

1. Which term refers to the ability of AI systems to learn automatically from past experiences?
a. Machine Learning b. Deep Learning

c. Arti fi cial Intelligence d. Natural Language Processing
2. In the context of AI, what does “Supervised Learning” involve?

a. Training on labelled datasets b. Training on unlabelled datasets
c. Making sequenti al decisions d. Clustering data
3. What is the primary difference between a rule-based approach and a learning-based approach
in AI modelling?

a. Rule-based systems are dynamic, while learning-based systems are stati c.

b. Rule-based systems rely on predefi ned rules, while learning-based systems adapt to new data.

61
61