Artificial intelligence and data

Guided filter

The guided filter is an edge-preserving image smoothing filter that transfers structure from a guidance image and runs in linear time, introduced by Kaiming He and colleagues in 2010.

Guided filtering

Guided filtering is an edge-preserving image filter, introduced by Kaiming He and colleagues in 2010, that transfers a guidance image's structures to a smoothed output in linear time.

Gynoid

A gynoid, also known as a fembot, is a robot or android with female characteristics, a term coined by Isaac Asimov in 1979 from the Greek for woman.

Hadoop: The Definitive Guide is Tom White's O'Reilly book on Apache Hadoop (HDFS, MapReduce, Pig, Hive, HBase, ZooKeeper, Sqoop), published in four editions from June 2009 to April 2015, tracking Hadoop 0.20 through Hadoop 2 and YARN.

Oct 15, 2026

Hailo-8

The Hailo-8 is an edge AI accelerator from Hailo Technologies of Tel Aviv, announced in 2019, delivering up to 26 TOPS at 2.5 W for local deep learning.

Hamiltonian path

A Hamiltonian path, also called a Hamilton path, is a path in a graph that visits each vertex exactly once. The problem of finding one is NP-complete.

Hamiltonian path problem

The Hamiltonian path problem asks whether a graph contains a simple path visiting every vertex exactly once, a classical NP-complete problem in Karp's 1972 list.

Handwriting recognition

Handwriting recognition is a machine learning and computer vision method that converts handwritten text in images or pen recordings into machine-readable text, used for historical documents, forms, and prescriptions.

Hard negative mining

Hard negative mining is a machine learning training technique that selects the negative examples a model currently scores wrongly or highly, such as background windows causing false alarms, and trains on those.

Hardware random number generator

A hardware random number generator (HWRNG) is a physical device or circuit, typically built into a processor, that produces random bits from unpredictable physical processes like thermal noise.

Hardware-aware neural architecture search

Hardware-aware neural architecture search (HW-NAS) is a machine learning method that searches for neural network architectures while including hardware metrics such as latency, energy, or memory footprint in the objective.

Harmony search

Harmony search, also known as the harmony search algorithm, is a population-based metaheuristic optimization algorithm introduced in 2001, inspired by musical improvisation and applied to engineering design, scheduling, and machine learning tuning.

Hash function

A hash function, also called a hashing function, maps data of arbitrary size to a fixed-size output used in hash tables, digital signatures, and password storage.

Hash table

A hash table, also called a hash map or scatter storage, is a data structure that maps keys to array positions for fast lookup, insertion, and deletion.

Oct 15, 2026

Hate speech detection

Hate speech detection is a natural language processing task that identifies language attacking people based on identity factors such as race or religion, used mainly for social media content moderation.

Hatsune Miku

Hatsune Miku (初音ミク) is a Japanese VOCALOID voice synthesizer and virtual singer released in 2007 by Crypton Future Media, built from voice actress Saki Fujita's samples.

Have I Been Pwned?

Have I Been Pwned? (HIBP) is a free website created by security researcher Troy Hunt that checks whether your email address or passwords have appeared in known data breaches.

Hawk-Eye

Hawk-Eye is a multi-camera ball-tracking system developed in the United Kingdom and owned by Sony since 2011, used for officiating, broadcast graphics, and performance data in sports including tennis, cricket, football, and baseball.

HDBSCAN

HDBSCAN, short for Hierarchical Density-Based Spatial Clustering of Applications with Noise, is a clustering algorithm that finds clusters of varying densities and labels leftover points as noise.

HDF5

HDF5 (Hierarchical Data Format version 5) is a data model, C library, and self-describing file format (.h5/.hdf5) for scientific data, developed by The HDF Group; groups, datasets, no size limits, netCDF-4 builds on it.

Head-driven phrase structure grammar

Head-driven phrase structure grammar (HPSG) is a lexicalist, unification-based theory of syntax introduced by Carl Pollard and Ivan Sag in 1987, where most grammatical information is carried by lexical entries.

Headless data architecture

Headless data architecture decouples data ownership, business rules, and APIs from the applications that consume them, using a shared stream (Kafka) and table (Iceberg) layer with pluggable processing heads; distinct from headless CMS and data lakes.

Health informatics

Health informatics, also called medical or clinical informatics, is the interdisciplinary field applying computer and information science to health data, aiming to improve human health and care delivery.

Heap (data structure)

A heap is a tree-based data structure satisfying the heap property, so the smallest or largest element sits at the root; the binary heap underlies priority queues and heapsort.

Heapsort

Heapsort is a comparison-based sorting algorithm that arranges the input as a binary heap and repeatedly extracts the largest element, sorting in place in O(n log n) worst-case time.

Oct 15, 2026

Hesitant fuzzy sets

A hesitant fuzzy set assigns each element a set of possible membership degrees instead of one, letting evaluators express hesitation. Vicenç Torra introduced it in 2009.

Heterogeneous graph attention network

The heterogeneous graph attention network (HAN) is a graph neural network architecture, introduced by Xiao Wang and colleagues in 2019, that learns node representations from heterogeneous graphs.

Heterogeneous graph neural network

A heterogeneous graph neural network (HGNN) is a graph neural network extended to graphs with multiple node and edge types, applied to knowledge graphs, citation networks, and recommendation.

Heuristic (computer science)

A heuristic in computer science is a technique that solves problems faster or more simply than complete methods, using rules of thumb at the price of no optimality guarantee.