Machine learning is a subfield of computer science that is concerned with building algorithms which, to be useful, rely on a collection of examples of some phenomenon. In this article, I will take you through how machines learn with machine learning.
Machine learning can be defined as the process of solving a practical problem by putting together a set of data and algorithmically building a statistical model based on that set of data. This statistical model is supposed to be used in one way or another to solve the practical problem.
Datasets can come from nature, be handcrafted by humans, or generated by some other algorithm.
How do Machines Learn with Machine Learning?
So how do machines learn with machine learning? Let me start by telling the truth that machines don’t learn. What machine learning does is find a mathematical formula that, when applied to a set of inputs called a training dataset, produces the desired results.
This mathematical formula also generates the correct outputs for most other separate inputs of the training data as long as those inputs come from the same statistical distribution or a distribution similar to that from which the training data was taken.
Why isn’t this considered as learning? Because if you warp the inlets slightly, the outlet is very likely to go bad. This is not how learning works in animals. If you learned to play a video game by looking directly at the screen, you would still be a good gamer if someone turned the screen slightly.
A machine learning algorithm, if it has been trained by looking directly at the screen unless it has also been trained to recognize the rotation, will not be able to play the game on a rotated screen.
Just like artificial intelligence is not intelligence, machine learning is also not learning. However, machine learning is a universally recognized term that generally refers to the science of training machines capable of doing various useful things without being explicitly programmed to do so.
Thus, the word learning in the term machine learning is used by analogy with learning in animals rather than literally. I hope you liked this article on how machines learning with Machine Learning. Feel free to ask your valuable questions in the comments section below.