Categories
Algorithms

LeetCode: Kth Largest Element in an Array using QuickSelect with Hoare Partition

Find Kth Largest Element in an Array is a problem which can be solved using e.g. QuickSort in O(nlogn) time and then pick the k-th element in the sorted array. Another way is to sort it using QuickSelect in O(n) times. The solution below beats 100% Java submissions on LeetCode for runtime. QuickSelect QuickSelect is […]

Categories
Data Science

Understanding Transformer Architecture in NLP

Posting some great resources to understand the Transformer architecture for NLP presented in the paper “Attention is All You Need” (Vaswani et al. 2017). This website by J Al-Ammar is excellent Second, read this article called “Attention! Attention!” by Lilian Weng For further background on Word Embeddings, look into this post by Jason Brownlee.

Categories
Data Science

SQL Notes for Data Science

SQL is one of the most widely used programming language but yet it remains too much undervalued. Here is some quick SQL query snippets for refreshing the memory. Introductory Concepts Optional: Learn about FOREIGN KEY and PRIMARY KEY and the different Database Normalization types from this Wikipedia page. Probably you will need only up to […]

Categories
Data Science OMSCS

Deep Learning Image Processing Tasks

Image Classification: Class distribution per image Semantic Segmentation: Class distribution per pixel Instance Segmentation: Class distribution per pixel with unique ID Object Detection: List of bounding boxes with Class distribution per box

Categories
Data Science

Easy explanation of Convolution vs Cross-Correlation in Convolutional Neural Network (CNN)

Convolution layer for CNN is explained in simple words

Categories
Blog

The 14 Leadership Principles for Amazon

Customer Obsession Ownership Invent & Simplify Are Right, A lot Learn and Be Curious Hire and Develop the Best Insist on the Highest Standards Think Big Bias for Action Frugality Earn Trust Dive Deep Have Backbone; Disagree & Commit Deliver Results

Categories
Algorithms Data Science OMSCS

Neural Network Differentiation

To differentiate the loss function in a Neural Network, there are four options Manual differentiation: It is labor intensive and often it is hard to calculate the closed form solution especially for complex function Symbolic differentiation: Like manual, it is also hard for complex function Numerical differentiation: Can handle complex function but may cause numerical […]

Categories
OMSCS

My OMSCS journey

I started my MS in Computer Science at Georgia Tech in Spring 2019. Since then it has been a very challenging yet rewarding journey. Let me revisit the courses every semester. Database System Design Reinforcement Learning and Decision Making (Eventually dropped) Software Architecture and Design Graduate Introduction to Operating System Information Security Machine Learning for […]

Categories
Essays

The Most Important Skill in the Future

Asking questions is the most important skill in the future. Finding the possible answers of the question is the next most important skill.

Categories
Algorithms Data Science OMSCS

Game Theory Concepts for Reinforcement Learning

There are many flavors of games in Game Theory which are interesting from Machine Learning perspectives, especially from multi-agent Reinforcement Learning applications. Here is the summary of multiple game types are if MinMax algorithm works and what type of strategy one needs to employ.