8 simple machine learning definitions you’ll really love
Gentle Reader, I have some homework for you. Please enter “Machine Learning definition” into your favorite search engine. You will get hundreds of hits. You could spend hours sifting through the search results trying to make sense out of the resultant verbiage, but I’ll save you some time.
As you saw, if you did your homework, most are like the Wikipedia definition.
Machine learning is a field of computer science that gives computers the ability to learn without being explicitly programmed.
They allude to the fact that the computer learns without programming. But how does the computer learn?
This is where most definitions fall short.
Without further ado… OK, a light sprinkling of ado… here are the 8 best definitions, of Machine Learning in the whole wide world web! For your viewing pleasure, the authors and links to the originating articles have been provided. The articles will help you better understand what Machine Learning is all about. And I won’t lie to you, number 8 was concocted by yours truly.
Drum roll please!
Machine learning is the idea that there are generic algorithms that can tell you something interesting about a set of data without you having to write any custom code specific to the problem. Instead of writing code, you feed data to the generic algorithm and it builds its own logic based on the data.
Machine learning is a thing-labeler, essentially. Machine learning is a new programming paradigm, a new way of communicating your wishes to a computer. Explain with examples, not instructions.
Cassie Kozyrkov, The simplest explanation of machine learning you’ll ever read.
Traditionally programmers automate tasks by writing programs. In machine learning, a computer finds a program that fits to data.
Anntti Ajanka, Differences between machine learning and software engineering
Machine learning is all about automating automation. Instead of coming up with the rules to automate a task such as e-mail spam filtering ourselves, we feed data to a machine learning algorithm, which figures out these rules all by itself.
Sebastian Raschka , How to Explain Machine Learning to a Software Engineer
Machine learning systems are made up of three major parts, which are: Model (the system that makes predictions or identifications), Parameters (the signals or factors used by the model to form its decisions), Learner (the system that adjusts the parameters — and in turn the model — by looking at differences in predictions versus actual outcome) .
Danny Sullivan, How Machine Learning Works, As Explained By Google
Machine Learning is making your algorithms smart, so that you don’t need to be.
Pararth Shah, How do you explain Machine Learning to non-Computer Science people
Machine learning occurs when the computer is programmed with a general-purpose equation or model (e.g. calculating the best fit line through a set of points) suited to the shape (e.g. rising trend line) of a large data set. The data set is defined by known answers (e.g. stock price) and the factors that contribute to the answers (e.g. last price, news releases, dividends, accounting errors, moon phase, etc.). A subset of the data is used to parameterize the equation. The remaining data is used for parameter adjustment; repeatedly, the parameters are re calibrated, and the equation is reapplied to the factors until the calculated answer closely matches the expected answer. The end result is an accurate equation that can be used to predict or classify new data.
Derek Moore, 8 good machine language definitions you will absolutely love (don’t click it!)
To conclude, Dear Reader, I have another homework assignment for you.
Read the articles!
A definition is hard to understand on its own; context and examples are required.
