Page 162 - Ai Book - 10

machine, we tell the machine that Outlook = Rainy; Temperature = Cool; Humidity = High and Wind = Strong. On
the basis of this testing dataset, now the machine will be able to tell if the player has been playing or not.
A drawback/feature for this approach is that the learning is static. Thus, we can say that rule-based systems, a
simplest form of AI based on rigid intelligence.

Learning Based Approach

Learning based approach or Adaptive Intelligence Approach refers to the model where relationship or patterns
in the data are not defined by the developer. A learning based approach system does not rely on static data
as random data is fed into the machine and it generates output on the basis of its own identifying patterns or
trends.

You should always remember that rule-based systems are static whereas learning based systems are dynamic
due to the adaptability of new user inputs and information. Frequent training is required in learning based
systems which is one of the major drawbacks of these systems.

For example, suppose you have a dataset of 100 images of butterflies. Now you do not have any clue as to
what trend is being followed as you don’t know their category colour or any other feature. Thus you would put
this into a learning approach based AI machine and the machines would come up with various patterns it has
observed in the features of these 1000 images. It might cluster the data on the basis of colour, size, fun, style,
etc. as shown.

Learning Based AI Mod
Learning Based AI Modelel
Training Dataset Using

Unlabelled data
Learning Approach AI Model

Output

Unlabelled Dataset

Clustering output based on pattern observed by the machine

The learning based approach can further be divided into three parts:

u Supervised Learning: As you know, dataset plays an important role in artificial intelligent models. A model
is said to be supervised if the labeled dataset is fed into the machines. A label is basically used to classify
things. Let us understand the concept of labeling with the help of a simple example. In your class, you have
seen that teachers use a grading system for the marks secured in examinations. These grades are labels that
categorize the students according to their marks.

The Supervised Learning is further categorized as:
z Classification: The term ‘Classification’ refers to the process of finding a model or function which helps
in separating the data into discrete values. In classification, data is categorized under different labels
36
36