Technical concepts used to build, connect and retrieve information for AI systems.
A standardized test or dataset used to objectively measure and compare the capabilities of different AI models.
A set of rules that allows different software applications to communicate with each other.
A field of AI that enables computers to derive meaningful information from digital images and videos.
A mathematical measure used to determine how similar two vectors are, often used to compare the semantic meaning of text.
A mathematical representation of data designed so that related meanings can be compared computationally.
The process of adapting a pre-trained AI model to a specific task or style by training it further on a specialized dataset.
A network of real-world entities and the relationships between them, used to store complex factual information.
A technique where a smaller student AI model is trained to mimic the behavior and outputs of a larger, more capable teacher model.
A technique to reduce the memory size and computational cost of an AI model by using lower numerical precision.
A branch of AI focused on giving computers the ability to understand text and spoken words.
A technique that grounds AI responses in facts by retrieving relevant information from external sources before generating text.
A search technique that attempts to find results based on meaning and context rather than only exact keyword matches.
Artificially generated information designed to resemble or represent the properties of real-world data.
A machine learning technique where knowledge gained while solving one task is applied to a different but related task.
A specialized database designed to store and rapidly search high-dimensional embeddings.