Page 97 - Touhpad Ai

vehicles to automate tasks and enhance decision-making processes.

Features of Machine Learning
Following are the features of machine learning:
u It is the science of having machines interpret, analyse and process data as a way to fix real-world problems.
u It learns from data and improve over a period of time. These learnings can be used for automation or prediction.
u It is the dominant mode of AI today.
u It can identify patterns, trends, and relationships within data that may not be immediately apparent to humans.
u It uses data analysis, training, and human review to learn without following specific rules or steps.
Let us now understand the difference between machine learning and deep learning:

Factors Deep Learning Machine Learning
Data Requirement Requires large data Can train on less data
Reliability Provides high accuracy Gives less accuracy

Training Time Takes longer to train Takes less time to train
Hardware dependence Requires GPU to train properly Trains on CPU
Hyperparameter Tuning Can be tuned in various different ways Limited tuning capabilities

Computer Vision
Computer Vision is a specialised domain dedicated to enabling computers to interpret and analyse digital images
and videos. By employing sophisticated algorithms, it extracts meaningful patterns and information from visual
data—essentially mimicking the human ability to see and understand the world.

What We See What Computer See

Representing Images with Numbers
Each pixel in a digital image has a numerical value. For black and white images, the value ranges from 0 to 255, where
0 is black and 255 is white. For coloured images, each pixel’s value is based on the RGB colour model, which stands for
Red, Green, and Blue. Each colour channel (Red, Green, Blue) can have a value from 0 to 255, creating over 16 million
possible colours. By mixing different amounts of red, green, and blue, a wide range of colours can be represented in an
image. Here is an example to make it clearer:
u Imagine a grayscale photo of a dog. Each pixel in the image has a value from 0 to 255, with 0 being black and 255
being white.

Introduction and State of Art of AI, Natural Language Processing (NLP), and Potential use of AI 95