My blog on AI projects and DSA learning journey
This post covers my key takeaways from Stanford's CS231n (2016) Lecture 2 by Andrej Karpathy. The lecture focuses on data classification strategies, specifically comparing the Nearest Neighbour approach to Linear Classification. Link: CS231n 2016 Lecture 2 . The Nearest Neighbour Approach One of the earliest approaches to classification was the Nearest Neighbour algorithm. This method classifies…
Problem: https://www.hackerrank.com/challenges/30-binary-numbers The requirement is to convert an integer and convert to a binary number format where we can get the maximum length of number of 1's. So this is how I approached the problem: Convert the integer input into binary format using bin() python built-in function. Since we get an output type of string input for binary input, we need to slice…
Before the Transformer boom, the neural networks was the new hype which was based on the human brain's neuron power and overall capability. In this post, we will delve deep into neural networks at a theoretical level and build from scratch with the use of PyTorch so that we can understand each step and how it works during the full training process. When we start explaining a NN, it begins with the…
This is my understanding of HackerRank Python question: Python - List Comprehension The idea is to provide an array of all possible combinations of [i, j, k] for the dimensions of a cuboid, however the sum of the array should not be equal to n. So we use a list comprehension to solve this by printing a list and within that list we have all the possible combinations allowed. Another key point is…
Linear regression is a fundamental concept in machine learning. It is heavily used in all sorts of deep learning architectures such as neural networks as an example. As a matter of fact, even ChatGPT uses linear regression to an extent. So why is linear regression called linear regression? The term regression basically means we have a line and we can an n number of…
The purpose of the gradient descent is to minimize the function. The more mathematical term is called the method of least squares. y = x 2 Why is the gradient descent specifically y = x 2 because the original formula for a line is y = m x + b but that does not have a bottom since a line is continuous and infinite, meaning there is no end. Whereas, the parabola is…