AI Glossary

A-C: Foundations and Core Concepts

Artificial Intelligence (AI)

The simulation of human intelligence in machines programmed to think and learn like humans. AI encompasses a wide range of technologies and approaches designed to enable computers to perform tasks that typically require human intelligence.

Algorithm

A set of step-by-step instructions or rules for solving a specific problem or performing a particular task. In AI, algorithms are the building blocks of intelligent systems.

Artificial General Intelligence (AGI)

Also known as strong AI or broad AI, AGI refers to AI systems capable of performing any intellectual task that a human can. This theoretical form of AI would match or exceed human-level performance across most cognitive tasks.

Automated Machine Learning (AutoML)

A field of machine learning that aims to automate the process of applying machine learning to real-world problems, making AI more accessible to non-experts.

Big Data

Extremely large datasets that can be analyzed computationally to reveal patterns, trends, and associations, especially relating to human behavior and interactions.

Computer Vision

A field of AI that focuses on enabling computers to interpret and understand visual information from the world, such as images and videos.

Convolutional Neural Network (CNN)

A type of deep learning model that processes data with a grid-like topology (e.g., an image) by applying a series of filters. CNNs are often used for image recognition tasks.

D-F: Advanced Techniques and Applications

Deep Learning

A subset of machine learning that uses artificial neural networks with multiple layers (deep neural networks) to learn and make decisions. It’s particularly effective for tasks like image and speech recognition.

Data Augmentation

Techniques used to increase the amount of training data by adding slightly modified copies of existing data or newly created synthetic data.

Explainable AI (XAI)

AI systems designed to be transparent and interpretable, allowing humans to understand how the AI arrives at its decisions or predictions.

Federated Learning

A machine learning technique that trains algorithms across multiple decentralized devices or servers holding local data samples, without exchanging them.

Fuzzy Logic

A form of many-valued logic that deals with reasoning that is approximate rather than fixed and exact, often used in AI systems for handling uncertainty.

G-I: Generative Models and Intelligence

Generative AI

AI systems capable of creating new content, such as text, images, or code, based on patterns learned from existing data. Examples include ChatGPT and DALL-E.

Graph Neural Network (GNN)

A type of neural network designed to work with graph-structured data, useful for tasks involving complex relationships between entities.

Inference

The process by which an AI model generates responses or actions based on input data. It’s the application of learned patterns to new situations.

Intelligent Agent

An autonomous entity which observes through sensors and acts upon an environment using actuators and directs its activity towards achieving goals.

L-N: Language Models and Neural Networks

Large Language Model (LLM)

A type of AI model trained on vast amounts of text data, capable of understanding and generating human-like text. Examples include GPT (Generative Pre-trained Transformer) models.

Machine Learning (ML)

A subset of AI that focuses on the development of algorithms and statistical models that enable computer systems to improve their performance on a specific task through experience.

Natural Language Processing (NLP)

The branch of AI concerned with giving computers the ability to understand, interpret, and generate human language.

Neural Network

A computing system inspired by biological neural networks, consisting of interconnected nodes (artificial neurons) that process and transmit information.

O-R: Optimization and Learning Paradigms

Optical Character Recognition (OCR)

Technology that recognizes and extracts text from images or scanned documents, making them machine-readable and searchable.

Overfitting

A modeling error that occurs when a function is too closely fit to a limited set of data points, resulting in poor performance on unseen data.

Quantum Computing

A form of computing that uses quantum-mechanical phenomena to perform operations on data, potentially revolutionizing AI by solving complex problems much faster than classical computers.

Reinforcement Learning

A type of machine learning where an agent learns to make decisions by taking actions in an environment to maximize a reward signal.

S-U: Specialized AI Techniques

Sentiment Analysis

The use of NLP techniques to determine the emotional tone behind words, used to gain an understanding of attitudes, opinions, and emotions.

Supervised Learning

A type of machine learning where the algorithm is trained on a labeled dataset, learning to map inputs to correct outputs.

Transfer Learning

A machine learning method where a model developed for one task is reused as the starting point for a model on a second task.

Unsupervised Learning

A type of machine learning where the algorithm is given unlabeled data and must find patterns and relationships on its own.

V-Z: Emerging Trends and Future Directions

Virtual Assistant

AI-powered software that can perform tasks or services for an individual based on commands or questions, such as Siri, Alexa, or Google Assistant.

Voice Recognition

The ability of a machine or program to receive and interpret dictation or to understand and carry out spoken commands.

XAI (Explainable AI)

AI systems designed to be transparent and interpretable, allowing humans to understand how the AI arrives at its decisions or predictions.