Skip to main content
Not sure where to start? Take a short quiz to get personalized recommendations.
Different approaches to Machine Learning
Introduction to Machine Learning
How you can use Machine Learning
How does a machine learn?
Bias in Machine Learning
check_box_outline_blank Machine Learning: Take the Quiz
Course
0% complete
5 minutes to complete

Different approaches to Machine Learning

3.2_hXnd2Gt.jpg

Learn to recognise what defines different machine learning solutions.

3.2_hXnd2Gt.jpg
Start

There are various ways to learn

3.1.jpg

There are different ways for a machine to learn. Different approaches to ML are commonly distinguished by the kinds of problems they try to solve, as well as the type and amount of feedback provided by the programmer.


Broadly, we can divide machine learning into three subareas:


  • Supervised learning
  • Unsupervised learning
  • Reinforcement learning


Although this might look like a neat categorisation, it's not always easy to place a particular method. Let's see what differentiates these three categories.

3.1.jpg

Supervised Learning

3.2_8fdua5N.jpg

Let's say you want to teach a machine to recognise dogs from cats. You give it as input photographs labelled as "cat" or "dog". Studying the examples, the algorithm will learn to recognise what distinguishes a cat from a dog and to assign the correct label to each new image you ask it to analyse.


In supervised learning, the machine needs labelled examples to learn. Those examples are used to train an algorithm to automatically assign the correct label.

In the journalistic context, supervised learning can, for example, train an algorithm to spot documents that might be interesting for an investigation. On a number of occasions this has already proven useful to investigative journalists having to deal with large volumes of documents.

3.2_8fdua5N.jpg

Unsupervised Learning

3.3.jpg

With unsupervised learning, the examples provided to the machine are not labelled. The algorithm is tasked with learning by itself to recognise patterns in the data, for example with the goal of clustering together records that share similar characteristics.

In other words, the algorithm is trained to discover some structure in the unlabelled data that you ask it to analyse. This might be used by a business to better understand its customers, for example by grouping them into categories that show similar shopping behaviours.


In journalism, these kinds of techniques have been deployed by investigative journalists to uncover tax evasion and to help campaign finance reporters link multiple donation records to the same donor.

3.3.jpg

Reinforcement Learning

3.4.jpg

The third type is reinforcement learning. Similarly to unsupervised learning, it doesn't need labelled data. It is instead based on the idea of learning what actions to take through trial and error, or in other words: by making mistakes. Initially the algorithm acts randomly, exploring the environment, but it learns with time by being rewarded when it makes the right choices.

Reinforcement learning is commonly used to teach machines to play games, with the most famous example being AlphaGo, the computer program developed by DeepMind that in 2016 managed to beat world’s top player Lee Sedol at the Chinese board game Go.

Journalistic applications are still rare, but reinforcement learning is used, for example, for headline testing

3.4.jpg

And what about Deep Learning?

3.5.jpg

Deep learning is another type of learning that has made a name for itself in recent years thanks to the increased computing powers we already discussed. It's in itself a subfield of machine learning, but differently from the approaches we just studied, deep learning is defined by the complexity and depth (hence the name) of the mathematical model involved.

The depth of the model refers to the use of multiple layers of analysis that allow the algorithm to learn progressively more complex structures. Deep learning is based on artificial neural networks, whose architecture is inspired by human biological systems, for example by how visual information is processed by our brain through our eyes.

3.5.jpg

Different learning models… so what?

3.6.jpg

Supervised, unsupervised, reinforcement, neural networks... your head must be spinning.

This lesson was not designed to put you off. It's important to understand the complexity of the field of machine learning and meet its subfields, but unless you want to dive deeper (pun intended) into the data science rabbit hole, what you should retain from this lesson is fairly simple: different problems require different solutions and different ML approaches to be tackled successfully.


In the next lesson, we will look at what situations in your work might welcome a machine learning solution. After that, we will explore the process that allows a machine to learn and introduce the concept of bias, with a few tips on how to deal with it.

3.6.jpg
Congratulations! You've just finished Different approaches to Machine Learning in progress
Recommended for you
  • nci

    Build your audience with News Consumer Insights

    lesson 5 minutes Beginner
    Get data-driven recommendations for your site
  • GO801_GNI_StayInTheKnow_TitleCard.jpg

    Google Alerts: Stay in the know.

    lesson 5 minutes Beginner
    Follow the breaking stories that are important to you.
  • image23_3AtCaUp.jpg

    Google Podcasts Manager

    lesson 5 minutes Beginner
    Better understand your audiences and reach them across Google products.