What is Machine Learning?
Before we speak about Machine Learning I want to clarify the difference between Machine learning(ML) and Artificial Intelligence (AI) as they are often used interchangeably.
this image explains it well:
you can see that both ML and Deep learning are subsets of Artificial Intelligence. A difference between both is that with ML there is more of a human presence in its development, but with AI the program, it will adapt and learns and develops itself.
ML is defined as the study of computer algorithms that improve through experience. this means that with more data the algorithm can be improved and developed, i.e will continue to learn
Machine Learning is split between 3 different categories.
- Supervised Learning
- Unsupervised Learning
- Reinforcement learning
Supervised Learning
perhaps the most common type of ML available.
Supervised learning is the machine learning task of learning a function that maps an input to an output based on example input-output pairs.
what this means is that we have data witch has the desired solution included in them when we feed the algorithm the data, The algorithms learns from that and is able to now make predictions on new data where we don't have the solution.
A great example of this is when we are trying to create an algorithm to detect spam mail. we feed it data that has the correct answers(Labels) and the algorithms learn and now when new data is presented it can detect based on what it learnt from the previous data weather this mail is spam or not
Unsupervised Learning
Unsupervised learning is a type of machine learning that looks for previously undetected patterns in a data set with no pre-existing labels and with a minimum of human supervision
what this means is that when the training data is unlabeled, you are pretty much trying to make the system learn without any help or aid, it will detect and notice trends/groups in the data and be able to make the connection between each without your help.
A good example I read online was:
NASA discovers new heavenly bodies and finds them different from previously known astronomical objects — stars, planets, asteroids, black holes etc. (i.e. it has no knowledge about these new bodies) and classifies them the way it would like to (distance from Milky way, intensity, gravitational force, red/blue shift or whatever)
Reinforced Learning
It is an area of ML concerned with how software agents ought to take actions in an environment in order to maximize the notion of cumulative reward.
this learning system(called an agent in this context) will observe the environment, it will choose and perform actions and get rewards or penalties depending on the action they performed. it will learn over time by making choices based on what path/strategy is best to maximize rewards.
All 3 types of ML have its applications in different situations and part of a Data scientists job is to be able to recognize and see which type to use and which ML Algoritihim is the best fit for the data