Introduction to Machine Learning for beginners
Machine Learning has been a new hype in the field of computer science since a year along with other trending topics such as Internet of Things, Artificial Intelligence, Big Data…
But what is Machine Learning for beginners?
Machine Learning is developing a computer program that improves automatically with experience.
This is a general definition according to me so that it is easy understood by freshers.
By the field of usage and kind of data we are using as input, we can modify this definition accordingly.
For example, Genetic programming is the field of Machine Learning where you essentially evolve a program to complete a task while Neural networks modify their parameters automatically in response to prepared stimuli and expected response.
Machine Learning can be divided into two following categories based on type of data we are using as input:
Types of Machine Learning for beginners perspective:
- Supervised learning – It is a task of inferring a function from Labeled training data.
- Unsupervised learning – It is the task of inferring from a data set having input data without labeled response.
Supervised Machine Learning:
Supervised learning is where you use an algorithm to learn mapping function from input to the output.
Y = f(x) where, x – input variable Y – output variable
The goal is to approximate mapping function so well that when you have new input data that you can predict the output variable for that data.
Supervised learning problem can be further divided into regression and classification problems.
A classification is when we have discrete valued output. For example, “spam” or “not spam” or “red”, “blue” & “green”.
A regression is when we have continuous valued output. For example, a price of house or height of a person.
Some example of supervised learning algorithms are:
- Linear regression example for regression problems.
- Logistic regression for classification problems.
- Random forest for classification and regression problems.
Unsupervised Machine Learning:
Unsupervised learning is where you only have input data and there is no corresponding output.
The goal of unsupervised learning is to recognize structure in the data in order to learn more about data.
Unsupervised learning problem can be further divided into clustering and association problems.
A clustering problem is where you want to recognize the inherent grouping in the data, such as grouping customers by who tends to eat veg food items in a restaurant.
An association rule learning problem is where you want to discover rules that describe your data, such as people that buy laptop also tend to buy antivirus.
Some example of unsupervised learning algorithms are:
- K-means for clustering problems
- Anomaly detection
This is general information about Machine Learning for beginners. We will cover more insight about this topic in upcoming articles. If you are interested in learning, subscribe to CSEStack weekly FREE newsletter & stay tuned.