Glossary
Searchable terminology from accessibility, web standards, and related fields.
80 results found in Machine Learning.
- 3D Gaussian Splatting (3DGS, Gaussian Splatting)
- An explicit 3D scene representation, introduced by Kerbl et al. in 2023, in which a scene is modelled as a cloud of anisotropic 3D Gaussians whose positions, shapes, colours, and opacities are optimis…
- AI contestability (Algorithmic contestability, AI contestation)
- The principle that users should be able to challenge, question, and seek recourse against decisions or outputs made by AI systems. In accessibility contexts, contestability is particularly important f…
- Acoustic Activity Recognition (Sound Activity Recognition, Audio Activity Recognition, Environmental Sound Recognition)
- The use of microphones and machine learning to automatically identify and classify sounds occurring in an environment, such as doorbells, alarms, appliances, speech, and other everyday acoustic events…
- Acoustic Event Detection (Sound Event Detection, Audio Event Detection, Sound Event Classification)
- The automated process of identifying and classifying specific sounds within an audio stream, such as recognizing a phone ringing, door knocking, fire alarm, or speech from continuous environmental aud…
- Acoustic Model (AM)
- An acoustic model is the component of an automatic speech recognition (ASR) system that maps short segments of audio (typically 10–25 ms frames of spectral features) to the linguistic units that produ…
- Adaptive Boosting (AdaBoost)
- A machine learning ensemble method that combines multiple weak classifiers to create a strong classifier, with each successive classifier focusing on the examples that previous classifiers misclassifi…
- App Review Mining (App Store Review Analysis, User Review Mining)
- The process of systematically extracting, classifying, and analyzing user reviews from app stores such as Google Play and the Apple App Store to identify patterns, issues, and feature requests. In acc…
- Attention Mechanism (Attention)
- A technique in neural networks that allows models to focus on relevant parts of the input when generating each part of the output, rather than relying solely on a fixed-length context vector. In seque…
- Automatic text simplification (ATS, Text simplification, Automated readability improvement)
- The use of natural language processing techniques to transform complex text into simpler, more readable versions while preserving meaning. ATS operates at two levels: lexical simplification (replacing…
- BLEU Score (BiLingual Evaluation Understudy, BLEU)
- A metric for evaluating the quality of machine-generated text by comparing it to one or more reference (human-written) translations. BLEU calculates precision by counting how many n-grams (sequences o…
- Black Box Model (Opaque Model)
- A machine-learning model whose internal workings are not directly inspectable or interpretable by a human, either because the model is architecturally complex (deep neural networks, large language mod…
- Calibration-Free Interface (Zero-Shot Interface, Plug-and-Play Interface, Cross-User Model)
- An input system that works for a new user without any per-user training or calibration data, typically by relying on models trained on large multi-user datasets that capture enough physiological and b…
- Camera-based assistive technology (Camera-based AT, Vision-based AT, VBAT)
- Assistive technologies that use cameras (typically smartphone cameras or smart glasses) combined with computer vision and AI to provide visual information to blind and low-vision users. Applications i…
- Chain-of-Thought (CoT, Chain of Thought Reasoning, Step-by-Step Reasoning)
- Chain-of-thought is a prompting and model-design technique in which a large language model produces its intermediate reasoning steps before giving a final answer. Modern reasoning models (e.g., OpenAI…
- Clustering Algorithm (Cluster Analysis, Unsupervised Clustering, K-means, PAM, CLARA)
- A clustering algorithm is an unsupervised machine-learning technique that groups similar data points together based on a distance or similarity measure, without needing pre-labelled training data. Com…
- Confidence score (Certainty score, Prediction confidence)
- A numerical value (typically 0-100% or 0-1) indicating how certain an AI system is about its prediction or classification. In accessibility contexts, communicating confidence scores to users — particu…
- Constitutional AI (CAI)
- A training method introduced by Anthropic in 2022 in which a large language model is aligned to a written set of principles (a 'constitution') through self-critique and reinforcement learning from AI …
- Continual Learning (Continuous Learning, Lifelong Learning, Never-ending Learning)
- A machine learning paradigm in which models learn incrementally from new data over time while retaining previously acquired knowledge, rather than being trained once on a fixed dataset. Continual lear…
- Convolutional Neural Network (CNN, ConvNet)
- A class of deep neural network that uses convolutional filters to automatically extract spatial features from data, originally designed for image processing but now widely applied to sensor data, audi…
- Counterfactual Explanation (Counterfactual XAI)
- An explanation technique that communicates what minimal change to the input would have produced a different output from an AI model, for example 'if the applicant's income had been $5,000 higher, the …