Machine Learning Pre-Starter

People have always made machine learning appear all geeky and out of this world kind of thing 🙂 We will be having a two-piece blog post on machine learning as it is often confused with artificial intelligence. The ability of a computer program to think and act as a human is often referred to as artificial intelligence. With A.I, the system is able to learn and acquire knowledge over a period of time and act based on that.

Graphic explanation of ML in relation to AI and data

One might ask; how then can we differentiate A.I from ML? Simply say ML is a subset of AI. We use a lot of ML systems everyday an example is spam detection calls. In Machine learning, the computer learns from experiences and not as AI that acts based on knowledge gained. Other examples of ML usage includes email classification; filtering of messages into spam and inbox folder and fraud detection for bank transactions. Ever wondered why your bank card is disabled when you use it a strange location for the first time? Or the most common, customer targeting aren’t we all tired 🙂

When should one use machine learning? People tend to misuse it these days as we have come to see that some systems don’t need ML. Things that could easily have been hard-coded have somehow been turned into an ML system.

Like every good meal, there is one ingredient that makes an ML system come out great CLEAN DATA!!! I wrote about it in a previous post. I saw a LinkedIn post sometime back via the #analytics hashtag and the catching phrase was “Data is all about understanding”. The post went on to say “It’s not about ML, statistics, visualization…” I believe this to be true. Once you are able to understand your data, then you are able to decide if it’s something that requires ML, deep learning or AI.

Clean data is the main ingredient to any system

*Graphics created using*

The goal of any project is to deliver a working software, this is achieved using the agile mindset by adapting new changes, being transparent, minimizing or elimination of waste etc. In our next post we will be going deeper into machine learning, explaining with use cases and a demo.

PS: Do you have any suggestions? Or what you would love to see covered in the next machine learning post? Please share. Thank you.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s