Beyond the Margins exploring mathematics & machine learning

Regularized (Penalized) Regression

In this article, we will explore regularized (penalized) regression methods that help prevent overfitting and address issues such as multicollinearity, which can make $X^TX$ ill-conditioned or even non-invertible. OLS Limitations: As mentioned in this article Read more

The Complex Beauty of the Mandelbrot Set

In this article, we will explore the artistic component of mathematics. Specifically, we will look at the Mandelbrot set– a set of complex numbers that exhibits artistic beauty. What Constitutes the Mandelbrot Set? The Mandelbrot set is a mathematical set of complex numbers. When we plot the points inside and outside this set we can observ... Read more

Multiple Linear Regression (Part 3)

In this article, we will look at another technique to calculate the regression coefficients $\beta$ called Gradient Descent. This is an optimization technique that involves taking the gradient to find the optimal $\beta$ values that minimize the loss function. Optimization and Linear Regression In the previous post, we looked at how the nor... Read more

NLP-Driven Predictive Modeling of Clinical Trial Status

Introduction/ Motivation Clinical trials are research studies conducted to evaluate the safety and effectiveness of new medical interventions, such as drugs, treatments, or medical devices. These trials involve the participation of human volunteers who may benefit from innovative healthcare solutions. However, not all clinical trials proceed as ... Read more

Multiple Linear Regression (Part 2)

In this article, we will explore the common metrics that help us assess the performance of our linear regression model. We will also look at an implementation of linear regression using the scikit-learn library in Python. Additionally, we will discuss the assumptions underlying linear regression and discuss when linear regression is useful in... Read more