Coursera Courses

Generative AI (Gen AI) has become a buzzword, but sometimes it’s tricky to know what really qualifies as Gen AI and what doesn’t. Let’s break it down step by step so you’ll always know whether you’re looking at generative AI or traditional machine learning. The Key Question: What Is the Output? Not Gen AI if the output (Y) is: A number (e.g., predicted sales) A class (e.g., spam vs. not spam, cat vs. dog) A probability (e.g., 75% chance of rain) Yes, Gen AI if the output is: Text (e.g., an essay, a poem, or code) Speech or audio Images or video (like our friend Fred 🐶 from before) 👉 In short: Generative AI doesn’t just label—it creates . A Quick Math View If you remember high school math: y = f ( x ) y = f(x) x (input): Data (CSV files, text, audio, images, etc.) f (function): The model (the rules or process applied) y (output): The result If y is a number/class , that’s traditional ML . If y is natural language, audio, ...

Machine learning is a broad field with many different approaches. One of the most powerful of these is deep learning , which takes inspiration directly from the human brain. Let’s break down what this means, and how it connects to generative AI —the technology behind tools like ChatGPT, image generators, and more. Deep Learning: The Next Step in Machine Learning Machine Learning (ML) : Covers many techniques that let computers learn from data. Deep Learning : A specialized branch of ML that uses artificial neural networks (ANNs) to learn more complex patterns. Just like your brain, ANNs are made of interconnected neurons (nodes). These neurons process data, make predictions, and when stacked in multiple layers , they become capable of recognizing very complex patterns—far beyond what traditional ML models can do. Supervised, Unsupervised, and Semi-Supervised Neural networks can work with: Supervised data (labeled) Unsupervised data (unlabeled) Semi-supervis...

When we talk about machine learning (ML), two major categories often come up: supervised and unsupervised learning. Understanding these two approaches is essential, because they form the foundation for more advanced topics—like deep learning and generative AI. The Key Difference: Labels  Supervised Learning : Works with labeled data —that means the dataset already comes with tags, like a name, category, or number. Unsupervised Learning : Works with unlabeled data —raw information with no predefined tags. Think of labels as answers to a question. Supervised models are trained with those answers, while unsupervised models try to uncover patterns without them. A Real-World Supervised Example Imagine you own a pizza restaurant. 🍕 You have historical data about: The total bill amount Whether the order was pickup or delivery The tip amount With supervised learning, your model studies this past data to predict future tips . For example, given a new bill tot...