All posts tagged with #ai.
A step-by-step mathematical analysis of the linear regression cost function J(w,b). We compute derivatives, find critical points w* and b*, build variation tables, and prove J is convex with a unique global minimum.
Learn how linear regression works by fitting a line to data. We cover the model f(x) = wx + b, training example notation, the slope parameter w, and the Sum of Squared Errors cost function J(w,b).
In this reflection, I share how I completed both my master's thesis and engineering project on IMRAD classification. From building a 169k-sentence dataset and fine-tuning BERT models to a 98.21 percent F1 score, to launching a full microservices SaaS platform. This post details the complete technical journey.