Introduction to Machine Learning

Machine learning is one of the techniques that surround us everywhere and we may not even realize it. For example, Machine learning technique is used by Google Gmail to check whether a mail is spam or not, it is also used in Google’s/ Tesla’s self-driving cars, almost in all online shopping apps like Amazon, Myntra, Nykaa, etc to tell your favorites based on your purchase. At Netflix, ML has been constantly used to improvise the recommendations and personalization problems, and there are many more countless examples.

Now, let’s state what Machine Learning actually is!

What is Machine Learning?

Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Machine learning focuses on the development of computer programs that can access data and use it to learn for themselves.

Types of Machine Learning

Machine Learning can be classified into four types:

1. Supervised Learning
2. Semi-Supervised Learning
3. Unsupervised Learning
4. Reinforcement Learning

Supervised Learning

Supervised learning is the most practical and widely adopted form of machine learning. It is where you have input variables (X) and an output variable (Y) and you use an algorithm to learn the mapping function from the input to the output.

Y = f(X)

The goal is to approximate the mapping function so well that when you have new input data (x) that you can predict the output variables (Y) for that data.

For example, we want an algorithm to predict house prices. To accomplish this, we would pass a set of training data with each row of data containing the features of the house like its size, number of bedrooms, the year the house was built, and the value we want to predict, namely the price. We pass many rows of this training data to the algorithm. The algorithm analyzes the features and the resultant price. It determines the relationship between the features and the price and creates a model that is trained to predict the price of the house based on the features present. Then, when a trained model is presented with the data for a new house, it executes its logic and accurately predicts the price for the new house.

Source of the image- towardsdatascience

Further classification of Supervised Learning:

Classification algorithms are used to predict/Classify the discrete values such as Male or Female, True or False, Spam or Not Spam, etc.

Regression algorithms are used to predict the continuous or quantitative values such as price, salary, age, etc.

Semi-Supervised Learning

Semi-supervised learning is actually the same as supervised learning except that of the training data provided, only a limited amount is labeled.

For example, In Image recognition, we might provide the system with several labeled images containing objects we wish to identify, then process many more unlabelled images in the training process.

Unsupervised Learning

In Unsupervised learning, we focus on clusters of like data. The algorithm analyzes input data and identifies the group of data that share the same traits.

For example, Look at the picture below.

An input data with the mixture of animal species is given as an input to an unsupervised machine learning algorithm. The algorithm helps in classifying the animal data separately into individual species.

Click here for the source of the image

Reinforcement Learning

Reinforcement Learning is a type of machine learning technique that enables an agent to learn in an interactive environment by trial and error using feedback from its actions and experiences.

For example, Imagine a baby is given a TV remote control at your home (environment). In simple terms, the baby (agent) will first observe and construct his/her representation of the environment (state). Then the curious baby will take certain actions like hitting the remote control (action) and observe how the TV responds (next state). As a non-responding TV is dull, the baby dislikes it (receiving a negative reward) and will take fewer actions that will lead to such a result(updating the policy*) and vice versa. The baby will repeat the process until he/she finds a policy (what to do under different circumstances) that he/she is happy with (maximizing the total (discounted) rewards).

*- Policy here refers to the change of state i.e, whether the TV is on or off.

I hope I helped you with understanding these terms well. A better understanding of these terms is the most essential prerequisite for understanding further ML concepts.

You guys can refer to the below sites to learn more about the growing world of Machine Learning:

1. https://www.geeksforgeeks.org/introduction-machine-learning/
2. https://towardsdatascience.com/introduction-to-machine-learning-for-beginners-eed6024fdb08
3. https://towardsdatascience.com/machine-learning-an-introduction-23b84d51e6d0
4. https://www.pluralsight.com/courses/python-understanding-machine-learning

Happy Learning!