Core Concepts

A concept from educational psychology applied to AI, referring to tasks an AI can perform with guidance but not independently.

AI designed and trained for a specific task, lacking the general cognitive abilities of human intelligence.

In machine learning, the amount by which the model's predictions vary from the average prediction, reflecting sensitivity to training data.

A type of machine learning where models learn patterns from unlabeled data, without explicit instructions.

A test of a machine's ability to exhibit intelligent behavior indistinguishable from that of a human.

The smallest unit of processing in NLP, which could be a word, part of a word, or a character, depending on the model.

A machine learning approach where models are trained on labeled data, learning to predict outcomes from inputs.

AI with the ability to understand, learn, and apply knowledge in ways indistinguishable from human intelligence.

A type of machine learning where an agent learns to make decisions by taking actions in an environment to achieve rewards.

The automated recognition of patterns and regularities in data using machine learning algorithms.

A modeling error in machine learning where a model learns the detail and noise in the training data too well.

The ability of AI to understand and interpret human language as it is spoken or written.

The field of AI focused on the interaction between computers and humans through natural language.

Generating coherent and contextually relevant text from structured data using AI.

AI systems that can process and interpret multiple types of data, such as text, images, and sound.

The science of getting computers to act without being explicitly programmed, through learning.

Broad term encompassing the capabilities of machines to learn from data and perform tasks.

Hidden or unobservable variables inferred from observable data in machine learning models.

The underlying purpose or goal that a user aims to achieve through a query or statement.

A parameter whose value is set before the learning process begins, influencing the training phase.

AI systems capable of generating new, original content or data that mimics real-world examples.

Artificial intelligence that exhibits cognitive functions across a wide range of tasks and domains.

AI systems designed to provide insights into their decision-making processes for transparency.

Specific, identifiable elements in text, such as names, places, dates, often extracted by AI.

A subset of machine learning involving neural networks with many layers to analyze data.

A branch of artificial intelligence focused on understanding the algorithms that drive learning.

AI systems designed to mimic human brain functioning, aiming for natural, human-like interaction.

Preconceived notions or predispositions in AI models that can affect decision-making and fairness.

Machines or systems capable of performing tasks and making decisions without human intervention.

Enhancing human decision-making with AI capabilities, focusing on collaboration between humans and AI.

A set of mathematical instructions or rules that a computer follows to perform a specific task efficiently.

The simulation of human intelligence processes by machines, particularly computer systems.