Skip to main content

MACHINE LEARNING FOR ALL



MACHINE LEARNING 

Artificial intelligence (AI) has an area called "machine learning" that focuses on creating statistical models and algorithms that let computers learn from experience without having to be explicitly programmed. In other words, it is a technique for teaching computers to learn from patterns and examples rather than from explicit instructions in order to make decisions or predictions.

Through the use of algorithms called machine learning, computers are now able to recognise and understand complex patterns and make predictions or judgements based on that knowledge. The three main categories of these algorithms are reinforcement learning, unsupervised learning, and supervised learning.

In supervised learning, each data point in the dataset has a matching label or target value, and the algorithm is trained on this labelled dataset. The objective is to develop a mapping function that, given new input data, can predict the right output. Algorithms for supervised learning include support vector machines, decision trees, random forests, and linear regression.

Unsupervised learning includes training algorithms on unlabeled data with the intention of identifying patterns, structures, or correlations in the data. Without explicit instruction, the algorithms pick up on the resemblances, discrepancies, or groupings in the data. Unsupervised learning algorithms frequently use clustering and dimensionality reduction methods like principal component analysis (PCA) and k-means clustering.

Reinforcement learning: Reinforcement learning aims to teach agents how to make decisions sequentially in a setting to maximise a cumulative reward. The agent interacts with its surroundings, gets feedback in the form of benefits or drawbacks, and learns by doing. It seeks to identify the best course of action that maximises long-term gain. Popular reinforcement learning algorithms include Q-learning and deep Q-networks (DQNs).

Machine learning is used in a wide range of fields and has several uses, including:


Recognition of voice and images: Machine learning algorithms can be taught to understand spoken language, recognise objects or faces in pictures, and recognise and interpret images.

Application areas like sentiment analysis, chatbots, and language translation are made possible by natural language processing (NLP), which applies machine learning techniques to understand and analyse human language.

Systems for making recommendations: Recommendation engines, which make personalised content, products, or services recommendations based on user preferences and behaviour, are powered by machine learning algorithms.

Fraud detection: Machine learning models are able to find patterns and abnormalities in huge datasets, which can be used to spot fraudulent behaviour in various industries, including finance, credit card transactions, and cybersecurity.

Medical imaging analysis, medication discovery, disease diagnosis, and personalised treatment planning are all made possible by machine learning.

Autonomous vehicles: Machine learning is essential to the development of self-driving cars because it gives them the ability to see, comprehend, and make decisions in real time about their surroundings.

These are but a few examples, and machine learning has numerous uses in numerous sectors and specialties. It keeps developing quickly as new frameworks, approaches, and algorithms are created to address issues that are getting more complicated.

It has been more than 20 years since a computer program defeated the reigning world champion in a game which is considered to need a lot of intelligence to play. The computer program was IBM’s Deep Blue and it defeated world chess champion, Gary Kasparov. That was the time, probably, when the most number of people gave serious attention to a fastevolving field in computer science or more specifically artificial intelligence – i.e. machine learning (ML).

As of today, machine learning is a mature technology area finding its application in almost every sphere of life. It predicts the future market to help amateur traders compete with seasoned stock traders. Google has become one of the front-runners focusing a lot of its research on machine learning and artificial intelligence – Google self-driving car and Google Brain being two most ambitious projects of Google in its journey of innovation in the field of machine learning.

The foundation of machine learning started in the 18th and 19th centuries. The first related work dates back to 1763. In that year, Thomas Bayes’s work ‘An Essay towards solving a Problem in the Doctrine of Chances’ was published two years after his death. This is the work underlying Bayes Theorem, a fundamental work on which a number of algorithms of machine learning is based upon. In 1812, the Bayes theorem was actually formalized by the French mathematician Pierre-Simon Laplace. The method of least squares, which is the foundational concept to solve regression problems, was formalized in 1805. In 1913, Andrey Markov came up with the concept of Markov chains.

The rapid development in the area of machine learning has triggered a question in everyone’s mind – can machines learn better than human? To find its answer, the first step would be to understand what learning is from a human perspective.

WHAT IS HUMAN LEARNING
In cognitive science, learning is typically referred to as the process of gaining information through observation. And why do we need to learn? In our daily life, we need to carry out multiple activities. It may be a task as simple as walking down the street or doing the homework. Or it may be some complex task like deciding the angle in which a rocket should be launched so that it can have a particular trajectory. To do a task in a proper way, we need to have prior information on one or more things related to the task. Also, as we keep learning more or in other words acquiring more information, the efficiency in doing the tasks keep improving. For example, with more knowledge, the ability to do homework with less number of mistakes increases. In the same way, information from past rocket launches helps in taking the right precautions and makes more successful rocket launch. Thus, with more learning, tasks can be performed more efficiently.

TYPES OF HUMAN LEARNING
Thinking intuitively, human learning happens in one of the three ways –

(1) either somebody who is an expert in the subject directly teaches us,
(2) we build our own notion indirectly based on what we have learnt from the expert in b
the past, or
(3) we do it ourselves,

may be after multiple attempts, some being unsuccessful. The first type of learning, we may call, falls under the category of learning directly under expert guidance, the second type falls under learning guided by knowledge gained from experts and the third type is learning by self or self-learning. Let’s look at each of these types deeply using real-life examples and try to understand what they mean.

CLICK THE FOLLOWING URL YOU GET FULL INFORMATION 

MACHINE LEARNING ALL UNITS - WITH LAB EXAMPLES

Comments

Popular posts from this blog

COMMUNITY SERVICE PROJECT

  NATIONAL DEGREE COLLEGE::NANDYAL Introduction  Community Service Project is an experiential learning strategy that integrates meaningful community service with instruction, participation, learning and community development  Community Service Project involves students in community development and service activities and applies the experience to personal and academic development.  Community Service Project is meant to link the community with the college for mutual benefit. The community will be benefited with the focused contribution of the college students for the village/ local development. The college finds an opportunity to develop social sensibility and responsibility among students and also emerge as a socially responsible institution CSP HAND BOOK DOWNLOAD IT EVERYONE Guidelines from APSHE SAMPLE CSP PROJECTS done by the Students of National Degree College CHILD LABOUR AGRICULTURE PRODUCTS AND MARKETING USAGE OF MOBILE ONLINE PURCHAGE PLANTATION DIABETES WATER POLUTION USE O

JAVA NOTES FOR ALL

  JAVA NOTES FOR ALL Consider the following important ideas and considerations when dealing with Java: Java is an object-oriented programming language, which means it places a strong emphasis on the idea of objects that encapsulate information and behaviour. Encapsulation, inheritance, and polymorphism are important OOP tenets. Syntax and Organisation: Classes are used as building blocks for objects while writing Java programming. Each class consists of variables (fields) for data storage and functions (methods) for behaviour definition. A main() function is often where Java programmes begin to run. Primitive and reference types are the two basic categories of data types in Java. Integer, double, and boolean types are examples of primitive types, whereas objects, arrays, and strings are examples of reference types. Control Flow: Java has statements for controlling the flow of execution based on conditions, including if-else, switch-case, for loops, while loops, and do-while loops. Exce

DATA MINING AND DATA WAREHOUSE

  DATA MINING AND DATA WAREHOUSE UNIT-1: Data Mining: Data mining is defined as the procedure of extracting information from large sets of data i.e. there is a large of data available in the industry. This data is of no use until it is converted into useful information. It is necessary to analyze this large amount of data and extract useful information. Sometimes referred as  Knowledge Extraction  Knowledge Mining  Pattern Anaysis  Data Archeology Areas of Data mining:  Financial Data Analysis: The financial data in banking and financial industry is generally reliable and of high quality which facilities systematic data analysis and data mining. Some of the typical cases are as follows:  Loan payment prediction and customer credit policy analysis.  Classification and clustering of customers for targeted marketing  Detection of money laundering and other financial crimes  Retail Industry: Data mining in retail industry helps in identifying customer buying items and trends that