Artificial intelligence and data

Federated meta-learning

Federated meta-learning is a machine learning approach combining federated learning with meta-learning, so a shared model learned without exchanging raw data adapts to each client with a few local gradient steps.

Federated multi-task learning

Federated multi-task learning (FMTL) is a distributed machine learning approach in which multiple clients jointly train models for related but distinct tasks while keeping their data local.

Federated transfer learning

Federated transfer learning (FTL) is a machine learning approach combining federated and transfer learning, letting parties train models across different domains without exchanging raw data.

Feedback optimization

Feedback optimization is a control method that adjusts a system's decision variables in real time from noisy measurements, driving it to the solution of an optimization problem.

Feedforward neural network

A feedforward neural network, also called a feedforward network or multilayer perceptron (MLP), is a machine learning model with layered functions connected in one direction and no feedback.

Few-shot class-incremental learning

Few-shot class-incremental learning (FSCIL) is a machine learning setting in which a model trained on base classes must learn new classes from few examples without forgetting.

Few-shot learning

Few-shot learning is a machine learning approach in which a model learns a new task from a few labeled examples, often by transferring knowledge from related tasks.

Few-shot object detection

Few-shot object detection (FSOD) is a machine learning task in which a detector recognizes and localizes objects of novel classes from only a small number of labeled examples.

Fibonacci heap

A Fibonacci heap, also called an F-heap or fib heap, is a data structure for priority queues, invented by Michael Fredman and Robert Tarjan in 1984 and published in 1987.

FidelityFX Super Resolution

FidelityFX Super Resolution (FSR) is a family of AMD upscaling technologies for Radeon graphics that render games at lower resolution and reconstruct them, adding frame generation in FSR 3 (2023).

FIFO (computing)

FIFO, first-in-first-out, is a queue discipline in which the first item added is the first removed, used in router buffers, CPU scheduling, and concurrent queues.

Filter bubble

A filter bubble, or informational bubble, is a state in which algorithmic personalization of online content isolates users from disagreeing material, coined by Eli Pariser in 2011.

Filtered back projection

Filtered back projection (FBP) is a tomographic reconstruction algorithm that filters each projection with a ramp and back-projects it into a cross-sectional image, long the standard method in CT.

Findings of the Association for Computational Linguistics

Findings of the Association for Computational Linguistics, commonly Findings of ACL, is a companion proceedings series of the Association for Computational Linguistics, first published with EMNLP 2020.

Fine-grained complexity

Fine-grained complexity is the area of theoretical computer science that proves conditional lower bounds based on the Strong Exponential Time Hypothesis (SETH) and similar conjectures such as 3-SUM and APSP.

Fine-tuning (deep learning)

Fine-tuning is the process of continuing the training of a pretrained machine learning model on task-specific data, including methods like LoRA that update only a small fraction of parameters.

Fingerprint recognition

Fingerprint recognition is a biometric method that matches a finger's friction-ridge pattern against stored templates, either to verify a claimed identity or to search a database.

Finite model theory

Finite model theory is the branch of mathematical logic studying the expressive power of logical languages over finite structures, with applications in databases, complexity theory, and formal languages.

Finite-state machine

A finite-state machine (FSM), also called a finite-state automaton, is an abstract mathematical model of computation with a finite set of states and a transition function.

Finite-state transducer

A finite-state transducer (FST) is a finite-state machine that reads an input string and emits an output string, widely used in computational linguistics, speech recognition, and text processing.

FIPA

FIPA, the Foundation for Intelligent Physical Agents, is a standards organization founded in Geneva in 1996, best known for its agent communication language, FIPA ACL.

Fire Information for Resource Management System

The Fire Information for Resource Management System (FIRMS) is a NASA web platform delivering near real-time satellite fire and hotspot detections globally within 3 hours of observation.

Firefly algorithm

The firefly algorithm is a nature-inspired metaheuristic introduced by Xin-She Yang in 2009 that solves continuous, discrete, and multiobjective optimization problems by simulating fireflies attracted to brighter candidates.

First normal form

First normal form (1NF) is the most basic level of database normalization: a relation qualifies when every column holds one atomic value, with no repeating groups.

Fisher–Yates shuffle

The Fisher–Yates shuffle, also called the Knuth shuffle, is an algorithm that randomly permutes a sequence so every ordering is equally likely, running in place in linear time.

GeneralOct 26, 2026

Fivetran

Fivetran (Fivetran + dbt Labs) is an Oakland, California-based managed ELT data movement platform with 700+ connectors, usage-based MAR pricing, and a 2021 $5.6B valuation; it completed an all-stock merger with dbt Labs in June 2026 at roughly $600M ARR.