Machine Learning course|2: Different types of Machine learning
In the last chapter we talked about understanding machine learning basics. Please follow me on medium for getting updated whenever I publish a chapter daily in my upcoming blogs. In this chapter, we will try to discuss the different types of Machine Learning.
There are basically 3 types of machine learning:
- Supervised Learning
- Unsupervised Learning
- Reinforcement Learning
Supervised Learning
Supervised Learning is a Machine Learning task of learning a function, which maps input to an output based on collected input output pairs. In the previous chapter we discussed about the example of a person cracking a business deal and getting rewarded from the company he works. So lets take the same example.
In the above example, lets assume, TA is 25% of DA. So, this is the function which relates TA and DA. We find an analogy to the equation of straight line. We will see every thing in depth when we will study Linear Regression and Classification models.
Unsupervised Learning
Unsupervised Learning is a Machine Learning task where we try to identify unknown patterns in data. Lets say, We collected weather data for a month and we are trying to perform an unsupervised learning in the data. From the weather data, we see, that whenever the weather is rainy, the temperature decreases and whenever the weather is sunny, the temperature increases. Or lets say, whenever the sky is cloudy, the probability of raining increases. So, here we tried to find patterns which are interconnected to each other. This kind of learning is called Unsupervised learning.
Reinforcement Learning
In case of Reinforcement Learning, an agent tries to learn how to behave in a given environment by performing actions and seeing the results. This kind of learning is basically a trail and hit method of Machine Learning. The chess game would be a great fit for reinforcement learning. But here for understanding lets take an example of “find the path” game. Have you ever entered a mirror house ever? You have to find a way out of the mirror house once you entered the house. So in this situation, you are the agent and the mirror house is the environment. You have to take a step every time and see if you can find a way out. If you hit a mirror, then you take a step back and try to find another way out.
In the next lesson, we will study about the graphical intuition of Machine Learning Algorithms. Please follow me on medium to get notified for the next blog.