AI Glossary

AI is a complex topic and is a subject with many specialised terms and names. In the glossary below you'll find some of the more common ones you're likely to come across.

A

Agent: A system or program that perceives its environment, makes decisions, and takes actions to achieve specific goals. AI agents can range from simple programs, like a chatbot responding to questions, to complex systems, like autonomous vehicles navigating through traffic.

Algorithm: A set of rules or instructions a computer follows to perform a task or solve a problem.

Artificial General Intelligence (AGI): A theoretical form of AI that possesses the ability to understand, learn, and apply knowledge across a wide range of tasks, similar to human intelligence.

Artificial Intelligence (AI): The capability of machines to perform tasks that typically require human intelligence, such as understanding language, recognizing patterns, and making decisions.

B

Bias: In AI, bias refers to systematic errors that can lead to unfair outcomes, often arising from prejudices in the training data.

C

Compute: The processing power and resources required to perform calculations or run algorithms, often in the context of machines or systems. In AI, "compute" typically refers to the computational resources needed to train models, make predictions, or analyze data, often measured in terms of processing units (like CPUs or GPUs) and time.

Machine Learning (ML): A subset of AI where computers learn from data to improve their performance on tasks without being explicitly programmed.

D

Data Catalog: A collection of metadata, combined with data management and search tools, that helps analysts and other data users to find the data that they need, serves as an inventory of available data, and provides information to evaluate fitness of data for intended uses.

Data Mining: The process of discovering patterns, correlations, and insights from large datasets using statistical and computational techniques.

Deep Learning: A branch of ML that uses neural networks with many layers to analyze various types of data, including images, text, and sounds.

F

Feature Extraction: The process of transforming raw data into a set of characteristics that can be effectively used in modelling.

H

Hyperparameter: Settings in ML algorithms that are configured before training and influence the learning process, such as the learning rate or the number of layers in a neural network.

M

Model: A mathematical representation trained on data to make predictions or decisions without explicit programming for the task.

N

Natural Language Processing (NLP): The field of AI focused on enabling machines to understand, interpret, and generate human language.

Neural Network: A computational model inspired by the human brain's network of neurons, designed to recognize patterns and relationships in data.

O

Overfitting: A modeling error in ML where a model learns not only the underlying patterns in the training data but also the noise, leading to poor performance on new, unseen data.

R

Reinforcement Learning: A type of ML where an agent learns to make decisions by performing actions and receiving rewards or penalties, aiming to maximize cumulative rewards.

S

Supervised Learning: An ML approach where models are trained on labeled data, meaning each input comes with the correct output, allowing the model to learn the relationship between them.

T

Testing Data: A separate dataset used to evaluate the performance and generalization capability of an ML model after training.

Training Data: The dataset used to teach an ML model, allowing it to learn patterns and make predictions.

U

Underfitting: A scenario where a model is too simple to capture the underlying structure of the data, resulting in poor performance on both training and new data.

Unsupervised Learning: An ML approach where models find patterns or groupings in data without labelled responses, identifying structures like clusters or associations.

V

Variance: The extent to which a model's predictions vary for different datasets; high variance can lead to overfitting.