Posts

We often treat machine learning models as mathematical abstractions, pure functions that map inputs to outputs. We assume that if the math is correct, the system is secure. But models don’t exist in a vacuum; they run on imperfect hardware, rely on approximate floating-point arithmetic, and execute within physical constraints. I wanted to understand exactly how fragile these implicit assumptions are. My goal wasn’t to build a high-performance classifier or to learn the basics of deep learning.

Artificial intelligence systems have rapidly transformed our lives, yet one critical aspect of human interaction remains largely absent in these digital creations—genuine empathy. While much attention is paid to issues like bias, transparency, and accountability, the inability of AI to truly understand and replicate human emotional nuance is rarely discussed. This “empathy gap” raises important ethical questions about how machines interact with vulnerable populations and the responsibilities of those who design and deploy these systems.

When we look up at the night sky, the planets, moons, and stars all seem to move in predictable paths. But what keeps them in motion? Why don’t planets like Earth just fall into the Sun? The answer lies in orbital mechanics, a fascinating branch of physics that explains how celestial bodies move under the influence of gravity. Newton’s Law of Universal Gravitation The first step in understanding orbits is gravity.

Calculus is often seen as a subject full of complex symbols and formulas, but at its core, it’s about understanding change. While derivatives help us measure how things change, antiderivatives do the reverse—they help us reconstruct the original function from its rate of change. In other words, if differentiation is breaking things down, antidifferentiation is putting them back together. What is an Antiderivative? An antiderivative of a function \(f(x)\) is another function \(F(x)\) such that when we take its derivative, we get back \(f(x)\).

In the mid-20th century, the world watched as the U.S. and the Soviet Union competed in a tense battle for technological and military superiority—the Cold War. Today, we are witnessing a new kind of Cold War, one that isn’t fought with missiles or espionage, but with algorithms and qubits. The United States is now locked in an “AI Cold War” with China and other global competitors, yet we are dangerously underinvesting in the key technologies that will define the future: artificial intelligence (AI) and quantum computing.

Exploring Monte Carlo simulations has always intrigued me because of their real-world applications in areas like physics, finance, and artificial intelligence. And what better place to start than with estimating \(π\)? This seemingly abstract number, 3.14159…, holds a special place in mathematics and everyday life, and Monte Carlo simulations give us an intuitive, probability-based approach to approximate it. And here it is, the journey from the math to the code, with everything in between!

In the world of data science, dealing with uncertainty is a constant challenge. Predicting outcomes, modeling trends, or making decisions based on incomplete data all boil down to one thing: how confident are we in the predictions we make? This is where Bayesian Inference comes into play. It provides a framework for updating our beliefs about a hypothesis as we gather new evidence, allowing us to model uncertainty in a probabilistic and flexible manner.

Derivatives are one of the most fundamental concepts in calculus. At their core, they represent how a quantity changes with respect to another. Whether you’re studying physics, economics, or engineering, derivatives allow you to model change, which is a critical part of understanding the world around us. In this installment of Codect, I’ll explain what derivatives are, how they are computed, and why they’re so important. What is a Derivative? Imagine you’re driving a car.

Machine learning models are shaping our world, from recommending what movies to watch next, to determining credit scores, to screening job candidates. At first glance, these algorithms seem like objective decision-makers, built to remove human error and bias. But as we’ve seen time and again, algorithms are only as unbiased as the data they’re trained on. And if there’s one thing we know about historical data—it often carries the weight of societal prejudices and inequalities.

If you’ve ever wondered how machines are able to “see” things in images or videos, then Convolutional Neural Networks (CNNs) are one of the key technologies behind that magic. CNNs have become the backbone of many modern computer vision tasks, from identifying objects in images to powering facial recognition software. In this Codects installment, I’ll explain the inner workings of CNNs, their structure, how they process images, and the mathematics behind them.

Welcome to another installment of Codects, my weekly coding adventure where I take on new challenges to learn something cool. Last week we dove into Linux and built my own simple UNIX-based shell. This week, I decided to build something practical and foundational in terms of web development—a simple web server in Python. While there are plenty of robust servers out there, like Apache and Nginx, building your own server from scratch is a great way to understand how the web actually works, so that’s what I did.

Welcome back to Codects, where I dive into coding projects each week to learn something new or just explore cool tech. This week’s project took me on a journey into the heart of the UNIX operating system: building a Unix shell from scratch using C. The project was both challenging and rewarding, offered me a deeper understanding of how command-line interpreters work. Why Build a UNIX Shell? Building a UNIX shell is like constructing the bridge between the user and the operating system.

Understanding Blockchain with a Simple Python Project Welcome to the inaugural edition of Codects — a series dedicated to exploring exciting coding projects and diving deep into emerging technologies. Each week, I’ll be tackling a new project, experimenting with different tech concepts, and sharing my journey along the way. For my very first project, we’re taking a look into the world of blockchain technology by building a simple blockchain implementation in Python.