- Machine Learning Basics
Today we are talking about Machine Learning, or the notion that data can be used to teach a computer to recognize types of patterns. Incredible as it may seem computers, like you, can also learn to do amazing things!
Let’s talk about how machine learning works (in a very general sense)! Let’s first put ourselves in the place of the learner.
Patterns Observed by Humans: Film Posters
Imagine that the below posters are for films that you might go to see. The films are about the action-packed duo, Smiles and Smiley and their adventures.
What do you note about the below themes?
If you have studied these posters, then you have certainly noticed that there is a recognizable (and common) theme across all the posters of the set.
What is the common theme?!
To shed some light on this feature, we study a new poster that does not have the common theme. Below, we see a poster of our hero Smiles and Smiley singing along side Taylor Swift.
- What common element of the above posters did you not see?
- What is the common theme?!
One of the common features is that Smiles and Smiley were always featured in front of some beautiful and outdoors scene. In the last poster, Smiles and Smiley were featured singing with Taylor Swift.
Patterns Observed by Machines
Types of Machine Learning
There are three main types of algorithms that teach a computer how to recognize objects.
- Supervised learning: The computer is presented with example inputs and their desired outputs, given by a “teacher”, and the goal is to learn a general rule that maps inputs to outputs. Check out WikiPedia to learn more!
- Unsupervised learning: No labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end (feature learning). Check out TowardsDataScience to learn more!
- Reinforcement learning: A computer program interacts with a dynamic environment in which it must perform a certain goal (such as driving a vehicle or playing a game against an opponent). As it navigates its problem space, the program is provided feedback that’s analogous to rewards, which it tries to maximize.
Let’s program with ML!
Try out one of the below tutorials with Python for learning more about Machine Learning!! Choose one or two tutorials below and then once finished, perhaps you could spend a moment to discuss and you explain what you discovered to your peers?!
Start by reading the first page here, and then choose a topic from below to study in more detail!
Now, choose one or two of the tutorials below!