Machine Learning Introduction

Machine Learning is a part of Data Science. In machine learning we mainly study about data, nature of data, data distribution, data preparation and with help of data we choose best model which can give maximum accuracy. The main challenge in machine learning is to fit data in most suitable model which give maximum accuracy.So there are three main tasks(Training the model,Testing the model and Result Predication) in machine learning splitting data into training data set and testing data set.

A Quick History of Machine Learning

When the idea of building computer in the very first came in the mind of  Charles Babbage was build a machine which can work with human, work for human and has capability to learn.This originated the concept of a digital programmable computer. In the 1940s, the first computer invented which as intensive numerical computation capabilities ENIAC (Electronic Numerical Integrator and Computer), manually operated computer system. so, ENIAC was called a numerical computing machine!. so we may say than the idea was to build a machine able  think and learn like human was from the beginning.

Arthur Samuel, coined the term "Machine Learning" in 1959 who was an American pioneer the field of computer gaming and artificial intelligence. During 1960s, the Nilsson's book on Learning Machines which deal mostly with machine learning for pattern classification. The interest of machine learning related to pattern recognition continued during 1970s. As a scientific endeavor, machine learning grew out of the quest for artificial intelligence. 

Machine learning became very famous in the 1990s. Computer science and statistics gave birth to probabilistic approaches in AI. This shifted the field further toward data-driven approaches. Having large-scale data available, scientists started to build intelligent systems that were able to analyze and learn from large amounts of data.

What is machine learning

Machine Learning (ML) is a subset of artificial intelligence (AI). In machine learning we  study the algorithms and statistical models that which help to build mathematical model  to perform a specific task without using explicit instructions. Machine learning algorithms find the patterns and inference to take decision  based on sample data, known as "training data". After training the model based on data model make predictions or decisions without being explicitly programmed to perform the task. Machine learning algorithms are used in a wide variety of applications, such as email filtering and computer vision,

Classification of Machine Learning

Machine learning tasks are classified into several broad categories:

  • Supervised learning: In this type of learning the machine algorithm builds a  model from a set of data that contains both the inputs and the desired outputs. It's just like teacher. A teacher teaches a subject from a book and student learn the concept of the subject and answers the question.  Each question has correct answer.

       Similarly in machine learning there are set of data with input and output, called as training         data based on training data machine learn from that and give the result or output of any               other data set or for question:


        Example :

        Here is exam data for quiz.

        Question                  ||          Answer

        ==============        =================

        Question 1                       A

        Question 2                       B

        Question 3                       A

        Question 4                       D

  • This above data is called training data.

  • Question ,Answer are attribute, column or field name

       If you want to test the model then suppose we ask the what is answer of Question 3(Input),          then answer should be A(Output).

  • Semi-supervised learning: Incomplete training data, where a portion of the sample input doesn't have labels.

  • Unsupervised learning: In this type of learning the machine algorithm builds a  model from a set of data that contains the inputs but not the desired outputs.

  • Reinforcement learning: Algorithms are given feedback in the form of positive or negative reinforcement in a dynamic environment, and are used in autonomous vehicles or in learning to play a game against a human opponent.