Introduction to Machine Learning

4 min readJul 28, 2021

Humans learn from their experiences and gain expertise. Machine Learning is concerned with computer programs that imitate this process. It is a field of study that gives computers the capability to learn without being explicitly programmed.

Can you imagine how Netflix makes those recommendations?

The program learns from your past activities and tries to gain expertise in predicting your behavior. It then recommends the shows accordingly.

When did it come into existence?

Arthur Samuel coined the term, Machine Learning, in 1949. Samuel is most known within the AI community for his groundbreaking work in computer checkers.

Samuel built a program that was among the world’s first successful self-learning programs. The program defeated the then self-proclaimed checker’s master Robert Nealey.

Types of Machine Learning

There are three major recognized categories of Machine Learning.

a) Supervised Learning

b) Unsupervised Learning

c) Reinforcement Learning

A. Supervised Learning

As the name suggests, the process of learning is being supervised in this type of Machine Learning. The program learns from the dataset that is labeled as a train dataset. The train dataset contains both, the input variables and the output variables. After learning, the program forms a function that maps the input to an output. So, the train dataset here supervises the formation of that function. This function can now be used for any dataset that needs its output variables to be predicted.

Steps involved in Supervised Learning

Firstly, define your problem statement.
Decide the dependent and independent variables.
Split the data into a training dataset, test dataset, and validation dataset.
Determine the suitable algorithm for the model.
Create a model(the function)by using the training dataset. Sometimes we need validation sets as the control parameters, which are the subset of training datasets.
After the model is created, execute the algorithm on the training dataset.
Evaluate the accuracy of the model by using the test dataset.
Improve the model.
Deploy the model and monitor real-time.

Supervised learning algorithms can be further classified into two types of problems.

i) Regression: The output variable, i.e the variable to be predicted in this type of algorithm is continuous. For example, predicting the amount of rainfall. Here the amount of rainfall is a continuous type of data.

ii) Classification: The output variable in this type of algorithm is discrete. For example, predicting whether it will rain or not tomorrow.

B) Unsupervised Learning

Again, as the name suggests there is no so-called train data set that supervises the process. The goal of unsupervised learning is to find the underlying structure of the dataset, group that data according to similarities, and represent that dataset in a compressed format.

Unsupervised learning algorithms can be further classified into two types of problems.

i) Clustering: Clustering is a method of grouping the objects into clusters such that objects with the most similarities remain in a group and have fewer or no similarities with the objects of another group.

ii) Association: Association rules allow you to establish associations amongst data objects inside large databases. This unsupervised technique is about discovering interesting relationships between variables in large databases.

For example, people that buy a new home are most likely to buy new furniture.

C) Reinforcement Learning

Reinforcement learning is the training of machine learning models to make a sequence of decisions. In simple words, we can say that the output depends on the state of the current input and the next input depends on the output of the previous input.

The best intuitive example for this type of learning is the game of Chess.

There are two types of Reinforcement Learning.

i) Positive

ii) Negative

Consider the scenario of teaching new tricks to your dog.

As the dog doesn’t understand the human language, we can’t directly tell it what to do. Instead, we follow a different strategy.
We emulate a situation, and the dog tries to respond in many different ways. If the dog’s response is in the desired way, we will give it a treat.
Now whenever the dog is exposed to the same situation, the dog executes a similar action even more enthusiastically in expectation of getting more reward(food).
That’s like learning that the dog gets from “what to do” from positive experiences.
At the same time, the dog also learns what not to do when faced with negative experiences.

References: AlmaBetter Course Material