AI Fundamentals

Artificial Intelligence

Artificial Intelligence, or AI, is the broad field of building software systems that can perform tasks that normally require human intelligence, such as understanding language, recognizing images, making predictions, or recommending actions.

Machine Learning

Machine Learning is a branch of AI where models learn patterns from data rather than being explicitly programmed with fixed rules. The model improves performance by training on examples and then applying what it learned to new data.

Computer Vision

Computer Vision is the area of AI focused on helping computers interpret and analyze images and video. Common use cases include object detection, quality inspection, medical imaging analysis, and visual search.

Large Language Model

A Large Language Model, or LLM, is an AI model trained on vast text data to understand and generate human-like language. LLMs power chat assistants, summarization tools, drafting systems, coding helpers, and question-answering experiences.

Generative AI

Generative AI refers to AI systems that can create new content such as text, images, code, music, or video. Unlike traditional AI that only analyzes or classifies, generative models produce original outputs based on what they’ve learned from training data.

Neural Network

A Neural Network is the core building block of most modern AI. It’s a computational model inspired by the human brain, made up of interconnected layers of nodes (neurons) that process data and learn complex patterns through training.

Deep Learning

Deep Learning is a subset of Machine Learning that uses multi-layered neural networks (deep neural networks) to automatically learn hierarchical representations of data. It powers many of today’s most advanced AI capabilities in language, vision, and audio.

Natural Language Processing (NLP)

Natural Language Processing is the branch of AI that enables computers to understand, interpret, and generate human language. It includes tasks like sentiment analysis, translation, named entity recognition, and text summarization.

Prompt Engineering

Prompt Engineering is the skill of crafting clear, effective instructions (prompts) to guide AI models—especially Large Language Models—to produce the desired output. Good prompt engineering significantly improves the quality and reliability of AI responses.

Training vs Inference

Training is the process of teaching an AI model by feeding it large amounts of data so it can learn patterns. Inference is what happens afterward—when the trained model is used in production to make predictions or generate outputs on new data.

Supervised Learning

Supervised Learning is a type of Machine Learning where the model is trained on labeled data (examples that include both input and the correct output). It’s commonly used for tasks like classification and regression.

Unsupervised Learning

Unsupervised Learning is a Machine Learning approach where the model learns patterns from unlabeled data without explicit guidance on what the “right” answer is. Common uses include clustering, anomaly detection, and dimensionality reduction.

Fine-Tuning

Fine-Tuning is the process of taking a pre-trained AI model (like a Large Language Model) and further training it on a smaller, specific dataset to improve its performance on a particular task or domain.

Hallucination

In AI, hallucination refers to when a model confidently generates information that is factually incorrect, fabricated, or not grounded in its training data. Understanding and mitigating hallucinations is a major focus when deploying LLMs in business settings.

Multimodal AI

Multimodal AI refers to systems that can understand and process multiple types of data at once—such as text, images, audio, and video. For example, a model that can describe a photo, answer questions about it, and generate related text or code.

Retrieval-Augmented Generation (RAG)

Retrieval-Augmented Generation, or RAG, is a technique that improves Large Language Models by first retrieving relevant information from external sources (like documents or databases) and then using that information to generate more accurate, up-to-date, and factual responses.

AI Agent

An AI Agent is an autonomous system that can perceive its environment, make decisions, and take actions to achieve specific goals. Unlike simple chatbots, agents can plan steps, use tools, and handle multi-step tasks with minimal human supervision.

Bias (in AI)

AI Bias occurs when a model produces unfair, skewed, or prejudiced results due to flaws in the training data or algorithm design. Addressing bias is essential for building trustworthy and ethical AI systems, especially in hiring, lending, or decision-making applications.

Context Window

The Context Window is the maximum amount of information (measured in tokens) that an AI model can consider at one time when generating a response. A larger context window allows the model to handle longer conversations, documents, or complex instructions without losing track.

Reinforcement Learning

Reinforcement Learning is a type of Machine Learning where an AI learns by interacting with an environment, receiving rewards for good actions and penalties for bad ones. It’s commonly used in robotics, game-playing AI, and optimizing processes like recommendation systems.

Overfitting

Overfitting happens when a Machine Learning model learns the training data too well—including noise and specific quirks—making it perform poorly on new, unseen data. Avoiding overfitting is key to building models that generalize effectively in real-world use.

Explainable AI (XAI)

Explainable AI focuses on making AI decisions transparent and understandable to humans. Instead of a “black box” that gives answers without justification, XAI techniques help show why a model made a particular prediction or recommendation.

Token

A Token is the basic unit of text that AI language models process. It can be a word, part of a word, or even a punctuation mark. The number of tokens affects cost, speed, and how much information fits in a model’s context window.

Model Drift

Model Drift refers to the gradual decline in an AI model’s performance over time because the real-world data it encounters changes from the data it was trained on. Regular monitoring and retraining help prevent drift in production systems.