3,135 articles
Fair clustering
Fair clustering is a family of machine learning algorithms that partition data into clusters while satisfying fairness constraints, such as approximate demographic balance between protected groups.
FAIR data principles
FAIR data principles: Findable, Accessible, Interoperable, Reusable; guidelines from FORCE11's Wilkinson et al. 2016 Scientific Data paper making research data and metadata machine-actionable for reuse, distinct from open data and complemented by CARE principles.
FAIR principles
The FAIR principles are fifteen guidelines for data management, published in 2016, stating that scholarly data should be Findable, Accessible, Interoperable, and Reusable for machines and people.
fairseq
fairseq is an open-source sequence modeling toolkit from Facebook AI Research, first released in 2017 and rewritten in PyTorch, used for machine translation, summarization, and language modeling.
Faiss
Faiss (Facebook AI Similarity Search) is an open-source C++ library with Python wrappers for approximate nearest neighbor search over dense vectors, developed at Meta's FAIR group.
Fake news detection
Fake news detection is the natural language processing task of predicting whether a news article is false or misleading, covering rumor, clickbait, and veracity classification.
Fashion-MNIST
Fashion-MNIST is a machine learning dataset of 70,000 grayscale 28×28 product images from Zalando across 10 clothing categories, released in 2017 as a direct drop-in replacement for MNIST.
FAST corner detection
FAST (Features from Accelerated Segment Test) is a fast corner detector for digital images, introduced by Edward Rosten and Tom Drummond in 2005 for high-performance tracking.
Fast wavelet transform
The fast wavelet transform (FWT), also known as Mallat's algorithm, is a linear-time algorithm that computes the discrete wavelet transform by filtering and downsampling a signal.
FastICA
FastICA is a fast fixed-point algorithm for independent component analysis that recovers independent source signals from linear mixtures, reported by Hyvärinen and Oja in 1997 and widely used in scikit-learn.
FastText
FastText is an open-source library for text classification and word embeddings developed by Facebook AI Research and released in 2016, with accuracy often on par with deep learning classifiers.
FBI Index
The FBI Index, also called the Index List, is the FBI's system of name indexes and target lists connecting people and organizations to FBI case files.
FBI Ten Most Wanted Fugitives
The FBI Ten Most Wanted Fugitives list, also known as the FBI Most Wanted List, is an FBI publicity program started in 1950 that publicizes ten dangerous fugitives.
FBI Ten Most Wanted Fugitives, 2000s
The FBI Ten Most Wanted Fugitives, 2000s covers fugitives placed on the FBI's flagship wanted list between 2000 and 2009, with emphasis on violent crime and terrorism.
FBI Ten Most Wanted Fugitives, 2010s
The FBI Ten Most Wanted Fugitives, 2010s covers the seventh decade of the FBI's publicity program, which named ten fugitives at a time and passed 500 additions in 2013.
FCHL19
FCHL19 is an atom-centered molecular representation for quantum machine learning, introduced in 2019 as a faster revision of FCHL18, encoding atomic environments as discretized two- and three-body distributions.
FCOS
FCOS (Fully Convolutional One-Stage Object Detection) is an anchor-free object detector treating detection as per-pixel prediction, proposed by Zhi Tian, Chunhua Shen, Hao Chen, and Tong He at ICCV 2019.
Feature (machine learning)
A feature in machine learning is an input variable, also called a dimension, used to generate predictions, with feature engineering transforming raw data into useful form.
Feature engineering
Feature engineering is the use of domain knowledge to create features, the input variables machine learning algorithms work on, aiming for a minimal subset that preserves predictive performance.
Feature learning
Feature learning, also called representation learning, is the set of machine learning methods in which a system automatically discovers data representations that make tasks like classification easier.
Feature matching (computer vision)
Feature matching is the computer vision method that establishes correspondences between detected image features across images, feeding object recognition, structure from motion, SLAM, and visual localization.
Feature mode decomposition
Feature mode decomposition (FMD) is an adaptive signal decomposition method, introduced in 2022, that splits vibration signals into modes with distinct center frequencies for machinery fault diagnosis.
Feature pyramid network
A feature pyramid network (FPN) is a computer vision component that builds multi-scale feature maps from one image pass, helping detectors recognize objects of very different sizes.
Feature scaling
Feature scaling is a machine learning preprocessing step that rescales the numeric features of a dataset to comparable ranges, such as zero mean and unit variance, before training a model.
Feature selection
Feature selection, also called variable or input selection, chooses a subset of a dataset's variables for a machine learning model to improve prediction and reduce overfitting.
Feature store
Feature store: a data system for storing, managing, and serving ML features consistently across training and inference. Also called feature platform (Tecton, Feast). Defined by dual offline/online stores, point-in-time correctness, and prevention of training-serving skew; emerged with Uber's Michelangelo in 2017.
Featureform
Featureform: open-source virtual feature store for machine learning, founded January 2021 by Simba Khadder and Shabnam Mokhtarani in San Francisco (formerly StreamSQL). MPL-2.0 licensed; orchestrates existing data infrastructure. Acquired by Redis October 2025, now Redis Feature Form.
Feder–Vardi theorem
The Feder–Vardi theorem states that every fixed-template constraint satisfaction problem is solvable in polynomial time or is NP-complete, proved in 2017 by Bulatov and Zhuk.
Federated averaging
Federated averaging (FedAvg) is a distributed machine learning algorithm, reported by McMahan and colleagues in 2016, in which a server averages locally trained models from clients holding private data.
Federated learning
Federated learning (FL) is a distributed machine learning method, named by McMahan and colleagues at Google in 2017, in which clients train a shared model locally and exchange only model updates.