Page 102 - Chinmaya_C8_flipbook
P. 102
DOMAINS OF ARTIFICIAL INTELLIGENCE
The three domains of AI explain how it carries out complex tasks and what its capabilities are. Let
us discuss each of these and then interpret them together.
DATA
The starting point of every application is data and it
is the foundation of artificial intelligence. Data is all
around us, be it a google search, a passport scan or
an online shopping history, all of this contains data
that is collected, analysed, and monetised. Data is not
just collected but also properly formatted and aligned
with the project requirements.
Examples of AI applications based on data:
Weather prediction models using AI need data such as temperature, humidity and all underlying
patterns that impact weather.
AI is used in the prediction of upcoming customer orders for the next season. This enables
retailers to plan the inventory and purchases which helps them predict and control the cost.
The software that controls vehicles works with the control radar system, lane control feature,
accident avoidance features, cameras, GPS, etc. All these technologies are AI based and rely
on data to function.
Companies like Google, Facebook and Amazon are ruling the world because they were the first
to build data sets. Amazon already knows what the customers are going to buy and all of this
has been possible because of predictive analytics and tons of customers’ data.
COMPUTER VISION
Computer vision is a subset of AI that helps machines see and extract meaning from pixels in
an image. It is a field of AI that enables computers to see, identify, and process images to derive
meaningful information from those images, videos, and other visual inputs. Computer vision is
important and linked to AI as AI enabled systems must interpret what it sees just like human
vision and act accordingly.
The goal of computer vision is to train machines to see, process, and provide useful results based
on its observations within a very short time. This can only be possible if lots of data is provided
to it which can be analysed over and over until it detects distinctions and ultimately recognises
images. For example, to train a machine to recognise tyres, it needs to study a lot of images of
tyres. and items related to it to learn to differentiate and recognise a tyre without fail.
100 Premium Edition-VIII

