đŻ Goal: To help you understand the difference between convex and non-convex functions â and why they matter when training machine learning models. đ§ 1ď¸âŁ What Is Optimisation in ML? At its core, machine learning is about optimising. You have a loss function (how wrong your model is), and you want to find the best […]
Tag: machine learning
Probability & Statistics for Machine Learning â Mastering Uncertainty
đŻ Why Itâs Critical in ML Machine learning models donât just spit out answers â they work in a world of uncertainty. We need probability and statistics to:â Quantify how confident a model isâ Understand data behaviourâ Measure errors, risks, and improvementsâ Make decisions when we donât know everything Without these tools, youâre essentially blind […]
Gradient Descent with Simple Intuition
If youâve ever peeked inside a machine learning modelâor even trained oneâyouâve probably heard the phrase âgradient descent.â But what is it exactly? And why should engineers care? Today, letâs strip away the jargon and look at gradient descent in plain English. No equations, just clear thinking â and a link to the world of […]
Why Every Engineer Should Understand the Basics of Machine Learning
Whether you’re building back-end systems, mobile apps, or front-end features, one thing is becoming clear: machine learning (ML) is no longer just for data scientistsâit’s becoming part of a modern engineerâs toolbox. But why should every engineer care? 1. Models Are Just Supercharged If-Else Statements Imagine you’re writing code to categorise emails as “spam” or […]
Calculus for Machine Learning â A Practical Guide
đŻ Goal: To give you a solid intuition for how and why calculus (especially derivatives and gradients) powers machine learning learning & optimisation. No need to master every detail â just enough to understand what’s going on when a model trains. đ§Ž 1ď¸âŁ Whatâs Calculus Doing in ML? Calculus is all about change. In ML, […]
Linear Algebra for Machine Learning
đŻ Goal: Help you understand and use vectors, matrices, and dot products â the building blocks behind ML models like linear regression, neural networks, and PCA. đ§ą 1. Whatâs a Vector? â Definition: A vector is just an ordered list of numbers â like a row or a column. In ML: đ§° 2. Whatâs a […]
