Highlights

Snow
Forest

Demo for Text Generation

A Demo for generating text from some starting input words, click here

Github Stats

chahalinder0007

Expanding Bernauli's Theorm to Real World - Amazon Reviews - Part 1

Expanding Bernauli's Theorm to Real World - Amazon Reviews - Part 1
Setting the objective In this blog we will try and explore the implementation of the Bernauli’s Theorm beyond the classical cases and try to get some useful information out of one of the implementation for a real world situation. This blog will be part 1 of a two Part series where we explore bernauli’s theorm to get hold of probability of getting a positive experience after buying a product online given that there are number of sellers available and all of them have similar positive reviews based on different number of total reviews for the same product. [Read More]

Pattern Exploiting Training for NLP

Pattern Exploiting Training for NLP
GPT-3 created quite a buzz when it was first launched a couple of months back for its ability to generate great good amount of text to create a more realistic feel, but it suffered from one particular shortcoming that its simply too big. There has been an increasing move towards creating more light weight implementations in NLP,CV and othe areas for machine learning and artificial intelligence, evident from the fact that most of the papers now along with accuracy also feature inference times for the respective model, a good sign of end use awareness in research. [Read More]

How I finally understood Bayes Theorem

How I finally understood Bayes Theorem
I came across Bayesian theorem a lot early in my education carrier, much like Thomas Bayes himself, I was not able to grasp the importance of this masterpiece. Additionally, much like most of the concepts at the time I just jumped over the understanding of the same and was mostly focused on solving some predefined pattern questions and never bothered to figure out how the theorem can actually be put to use in the real-world implementations. [Read More]

Recommender System made easier with TFRS

Recommender System made easier with TFRS
Creating scalable deep learning-based recommendation systems from scratch is a significantly time-consuming task, especially so that we need to spend significant time on the non-productive elements involved in setting up the model for experiments. It is a given that we will need to perform levels of iterations on the model architecture to get optimal hyperparameters for a particular use case. Google has now launched just the instrument required to reduce the non-productive component in that cycle. [Read More]

Mathematics for solving game of shells

Simple applied mathematics for logical decisions in-game of shells or stocks maybe I shared this post that takes a simple example of Geometric progression and shows how you can quantize and make logical decisions in a game of shells, essentially betting on the outcome to be always profitable. There was a lot of backlash from people saying its wrong to use mathematics to make money and whatnot. My point simply is, if people are aware they can have a look at mathematics in a different light and can adopt it in general life to make informed decisions. [Read More]