A Beginner’s Guide To Machine Learning

Introduction

Machine learning is a subfield of Artificial Intelligence, that allows the computer to think and learn without being explicitly programmed. Machine Learning focuses on using Algorithms to find out patterns and make predictions from data. Just like a human, the Machine Learning system learns from its experience and gradually increases its accuracy in finding patterns and making predictions¹.

The AI traffic violation camera, which detects violations like wearing seat belts, and helmets, is a good example of Machine Learning. The application of Machine learning is not limited to finding traffic violations. Fields in which Machine Learning is used are given below.

Healthcare:

Disease diagnosis.
Drug development.
Personalized medicine.
Medical image analysis

Finance

Fraud detection and prevention.
Algorithmic trading and stock market prediction.
Credit risk assessment.

Retail

Product recommendation systems (e.g., Amazon and Netflix recommendations).
Demand forecasting and inventory management.
Price optimization.
Customer segmentation for marketing.

Agriculture

Crop disease detection and monitoring.
Precision agriculture and yield prediction.
Livestock management and animal health monitoring.

Classification of Machine Learning Algorithms

Machine Learning can be mainly classified into Supervised Learning and Unsupervised Learning

Supervised Learning:

In supervised learning, the algorithm is trained on a labeled dataset². From analyzing the dataset, the algorithm will derive patterns to make future predictions. An example of labeled dataset would be the data of medical features of patients who are tested for Covid 19. If there are medical features for people who are tested positively and negatively for Covid 19, when a new patient comes for testing for Covid 19 the machine learning algorithm will be able to predict if the patient is covid positive or not by looking only at the medical features. This can be done for cancer Prediction, diabetes prediction, weather prediction, House price prediction etc

Supervised learning is like teaching a computer to learn from examples (Labeled Dataset). For example, you show the Computer 50 photos of Dogs( labeled dog photos) and 50 photos of Cats( Labeled as cat photos). The Supervised Machine Learning Algorithm goes through all the Dog photos and identifies the common patterns of a dog photo. A similar operation is done on the cat photo as well. The next time you show the computer a new picture of a cat or a dog, the algorithm will itself predict whether it’s a cat or a dog.

A similar technique is used in AI traffic violation cameras. Feed the computer 1000 images of person wearing a helmet (labeled data) and 1000 images of person not wearing a helmet (labeled data). The Supervised Machine Learning Algorithm will find common patterns in photos of person wearing a helmet and not wearing a helmet. Next time you show the computer a new picture of a person travelling on a bike, the algorithm will tell if the person is wearing a helmet or not.

Examples of Supervised Learning algorithms are: Linear Regression, Logistic Regression, Naive Bayes, Decision Tree, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), etc

Unsupervised Learning:

Unsupervised learning deals with unlabeled data, where the algorithm tries to find hidden patterns or structures within the data without any explicit guidance². For instance, If you provide the customer data of a supermarket to an Unsupervised algorithm, it will be able to find patterns which are not obvious to us humans.

Examples of Unsupervised Learning algorithms are: K-means clustering, Hierarchical clustering, DBSCAN, etc

Machine Learning Toolkit

We need the following tools to get started with a Machine Learning Project. In this article, we will cover only a brief introduction to Machine learning, but in the coming articles, we will delve into successfully completing a machine learning project on our own. Let us look at the tools required.

Programming Languages:

When it comes to the choice of programming languages, Python and R are at the forefront. Due to simplicity and rapid growth factor, I am choosing Python for our Machine Learning adventure.

Integrated Development Environments (IDEs):

There are several IDEs out there to run Machine Learning Code, but out of all those, Google Collab is the one I would prefer due to its user-friendliness. If you have a Computer with a browser and an internet connection (and dedication), you can become a Data Scientist.

Data:

What good is Machine learning if there is no data to learn from? Collecting data relevant to our Machine Learning Project is a hectic task by itself. I will be writing an article only on that aspect. But for the time being, we can make use of sites such as Kaggle to provide us with sample data for our ML project.

Conclusion

It is of no use to bombard people with a ton of content, especially when it comes to a technical topic like Machine learning. So I am concluding my article here. My ultimate aim is to allow even a high school student to be able to execute at least one Machine Learning Project. To fulfill that, I encourage you to be thorough with this article and wait for the second article on Machine Learning.