-
Rosalind Rangers
A series where we will be solving problems from Rosalind, a platform for learning bioinformatics through problem-solving
-
[CnC02] Turing Machines
In this post, we will discuss Turing Machines, a theoretical model of computation that can simulate any algorithm. We will explore the components of a Turing Machine, its working principle, and its significance in the field of computer science. By the end of this post, you will have a clear understanding of how Turing Machines operate and their role in the study of computability and complexity theory.
-
[CnC01] Basic Plotting Using Python
This post recaps the August 17th Code n Coffee session on basic plotting with Python's matplotlib, covering CSV data, plot customization, and polynomial fitting for effective data visualization.
-
[ML02] Other Loss Functions: Stochastic Gradient Descent, Regularization
This post covers stochastic gradient descent (SGD) for efficient optimization with large datasets, introduces cross-entropy loss for classification, and discusses regularization to prevent overfitting and improve generalization.
-
[ML01] Introduction: Linear Regression and Gradient Descent
A brief introduction to Machine Learning through curve fitting, the mathematical formulation of linear regression, loss functions, and the gradient descent algorithm for optimizing model parameters.
-
Git & GitHub: An Invitation to Version Control
This blogpost / talk is meant for beginners, and assumes no prior knowledge of Git or GitHub. It is also meant to be interactive, so that the readers can follow along and try out the git commands themselves.
-
Remote Devlopment on SSH Servers
Secure Shell servers, are used for providing secure and encrypted access to remote servers. Here we dive into the details of these servers, covering topics like creating servers, setting up environments, updating projects, and running code.
-
Markdown
Here we focus on the fundamentals of Git & GitHub, covering basic concepts like commits, branches, pull requests (PRs), merges, and integration with other tools used by coders, such as VS Code.
-
Why Neural Network
We want to build an intelligent system. But why neural networks? In this, we will explore the concept of universal approximation, which states that neural networks can theoretically approximate any function, given enough hidden units and a suitable activation function.