Supervised Learning
Audio Blog Version:
In a 90 sec video here I have provided the general high-level introduction of machine learning. In this article, I will explain supervised learning and how it is used to solve everyday problems by business owners.
Supervised Learning is the type of machine learning where the learning process is supervised. In this case, we provide the algorithm with the expected labels or outputs. Once our model is well trained by providing it sufficient representable data, we can deploy it for production. Supervised learning is generally classified into two categories. Classification and Regression.
Classification
If you feed your model with pictures of various fruits and label them as fruits, once well trained when you will provide a picture of a fruit the algorithm will detect if it is a fruit or not. Similarly, we can also train our model to classify between different fruits i.e. apple vs orange vs banana by providing the suitable data for training. This type of supervised learning where you classify between different categories or objects within a category is generally referred to as classification.
Regression
Regression is the type of supervised learning where we predict an outcome or value based on the information available to us from historical data. For example, a company can predict its inventory requirements based on the data of sales from previous months. Similarly, if you have available data about the housing prices of a particular region based on different attributes of the houses you can predict the price of the house you are planning to buy in a particular region.
Application
Imagine you are a retail shop owner, and you want to use machine learning to make your processes more efficient, have more visibility and to increase the revenue based on that information. Your requirement is to have more information on the customers that are visiting your store which is generally referred to as “demographic analysis” and you want to predict based on that information your sales and required inventory. Advantech based on Intel’s hardware provides “store traffic analysis” solution which uses supervised learning to classify between age and gender of people. Coupled with the whole UShop solution you can also predict (regression) your sales based on footfall and how it will impact revenue of the store.
To learn more about the solution using machine learning to solve real world use-cases visit TD SYNNEX’s IoT solutions catalogue page here.
Naqqash Abbassi
IoT Solution Architect (A.I and Vision)
IoT and Analytics Team
TD SYNNEX Europe