Machine Learning with real world examples
Artificial Intelligence (AI) or its subset Machine Learning (ML) is one of the most rapidly evolving field in the tech world . According to many surveys, AI and Machine Learning are the top technology trends in 2020. With high demand in these fields, more and more people are advancing their career in the field of Data Science and with plethora of courses and boot-camps available online, anyone can easily master the skills required to become a data science professional.
Artificial Intelligence is a branch of computer science where machines are designed or trained to performed activities which require intelligence. Machine Leaning on the other hand, can be called a subset of AI.
As defined by Aurelien Geron in the book Hands-on-ML,
“Machine learning is the science (and art) of programming computers so they can learn from data.”
In layman’s term, we use statistics (traditional mathematics) to build models which when fed with data collected over a time period help us to forecast the outcomes.
We use Machine learning in our daily activities most of the time without even realizing it. To explain with a real-life example, while shopping on Amazon or any other website you might have come across suggestions on similar products or recommendations to buy products which go along with the purchased product. You would have also figured out how Netflix recommends you movies you may like. Machine learning makes all our lives easier and saves a lot of our time.
Data is growing rapidly in all domains in the form of information, images, audio, etc. So, to predict something helpful or to learn a pattern from the provided data is possible with Machine Learning. The more you train the machine learning models with data it forecasts more accurately. Machine learning has gained lot of popularity because it has the potential to yield valuable insights. Businesses are dependent on them as it guides them by highlighting the areas of prime impact and are of benefit to the company.
Machine learning has many types, but here I would like to explain about the 2 main types.
1.Supervised Learning: In supervised learning, the model is trained on past input and its corresponding labelled output data. The learning algorithm creates a function which when fed with input data predicts the possible output. The more we train the model with data, the more accurate the predicted results will be. Consider a cab service company who wants to calculate the trip duration of the ride. It will train the model with data (distance covered, time taken, time of the day, weather conditions etc.) of past rides. On supervising the machine learning model with past ride details it can accurately predict the upcoming one.
2. Unsupervised learning: In Unsupervised learning, there is no prior information about the data. And since the data is not labelled, the machine should learn to categorize the data on the similarity and patterns it finds in the data. This helps us to obtain interesting relations between the features present in the data. An example of unsupervised machine learning would be a case where a supermarket wants to increase its revenue. It decides to implement a machine learning algorithm on its sold products’ data. It was observed that the customers who bought cereals more often tend to buy milk or those who buy eggs tend to buy bacon. Thus, redesigning the store and placing related products side by side can help them understand consumer mindset and increase revenue.
Summary:
I have tried to explain the basics of Machine learning in the easiest way possible. I hope this motivates you to explore more on Machine Learning and its applications.
If you have any questions or recommendations, you can reach out to me in the comment section.
