Basics of Machine Learning
Machine learning involves training machines to learn from past data,
understand and reason. It is more than just learning as it involves
prediction and classification of new data. In this article, we will explore the
basics of machine learning.
Example:
Let's consider an example of Paul who likes songs with fast tempo and
soaring intensity while he dislikes songs with relaxed tempo and light
intensity. If we plot the songs on a graph with tempo on the x-axis and
intensity on the y-axis, we can easily classify the unknown song based on
Paul's past choices. However, if the choice becomes complicated, as in the
case of a song with medium tempo and intensity, machine learning comes
in to learn from past data, build prediction models and predict new data
points.
Supervised Learning:
Suppose your friend gives you a dataset of one million coins of three
different currencies, and each coin has different weights. When you feed
this data to the machine learning model, it learns which feature is
associated with which label. Hence, supervised learning uses labeled data
to train the model.
Unsupervised Learning:
Suppose you have a cricket dataset of various players with their respective
scores and wickets taken. When you feed this dataset to the machine, it
identifies the pattern of player performance and clusters them as batsmen
and bowlers. Here, there were no labels of batsmen and bowlers, hence
the learning with unlabeled data is unsupervised learning.
Reinforcement Learning:
Reinforcement learning works on the principle of feedback. Suppose you
provide the system with an image of a dog and ask it to identify it. The
system identifies it as a cat. You give a negative feedback to the machine,
and it learns from the feedback and classifies correctly in the future.
Machine learning involves training machines to learn from past data,
understand and reason. It is more than just learning as it involves
prediction and classification of new data. In this article, we will explore the
basics of machine learning.
Example:
Let's consider an example of Paul who likes songs with fast tempo and
soaring intensity while he dislikes songs with relaxed tempo and light
intensity. If we plot the songs on a graph with tempo on the x-axis and
intensity on the y-axis, we can easily classify the unknown song based on
Paul's past choices. However, if the choice becomes complicated, as in the
case of a song with medium tempo and intensity, machine learning comes
in to learn from past data, build prediction models and predict new data
points.
Supervised Learning:
Suppose your friend gives you a dataset of one million coins of three
different currencies, and each coin has different weights. When you feed
this data to the machine learning model, it learns which feature is
associated with which label. Hence, supervised learning uses labeled data
to train the model.
Unsupervised Learning:
Suppose you have a cricket dataset of various players with their respective
scores and wickets taken. When you feed this dataset to the machine, it
identifies the pattern of player performance and clusters them as batsmen
and bowlers. Here, there were no labels of batsmen and bowlers, hence
the learning with unlabeled data is unsupervised learning.
Reinforcement Learning:
Reinforcement learning works on the principle of feedback. Suppose you
provide the system with an image of a dog and ask it to identify it. The
system identifies it as a cat. You give a negative feedback to the machine,
and it learns from the feedback and classifies correctly in the future.
