Assignment on
Module 1: Introduction to Machine Learning
Subject: Artificial Intelligence / Machine Learning
Prepared by: Daksh Prajapati
College: ____________________
Date: 25 January 2026
1. Introduction
Machine Learning is one of the most important and fast growing fields in modern technology. It is a
branch of Artificial Intelligence that focuses on making machines learn from data and improve their
performance automatically without being specially programmed every time.
In earlier days, computers could only work based on fixed instructions given by programmers. But in
today’s world, data is very large and complex, so it is not possible to write rules for every situation.
Machine learning solves this problem by allowing computers to learn patterns from data.
Machine learning is widely used in daily life. For example, Google search suggestions, YouTube
video recommendations, face unlock in mobile phones, spam email detection and online shopping
recommendations all use machine learning.
In this assignment, we will study about machine learning, its history, importance, workflow and
different types of machine learning in detail.
2. What is Machine Learning?
Machine Learning can be defined as a method by which a computer system learns from experience
and improves its performance over time. Instead of writing programs with fixed rules, we provide
data to the system and it learns from that data.
In simple words, machine learning means teaching the computer using examples, just like humans
learn from experience. The more data the system gets, the better it becomes at making decisions.
According to Arthur Samuel, machine learning is the field of study that gives computers the ability to
learn without being explicitly programmed.
Machine learning is mainly used where normal programming fails, such as image recognition,
speech recognition and prediction systems.
3. Machine Learning Workflow
The machine learning workflow means the step-by-step process used to build a machine learning
system.
The first step is Data Collection. In this step, we collect data related to the problem. The quality of
the data is very important for good results.
The second step is Data Preprocessing. In this step, the data is cleaned, missing values are
handled and unnecessary data is removed.
The third step is Model Selection. Here, we choose a suitable algorithm or model based on the type
of problem.
The fourth step is Training. In this step, the model is trained using the available data so that it can
learn patterns.
The fifth step is Evaluation. The trained model is tested using new data to check its accuracy and
performance.
The last step is Deployment. In this step, the model is used in real life applications.
4. History and Evolution of Machine Learning
The history of machine learning started in the 1950s. Scientists like Alan Turing and Arthur Samuel
played an important role in its development.
In 1957, Frank Rosenblatt introduced the Perceptron, which was an early form of neural network.
In the 1970s and 1980s, expert systems and statistical methods became popular.
In the 1990s, algorithms like decision trees, support vector machines and random forests were
developed.
After 2000, due to the availability of big data and powerful computers, deep learning became very
successful.
Today, machine learning is used in almost every field such as healthcare, banking, education and
technology.
5. Importance of Machine Learning in Modern Society
Machine learning plays a very important role in modern society.
It helps in automation and saves human time and effort.
It is used to provide personalized recommendations in shopping websites and entertainment
platforms.
In healthcare, it helps doctors in disease detection and medical image analysis.
In banking and finance, it is used for fraud detection and risk analysis.
In security systems, it helps in face recognition and cyber security.
6. Types of Machine Learning
There are mainly four types of machine learning: Supervised learning, Unsupervised learning,
Semi-supervised learning and Reinforcement learning.
Each type has its own working method and applications.
7. Supervised Learning
Supervised learning is the type of machine learning in which the model is trained using labelled
data.
This means that each input data has a correct output.
There are two main types: Classification and Regression.
Examples of supervised learning include spam detection, disease prediction and price prediction.
Common algorithms used are linear regression, logistic regression, decision trees and neural
networks.
8. Unsupervised Learning
Unsupervised learning is the type of machine learning in which the data has no labels.
The system tries to find patterns and structures by itself.
It is mainly used for clustering, dimensionality reduction and anomaly detection.
Examples include customer grouping and market segmentation.
9. Semi-Supervised Learning
Semi-supervised learning uses both labelled and unlabelled data.
Only a small part of data is labelled, and the rest is unlabelled.
This method reduces cost and improves performance.
It is used in medical diagnosis, image recognition and text analysis.
10. Reinforcement Learning
Reinforcement learning is a type of learning in which an agent learns by trial and error.
The agent performs actions in an environment and receives reward or punishment.
The main goal is to maximize the total reward.
It is used in robotics, games, self-driving cars and smart systems.
11. Conclusion
Machine learning is a very powerful and important technology in today’s world.
It is used in almost every field and makes systems smarter and more efficient.
In the future, machine learning will play an even bigger role in the development of science and
technology.