“Machine learning” sounds mysterious for most people. Indeed, only a small fraction of professionals really know what it stands for. And there is a serious reason for it – this field is rather technical and difficult to explain to a layman. However, we would like to bridge this gap and explain a bit about what machine learning (ML) is and how it can be used in our everyday life or business.
So what is this mysterious ML?
Machine learning can refer to:
- the branch of artificial intelligence;
- the methods used in this field (there are a variety of different approaches).
Overall, if talking about the latter, Tom Mitchell, author of the well-known book “Machine learning”, defines ML as “improving performance in some task with experience”. However, this definition is quite a broad one, so we can quote another more specific description stating that ML deals with systems that can learn from data.
ML works with data and processes it to discover patterns that can be later used to analyse new data. ML usually relies on specific representation of data, a set of “features” that are understandable for a computer. For example, if we are talking about text it should be represented through the words it contains or some other characteristics such as length of the text, number of emotional words etc. This presentation depends on the task you are dealing with and is typically referred to as “feature extraction”.
Types of ML
All ML tasks can be classified in several categories, the main ones are:
- supervised ML;
- unsupervised ML;
- reinforcement learning.
Now let us explain in simple words the kind of problems that are dealt with by each category. Supervised ML relies on data where the true label/class was indicated. This is easier to explain using an example. Let us imagine that we want to teach a computer to distinguish pictures of cats and dogs. We can ask some of our friends to send us pictures of cats and dogs adding a tag ‘cat’ or ‘dog’. Labelling is usually done by human annotators to ensure a high quality of data. So now we know the true labels of the pictures and can use this data to “supervise” our algorithm in learning the right way to classify images. Once our algorithm learns how to classify images we can use it on new data and predict labels (‘cat’ or ‘dog’ in our case) on previously unseen images.
As the reader can guess from the name, unsupervised ML means that we deprive a learning algorithm of the labels we used in supervised learning. We just provide ML with a large amount of data and characteristic of each observation (single piece of data). As an example, imagine your friends were not very helpful and forgot to label the images of cats and dogs that they have sent. However, you still want to split this data into 2 categories. You can employ unsupervised ML (in this case a technique called clustering) to separate your images in two groups based on some inherent features(characteristics) of the pictures.
A graph below presents a simplified workflow of a typical ML task (it is a general graph that shows the processing both in terms of supervised and unsupervised ML).
Typical Machine Learning workflow
Another well-known class of ML problems is called reinforcement learning. This class of ML problems can be easily illustrated by an example of learning to play chess. As input to this problem ML receives information about whether a game played was won or lost. So ML does not have every move in the game labelled as successful or not, but only has the result of the whole game. Therefore ML algorithm can play a lot of games and each time gives bigger “weights” to those moves that resulted in a winning combination.
What do we need to use ML?
Given the fact that ML relies on data, the most important requirement of using ML is having the data you can use to train a ML model. The amount of data needed depends on what you are looking for and how complex your problem is. However, collecting more data is always a good idea. One should also keep in mind that this data (that you want to train your ML on) should be similar to the one you want to make predictions on later. For example, looking at reviews of books and learning to predict opinions of people (positive or negative) about some books, may yield not really great results when applied to reviews of mobile phones or laptops.
Another requirement involves your ability to formulate the question you want to pose to an ML expert, you need to know what you want to get as a result. For example, you can ask to have a look at the purchases in your online shop over the last few years and predict sales for the next year. However, it would be unreasonable to ask for such an estimate if you just opened a shop and have no data available. ML is certainly powerful but it is not magic!
In this article we tried to bridge the gap between the world of technology and statistics, and laypeople who might be interested in finding out a bit more about the mysterious ML.
