Skip to main content

Machine Unlearning #0 (Intro)

You might be familiar with the term Machine Learning. Worry not if you have not, cause I have tried to give a gist of the concept here. The term has been in the limelight of late and has been tossed around rather liberally to denote anything related to artificial intelligence, robotics, and data mining. Machine Learning, as the name suggests, could simply mean the field of study of enabling the “machines” (computers) to “learn” from past experiences and make informed decisions in the future.  


Wait a minute! Learning from past experiences is something humans do, right? Exactly! The computer folks want computers to behave more and more like us. As if there aren't enough of us already. As the machines are becoming more like us, we are becoming more like them.

Introspection time! Most of us wake up every morning like clockwork! Then we rush through the morning routines - get dressed, wade through the traffic, and reach our offices or schools or wherever people expect us to be. We spend the most hours of most days of our lives there, doing what we call our work or our duty. What exactly is this work? In most cases, it would be a set of instructions laid out to us by some higher authorities. 


Let us assume that you work at a tea stall. You could be spending most of your time boiling milk and adding tea leaves and sugar to it. When the milk boils, it rises up almost instantaneously and spills over the pot. Obviously, you did not know that when you started the new job. It is when the milk actually got spilt and your superior made you clean up the mess, you realized that the stove must be turned off or the flame be lowered as soon as the milk is boiled. Here, you learned something from an experience. In very basic terms, this is the very essence of machine learning.


How do we make machines learn? Well, the techies have come up with some cool techniques to go about that. While there are numerous techniques, the most common ones include classification, regression, clustering, and reinforcement learning.


This is not a series on Machine Learning. Therefore, we would not be discussing the techniques in detail. However, in the following write-ups, we shall take up some of the machine learning terminologies and look at how we have been applying similar concepts in our daily lives in a not so right manner, and how to unlearn the same.


Unlearn? Let’s find out.


Machine Unlearning is a series broken up into tiny, one-minute readable pieces to humor our ever-shortening attention span. Sharing the links to every single piece right below:



Comments

Popular posts from this blog

First Rejection

About four years ago, I self-published my first novel, I Want Your Life . Self-publishing was not my initial plan. Like most aspiring writers, I envisioned my book being published under the label of one of the prominent publishing houses in the country, such as Penguin or HarperCollins. However, my editor gave me a reality check and explained that large publishing houses receive several submissions daily, making it highly unlikely for a first-time writer to get noticed. More than the prestige of being published under an established banner, my excitement lay in seeing my story in the form of a book. So, I chose the self-publishing route. After months of back-and-forth with my publishing team - proofreading, editing, revisions, illustrations, book registration, and printing - my book was finally out. It was truly a dream come true. The upside of self-publishing is the sweet certainty of getting published. The downside, however, is that you are responsible for everything, including promot...

IFF(FPC)K

 If you know me personally, you might also know that I am a regular at the International Film Festval of Kerala, held annually in December at Thiruvananthapuram (and if you don’t know me personally, just read the first sentence). A habit that started during my Thiruvananthapuram days in 2016, I look forward and try to attend the week long celebration of cinema - unless life or a killer virus gets in the way. Prologue Since the dates for the next fest are officially announced during the conclusion of the current fest, what follows is an year long wait. Nothing significant happens for the most part of the year, so let us skip ahead to November - when the registration opens for delegates. Yes, we know that there are over ten thousand delegate passes and registration window usually lasts days - still most of my friends (and I) hit the servers with a passion  until our registrations go through. Once that is done, the wait begins for the schedule to be released - where we would come...

Familial Cowswami

Last day, I had the misfortune of interacting with the husband of one of my cousins at a family event. Since we’ve already established my feelings toward him, let me clarify that he is not an evil person. It’s just that our ideologies and outlooks toward life could poetically be described as Yin-Yang—completely opposite, with no common ground. That’s fine; everyone is entitled to their vision, as long as they don’t try to claim their vision as the only correct one and attempt to shove it on others who haven’t asked for advice. After exchanging pleasantries, we got down to the “real talk.” He started by asking me why I am still sticking around here (India) and not moving abroad. To set the context, he has been working in the Middle East ever since I first met him at my cousin’s wedding, around fourteen years ago. His wife and kids, who used to live with him, recently moved to Canada, possibly to settle there once he retires. Of course, moving abroad seems to be the trend (or even the no...