AI Basics: Key Terms Explained

AI can sound complicated, but many concepts are easier than they seem. Here’s a simple glossary of key terms, each with a real-world example:

🤖 Artificial Intelligence (AI)

Any technique that enables computers to mimic human intelligence — like reasoning, learning, or problem-solving. Example: A chatbot that answers your customer service questions.

📚 Machine Learning (ML)

A type of AI where the system improves its performance by learning from data — without being explicitly told what to do. Example: A spam filter that gets better over time by analyzing which emails you mark as spam.

🧠 Neural Network

A machine learning model made up of layers of interconnected nodes (like virtual neurons) that recognize patterns in data. Example: A model that can identify animals in pictures by learning shapes and features.

📊 Dataset

A structured collection of data used to train or evaluate an AI model. Example: Thousands of labeled photos showing cats and dogs, used to teach an image classifier.

🏋️ Training vs. Inference

Training is the learning phase — the model adjusts itself using example data. Inference is when the trained model makes predictions on new, unseen data. Example: A language model is trained on books (training), then used to write an email reply (inference).

⚙️ Algorithm

A defined set of instructions a computer follows to solve a specific task. Example: A sorting algorithm that arranges products by price on an online store.

🗣️ Natural Language Processing (NLP)

A branch of AI focused on helping computers understand, interpret, and generate human language. Example: GReq uses NLP to detect vague or inconsistent wording in requirement documents.

👁️ Computer Vision

A field of AI focused on enabling computers to understand and interpret visual information such as photos, videos, or live camera input. Example: A self-driving car uses computer vision to detect lanes, signs, and pedestrians in real time.

🎲 Reinforcement Learning

A type of machine learning where a model learns to make decisions by interacting with an environment. It receives feedback in the form of rewards or penalties and learns to optimize its behavior over time. Example: A model learns to play chess by trying different moves and improving based on which ones lead to a win.

✨ Generative AI

AI models that create new content — such as text, images, audio, or code — that wasn’t directly copied from the training data. Example: An AI model that generates new marketing copy based on your product description.

---

These concepts are the building blocks of modern AI — understanding them makes it easier to evaluate, apply, or even build intelligent systems.