Skip to main content

Posts

This and that

You might have come across this joke that has been doing rounds for years now. Let me tell it to you nevertheless. It unfurls in a classroom, where the teacher is conducting an exam. The students are to write an essay on coconut trees. (What other topic to write on in a state named after coconut trees!) While all the kids went gaga over it, Veer was yet to write a word. Veer was not from the state named after coconut trees, and he knew scant about those. This is not to imply that his was a gone case. He decided to make up for his lack of knowledge in coconuts by leveraging his extensive knowledge about cows. This is how we wrote his essay: Coconut trees are good trees. We have a coconut tree in our backyard. My uncle ties our cow to the coconut tree in the afternoon. The cow gives us milk everyday. My uncle loves our cow very much... In a system that rewards on the basis of the number of words written rather than the sense it carries, Veer passed the test in flying colors. He later hel
Recent posts

The Dress Club

 The Dress was white and gold. It has always been so. The woman who had purchased the dress for her best friend's wedding had put up a pic of it on her social media, and a couple of her prankster friends had claimed the dress to be black and blue, setting the stones in motion. (It is important to note that at the time they were commenting, they had just thought of it as a harmless joke.) The woman who had uploaded the pic of the white and gold dress that she had  purchased for her best friend's wedding lost her mind when her friends said the dress was blue and black. She was a person of simple thoughts, and her mind had no place for her friends' mischief. However, their hard stand was throwing her off. She needed closure. So she did the one thing people do when they need closures. She poised the question to the Internet, with an elaborate description of how she had bought the white and gold dress for her best friend's wedding but how some of her friends were seeing it a

The Trout and The Fighter

The days of tranquillity are probably over. The two-leggeds are back. They have been uncharacteristically away for a while now. No idea what kept them so busy that they decided to forego their annual pilgrimage to our humble abode. Whatever it was, they seem to have dealt with it. Here they come, in their warm sweaters made off the wool from our sheep, wanting to lie in peace at the quaint valley of our own Parvati. For the record, I do not hold anything against the two-leggeds. I find them to be simple and soft creatures. Their bodies could not tolerate the mood swings of the climate that they had to wrap themselves in artificial layers of skin. Their bodies are not fast enough that they had to build metal boxes to get them places. Delicate creatures. Often they come here - with tall tales of how they long to be one with nature. Between you and me, most of them come here primarily to inhale the magic plant. Anyway, I don't intend to indulge in gossip much. Their arrival doesn'

The High State

 Before The Judgement I believe I must begin by addressing the pressing question - Was planning a vacation in the midst of a pandemic a recommended move?  No. Yet we went ahead with it. Here is why.  We (Nithya & I) were newly married, and our vividly planned vacation at the island of Langkawi was stolen away from us by the virus. Our stay in Delhi was coming to an end due to job-related moves, and we felt it would be a waste not to utilize this opportunity in exploring at least one of the tourist hot spots easily accessible from the national capital region. Let us end this section by answering another question - Are the reasons listed above good enough to risk a vacation during a pandemic? No. We had taken a calculated risk. Arrival at Manali There are two phases to this - planning and execution. We had not started planning with Manali in mind. There were numerous choices - starting from Jaipur and Amritsar to Nainital, Shimla, and Manali. After a bit of reading and deliberations,

Machine Unlearning #5 (Reinforcement Learning)

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: Machine Unlearning #0 (Intro) Machine Unlearning #1 (Classification) Machine Unlearning #2 (Regression) Machine Unlearning #3 (Clustering) Machine Unlearning #4 (Outlier Analysis) Reinforcement Learning is a slightly different learning model than the other techniques that we have discussed previously. Therefore, I wouldn’t be able to explain the same using the fruit basket example that we have been using all this while. Let’s replace apples and oranges with self-driving cars! Suppose that you are at Google or Tesla and are trying to train a car to drive by itself! How would you go about that? Driving requires the knowledge of much more than turning the ignition on and steering the wheel. You should know to keep the side of the road, to stop at the red signal, or to keep off the footpath, for instance. You decide

Machine Unlearning #4 (Outlier Analysis)

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: Machine Unlearning #0 (Intro) Machine Unlearning #1 (Classification) Machine Unlearning #2 (Regression) Machine Unlearning #3 (Clustering) Machine Unlearning #5 (Reinforcement Learning) Let’s start with the example. We have the basket full of different fruits and we are sorting the fruits based on their distinctive properties, or features. What would happen if a coconut got mixed in the fruit basket that contained oranges, apples, bananas, cherries, and mangoes? The coconut does not share any feature (color, shape, or size) with any of those fruits in the basket. Since there is only in coconut in the basket, it is not possible to create a separate group of coconuts. Such items in the group, which stand out or are distinctive than the others are generally termed outliers. Outliers are sometimes discarded as noise

Machine Unlearning #3 (Clustering)

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: Machine Unlearning #0 (Intro) Machine Unlearning #1 (Classification) Machine Unlearning #2 (Regression) Machine Unlearning #4 (Outlier Analysis) Machine Unlearning #5 (Reinforcement Learning) We have already gone through classification and prediction. Now let us see what clustering is. Another popular learning technique, clustering is different from the other two since it is an unsupervised learning technique. What does that mean? Let us revisit the classification technique. We show the machine an Orange and explains the features of the Orange to it. Similarly, each different fruit and its features are shown to the machine during the training phase. Once it has learned enough, we use the machine to label a randomly picked fruit. In clustering, such training does not take place. We present the system with a baske