{"id":6201,"date":"2019-08-12T09:00:55","date_gmt":"2019-08-12T13:00:55","guid":{"rendered":"https:\/\/blog.brainstation.io\/?p=6201"},"modified":"2020-12-13T22:55:37","modified_gmt":"2020-12-14T03:55:37","slug":"what-machine-learning-is-and-what-it-can-do","status":"publish","type":"post","link":"https:\/\/brainstation.io\/blog\/what-machine-learning-is-and-what-it-can-do","title":{"rendered":"What is Machine Learning and What does it do?"},"content":{"rendered":"

If you work in tech (or are even thinking about it), you\u2019ve probably come across the term \u201cmachine learning.\u201d Google Trends shows that the popularity of this as a search term <\/span>has grown by about 200 percent in the last three years, which indicates a growing interest in machine learning<\/span> \u2013 but what exactly is it? <\/span><\/p>\n

We’ve written about the more specific In this post, we’ll take a closer look at what is meant by machine learning<\/a>, and explain why it seems to have such importance to modern businesses.<\/span><\/p>\n

What Is Machine Learning?<\/span><\/h2>\n

There is a famous definition by the Computer Scientist Tom M. Mitchell that has often been used, and which we will adopt here. We say that a computer program is <\/span>learning <\/span><\/i>how to perform a task if it gets better at performing the task as it accumulates <\/span>experience<\/span><\/i>. Computer programs that learn this way are said to fall under the umbrella of machine learning.<\/span><\/p>\n

It might help to understand this definition by considering programs that do <\/span>not<\/span><\/i> satisfy the definition. An important problem in some areas of math and computer science is the problem of finding the prime factors of a number. If you input the number 1081 into a program that solves this problem, it would output the numbers 23 and 47 because of 1081 = 23 * 47. It\u2019s not too hard to figure out how to write a simple program that solves this problem \u2013 an obvious one simply tries dividing 1081 by all the numbers smaller than 1081. This program accomplishes the task, but it does not <\/span>learn<\/span><\/i>: it does not get better at factoring numbers with experience. You can run the program on a million inputs and it will never factor the number 1081 any faster or better than it did the first time you ran it.<\/span><\/p>\n

Now, let\u2019s think about a different kind of task: recognizing handwriting. Suppose we wish to write a program that takes as its input an image of a handwritten digit and gives an output digit from 0 to 9. Coming up with a simple solution to this problem is not as straightforward as the integer factoring problem above, but we might be able to come up with some ideas. You might write a program that says something like:<\/p>\n