Machine Learning Summarized in One Picture

Here is a nice summary of traditional machine learning methods, from Mathworks.

I also decided to add the following picture below, as it illustrates a method that was very popular 30 years ago but that seems to have been forgotten recently: mixture of Gaussian. In the example below, it is used to separate the data set into two clusters. Note that you can use a mixture of any distributions, not just Gaussian, for instance, (data-driven) estimated distributions such as those based on kernel density estimation.

Also, I would put neural networks in the supervised learning category.

Top DSC Resources

Article: Difference between Machine Learning, Data Science, AI, Deep Learnin...
Article: What is Data Science? 24 Fundamental Articles Answering This Question
Article: Hitchhiker's Guide to Data Science, Machine Learning, R, Python
Tutorial: Data Science Cheat Sheet
Tutorial: How to Become a Data Scientist - On Your Own
Categories: Data Science - Machine Learning - AI - IoT - Deep Learning
Tools: Hadoop - DataViZ - Python - R - SQL - Excel
Techniques: Clustering - Regression - SVM - Neural Nets - Ensembles - Decision Trees
Links: Cheat Sheets - Books - Events - Webinars - Tutorials - Training - News - Jobs
Links: Announcements - Salary Surveys - Data Sets - Certification - RSS Feeds - About Us
Newsletter: Sign-up - Past Editions - Members-Only Section - Content Search - For Bloggers
DSC on: Ning - Twitter - LinkedIn - Facebook - GooglePlus

29 members like this

Comment

You need to be a member of Data Science Central to add comments!

Join Data Science Central

Comment by Ilan Chamovitz on April 17, 2018 at 2:29pm: Hi Vincent, good article. Please consider including a reference/credits at the bottom, in figures ;-).

If they are shared there will be a reference to the website.

Comment by TRR on August 22, 2017 at 1:02am: Is Random forest part of Decision Trees in the above diagram?

Comment by M'hamed Bilal ABIDINE on June 13, 2017 at 12:47pm

Hi!

I'm agree with Dragos, the Neural networks is also used for Classification task !

Comment by Tony Pellerin on May 28, 2017 at 3:37am: Hello Vincent

Thank you for this article (and all the others!)
Shall we include reinforcement learning as another ML category?

Comment by Mbaye Babacar GUEYE on April 11, 2017 at 10:46pm: Hi!

I'm agree with Dragos.

Comment by Lance Norskog on February 28, 2017 at 4:59pm: The "Three Cs": Classification, Cooccurrence, Clustering. Isn't regression an implementation of classification?

Where are recommenders?

Comment by Dragos Bandur on February 16, 2017 at 8:02am: Hello Vincent,

I follow with interest your posts for their diversity. This diagram is very interesting and, if I may suggest, should include deep learning as a link between unsupervised and supervised learning.

Also, not all neural networks should go under supervised learning: I would add self-organizing (e.g. Kohonen) networks under unsupervised learning.

Comment by Dragos Bandur on February 16, 2017 at 7:59am: Hello Alind,

Logistic Regression is within the GLM under Regression

Comment by Oscar Wijsman on February 11, 2017 at 5:09am: A decision tree gives a description of the data. The resulting classification tree can be an input for making a decision. A nice article on decision tree classifiers is this one http://mines.humanoriented.com/classes/2010/fall/csci568/portfolio_...