Origin of Machine Learning
Machine Learning is a sub-set of artificial intelligence where computer algorithms are used to autonomously learn from data and information. In machine learning computers don’t have to be explicitly programmed but can change and improve their algorithms by themselves.
1950: Alan Turing creates the “Turing Test” to determine if a computer has real intelligence. To pass the test, a computer must be able to fool a human into believing it is also human.
1952: Arthur Samuel wrote the first computer learning program. The program was the game of checkers, and the IBM computer improved at the game the more it played, studying which moves made up winning strategies and incorporating those moves into its program.
1957: Frank Rosenblatt designed the first neural network for computers (the perceptron), which simulate the thought processes of the human brain.
1967: The “nearest neighbor” algorithm was written, allowing computers to begin using very basic pattern recognition. This could be used to map a route for traveling salesmen, starting at a random city but ensuring they visit all cities during a short tour.
1979: Students at Stanford University invent the “Stanford Cart” which can navigate obstacles in a room on its own.
1981: Gerald Dejong introduces the concept of Explanation Based Learning (EBL), in which a computer analyses training data and creates a general rule it can follow by discarding unimportant data.
1985: Terry Sejnowski invents NetTalk, which learns to pronounce words the same way a baby does.
1990: Work on machine learning shifts from a knowledge-driven approach to a data-driven approach. Scientists begin creating programs for computers to analyze large amounts of data and draw conclusions — or “learn” — from the results.
1997: IBM’s Deep Blue beats the world champion at chess.
2006: Geoffrey Hinton coins the term “deep learning” to explain new algorithms that let computers “see” and distinguish objects and text in images and videos.
2010: The Microsoft Kinect can track 20 human features at a rate of 30 times per second, allowing people to interact with the computer via movements and gestures.
Introduction
Machine-learning is one of the subfields of artificial intelligence. Machine learning is a method which processes data and the conclusion of fire by finding patterns, suggesting behavior, identifying trends and optimizing performance. Machine Learning approaches have beneficial outcomes when there are more useful data. Machine Learning is the ability of machines to imitate human behavior, in which a computer composed of different algorithms using these algorithms chooses its own choice and provides the user with the outcome or output.
 |
| https://pixabay.com/illustrations/head-circuit-board-machine-learning-4519964/ |
Machine Learning is the ability of machines to learn where a machine is built up using certain algorithms which allow it to make its own decisions and provide theuser with the result. Machine learning is closely linked to mathematical features that reflect theory, techniques, and implementation, and operates on various tasks where algorithms are clearly impracticable to program and design. It is easy-to-use algorithm making that helps the machine to learn and select compulsory decisions. Optical Character Recognition [OCR], Spam Mail Filtering, Computer Vision and Search Engines Optimization are some examples of machine learning applications.
Machine Learning Algorithms
Machine learning means building algorithms that enable learning on a system. Learning is not a compulsory understanding which means obtaining identical patterns and statistical consistency in the input data. Machine learning algorithms attempting to find out, how a human mind completes a process of learning. Machine learning algorithms capable of providing insight into the data by finding similar learning patterns in different environments. Different algorithms for decision making and data classification are developed for different types of machines. For scientists and developers the key challenge is to design and evaluate an algorithm for performance measurement.
 |
| https://www.wordstream.com/ blog/ws/2017/07/28/machine-learning-applications |
In a learning environment a computer adapts various learning experiences from various types of algorithms. Using these algorithms a computer takes the appropriate decision and performs specific tasks, so it is very important for the algorithms to be checked correctly and the algorithm's complexity should be reduced so the computer can make effective decisions with an efficient algorithm.
Decision tree and help vector machine like learning algorithms play the key role for data classification in all applications relating to artificial intelligence. Help vector machine effectively deals with disjunctive data to render the nonlinear partitions between the various groups and decision tree algorithm. These methods of learning have their own characteristic extraction quality which makes them suitable for almost all classification tasks.
Machine Learning algorithms are broadly divided into three categories as follows:
- Supervised Learning
- Un-Supervised Learning
- Reinforcement Learning
 |
| https://www.freepik.com/ search?format=search&query= supervised%20machine%20learning |
