Blog

If you have read of neural networks, there’s some chance you must have heard of the universal approximation theorem. The key principle that makes these machines so powerful. Universal Approximation Theorem The Universal Approximation Theorem states that a feedforward neural network with a single hidden layer containing a finite number of neurons can approximate any continuous function on a compact subset of \(\mathbb{R}^n\), provided the activation function is non-constant, bounded, and continuous. ...

Just Why? The first thing that needs to be addressed is why I decided to make this website. Why did I spend the entirety of 19th January 2025 figuring out how to host this goddamn webpage? The reasons are threefold: I have lately realized I love to yap, have tons of thoughts, and would love a place to pen (type) them down (hence the blog). I have always been somewhat obsessed with the idea of having a domain name for myself. I splurged a bit today and therefore had to add content to the page with my name—what better than random thoughts? I have to thank Aniruddha Deb for the idea of hosting a blog page using Hugo. I have always enjoyed reading his blogs and was inspired by him to create something similar. You will see that the theme of this page is inspired by Aniruddha’s page because I found Hugo through his blog and used some style elements from his GitHub repository. ...