Understanding Transformers (NLP )
In this article we will try to understand the complex “transformers” structure , there are a lot of components involved within the structure and i hope you are familiar with …
Kolmogorov–Smirnov test ,comparing distributions
Understanding and recognizing the distribution of data points is one of the important tasks of any Machine learning problem. Many mathematical assumptions , feature engineering techniques or algorithm selections are …
Kolmogorov–Smirnov test ,comparing distributions Read More »
Weight initialization techniques visual demo
Any deep neural network (with similar structure as below) has “weights” associated with every connection . “Weights” can be viewed as how important , (with either positive or negative correlation …
PCA for interviews-Eigenvectors/Langrangian
The math behind constrained optimisations , drawbacks and other important discussions One of the most important mathematical concept required to understand the working of PCA is the concept of Eigenvectors …
GloVe Model
The first and foremost task of any NLP problem statement is to perform text pre-processing and eventually find some way to represent texts as machine understandable numbers. This article assumes …
TIME COMPLEXITIES OF ML ALGORITHMS
THIS ARTICLE SUMMARISES THE TIME COMPLEXITIES OF THE MOST COMMONLY USED AND ENQUIRED MACHINE LEARNING MODELS. TIME COMPLEXITIES ARE IMPORTANT TO REMEMBER IN RELATION TO THE FOLLOWING QUESTIONS ASKED: WHEN …
Gaussian NAIVE BAYES, continuous features
There are different variants of Naive bayes , bernoulli, and Gaussian. This article assumes you are familiar with the the basic idea behind Naive bayes and also how it works …
Splitting nodes in DT for continuous features(classification)
Splitting nodes in decision trees (DT) when a given feature is categorical is done using concepts like entropy, Information Gain and Gini impurity. But when the features are continuous , …
Splitting nodes in DT for continuous features(classification) Read More »
KNN and Probability (interview questions)
Article on one of the most common interview question: How do you interpret KNN outputs? KNN does not have a learning phase . Its a lazy algorithm that just finds …
The Fault In “GPT-3”. IS IT A HYPE?
IS GPT-3 A HYPE? WHAT MEDIA SAYS AND IS IT IMPORTANT FOR INTERVIEWS? If you are familiar with the concept of attention and transformers , you must have come across …
INTERVIEW GUIDE TO TSNE
Here we discuss one of the most important concepts when it comes to interviews , there are many resources on the internet available , but remember interview questions are not …