All key artificial intelligence terms explained simply. Each definition links to related AI tools.
The simulation of human intelligence processes by computer systems, including learning, reasoning, and self-correction.
A field of AI that enables computers to interpret and understand visual information from the world.
A subset of machine learning using neural networks with multiple layers to model complex patterns in data.
AI systems that can create new content including text, images, audio, video, and code.
A subset of AI where systems learn and improve from experience without being explicitly programmed.
A computing system inspired by biological neural networks, consisting of interconnected nodes that process information.
A field of AI focused on the interaction between computers and human language.
A type of machine learning where the model is trained on labeled data with known input-output pairs.
A type of machine learning where the model finds patterns in data without labeled examples.
A neural network architecture designed to process grid-like data such as images using convolutional filters.
A generative AI model that creates data by learning to reverse a gradual noising process.
A large AI model trained on broad data that can be adapted to a wide range of downstream tasks.
A pair of neural networks (generator and discriminator) that compete to produce increasingly realistic outputs.
A family of large language models developed by OpenAI that generate human-like text using transformer architecture.
A neural network trained on massive text datasets, capable of understanding and generating human-like text.
AI systems that can process and generate multiple types of data such as text, images, audio, and video.
AI models and tools whose source code and/or weights are freely available for use, modification, and distribution.
A technique that allows neural networks to focus on relevant parts of the input when producing output.
A prompting technique that encourages AI models to break down complex problems into step-by-step reasoning.
A numerical representation of data (text, images) in a continuous vector space where similar items are close together.
A technique where an AI model learns to perform a task from only a few examples provided in the prompt.
The process of further training a pre-trained AI model on a specific dataset to adapt it for a particular task.
An efficient fine-tuning technique that adapts large models by training only small, low-rank matrices.
The practice of crafting effective inputs (prompts) to guide AI models toward desired outputs.
A technique that reduces model size and memory usage by using lower-precision numbers for model weights.
A technique that combines information retrieval with text generation to produce more accurate and grounded AI responses.
A type of machine learning where an agent learns to make decisions by receiving rewards or penalties for its actions.
A training technique that uses human preferences to fine-tune AI models for more helpful and safe outputs.
The process of breaking text into smaller units (tokens) that an AI model can process.
A technique where a model trained on one task is reused as the starting point for a model on a different task.
A neural network architecture based on self-attention mechanisms, foundational to modern NLP and generative AI.
A technique where an AI model performs a task it was not explicitly trained on, without any examples.
AI systems designed to autonomously plan, reason, and execute multi-step tasks with minimal human intervention.
An autonomous AI system that can perceive its environment, make decisions, and take actions to achieve specific goals.
An AI assistant embedded in a workflow or application that augments human productivity by suggesting actions.
An AI-powered software application designed to simulate human conversation through text or voice interactions.
AI systems that automatically write, complete, or suggest programming code from natural language or partial code.
The use of AI to create new images from text prompts, sketches, or other images.
A search technique that understands the meaning and context of queries rather than just matching keywords.
An NLP technique that identifies and extracts subjective information (positive, negative, neutral) from text.
AI technology that converts spoken audio into written text, also known as automatic speech recognition.
AI technology that generates images from natural language text descriptions.
AI technology that converts written text into natural-sounding spoken audio.
A set of protocols that allows different software applications to communicate with AI models and services.
The maximum amount of text (measured in tokens) that an AI model can process in a single interaction.
A specialized processor originally designed for graphics but now essential for training and running AI models.
The process of using a trained AI model to make predictions or generate outputs on new data.
A database optimized for storing and querying high-dimensional vector embeddings for similarity search.
A hypothetical AI system with human-level cognitive abilities across all intellectual tasks.
The challenge of ensuring AI systems behave in accordance with human values and intentions.
Systematic errors in AI outputs that reflect prejudices present in training data or model design.
When an AI model generates confident but factually incorrect or fabricated information.