Machine learning is the ability to learn without being explicitly programmed. Well, what does that mean? In essence, computers or CPUs are pretty dumb if we don’t program them. Without AI, a computer usually works in a simple input to output paradigm. We input a command either through programming or UI, open Word and then the computer responds with opening the program, the output. Another example is your calculator. We input two times five and the calculator outputs 10 as the response.

In a machine learning paradigm, there is another factor added to this input to output equation, the learning part. We have an input, learning model, and then the output. In this paradigm, the machine learns from your inputs and makes better output over time. Let me demonstrate with a simple Google search. If you were to type and make the mistake to type into Google search this query, what is the biggest dessert in the world, when you meant desert, in a simple input to output paradigm, Google may show you the biggest cookie or cake in the world.

But because Google is built with AI at its core, it will have inferred that when someone is asking for the biggest dessert in the world, they probably are looking for a desert, not food.And this is where machine learning comes into play. Over years of gathering data or training the ML model, Google has learned that in most cases when someone is searching for biggest dessert in the world, they truly mean desert and that is the important item of machine learning.It needs to be trained for its model to be efficient, accurate or in other words intelligent.

A machine learning paradigm needs to be fed with hundreds, thousands of more data sets to work. A great example is when Deep Mind trained their machine learning computer to play Go,a Chinese board game. They spent hundreds of hours of feeding their machine all types of plays before the machine was able to predict what move to do next. So this is what machine learning is.

Common Use cases
  • Inventory optimization through SKU assortment + machine learning ensure shelves are stocked and best products are always available for purchase.
  • Detecting Fake News Fake news is a real problem, and part of the problem is that there aren’t enough humans to sit there and manually sift through every article to determine its genuineness. This is the kind of scale problem that machine learning is really good at solving.
  • Face Authentication – Recent IPhoneX has build in Face authentication, It is good at solving the problem of not to remember and typing in passwords.
  • Sentiment Analysis can help companies improve their products and services by better understanding how their offering impact customers.
  • Fraud Detection to detect anomalies and other errors that signal dishonest behavior.
  • Demand forecasting by pricing optimization to meet consumer demand related by creating a demand forecast at various price points and business constraints to maximize potential profit.
  • Personalized offers improve the customer experience by offering relevant information which in turn provides retailers with improved data about the customer’s brand engagement.

2 thoughts on “Introduction to Machine Learning

  1. Aw, this was an exceptionally nice post.
    Taking the time and actual effort to produce a very good
    Machine Learning seems like a future to go. Explained so nicely and easy to follow.

Leave a Reply

Your email address will not be published. Required fields are marked *