Artificial intelligence and data

Laplacian of Gaussian

The Laplacian of Gaussian (LoG) is an image-processing operator that detects edges as zero crossings and blobs by scale-space extrema, key to Marr–Hildreth edge detection and SIFT.

Large language model

A large language model (LLM) is a neural network with over a billion parameters, trained on large text corpora to generate text and answer questions.

Large neighborhood search (LNS) is a metaheuristic for combinatorial optimization that iteratively improves a solution by destroying part of it and repairing it, proposed by Paul Shaw in 1998 for vehicle routing.

Last.fm

Last.fm, also known as AudioScrobbler, is a music website founded in London in 2002 that records what users listen to across streaming services, producing personal charts and music recommendations.

Oct 26, 2026

Late-arriving data

Late-arriving data (late data, out-of-order events): records reaching a pipeline after their event-time window was processed. Handled via watermarks, allowed lateness, lookbacks, and Kimball inferred members; differs from duplicates.

Latent semantic analysis

Latent semantic analysis (LSA), also known as latent semantic indexing, is a natural language processing technique that represents words and documents as vectors derived from term co-occurrence, published in 1990.

Lattice-based cryptography

Lattice-based cryptography (lattice cryptography) is public-key cryptography whose security rests on hard lattice problems, making it resistant to quantum computer attacks; NIST standardized ML-KEM and ML-DSA in 2024.

Layer normalization

Layer normalization is a deep learning technique that standardizes a neural network layer's activations per example, introduced by Jimmy Lei Ba and Geoffrey Hinton in 2016 and widely used in transformers.

Leaky integrate-and-fire model

The leaky integrate-and-fire (LIF) model is a simplified mathematical model of a neuron, proposed by Louis Édouard Lapicque in 1907, that fires when its membrane potential reaches a threshold.

Learned perceptual image patch similarity

Learned perceptual image patch similarity (LPIPS) is an image quality metric proposed by Richard Zhang and colleagues in 2018 that compares images through deep neural network features.

Learned sparse retrieval

Learned sparse retrieval (LSR) is a family of first-stage neural ranking methods that encode queries and documents as sparse, non-negative vectors over a vocabulary-sized space, so learned matching runs on standard inverted indexes built for BM25.

Learning automata

A learning automaton is a stochastic decision-making device that updates action probabilities from a reinforcement signal, a foundation of reinforcement learning introduced by Tsetlin in 1961.

Learning classifier system

A learning classifier system (LCS) is a rule-based evolutionary machine learning method that combines a genetic algorithm with reinforcement or supervised learning, originating with John Holland and refined by Stewart Wilson's 1995 XCS.

Learning to Prompt

Learning to Prompt (L2P) is a continual learning method that trains a frozen pre-trained model on sequential tasks via a learnable prompt pool, introduced in a 2022 CVPR paper.

Learning to rank

Learning to rank, also called machine-learned ranking or learn to rank, is the machine learning task of building a model that sorts documents by their relevance to a query.

Learning vector quantization

Learning vector quantization (LVQ) is a supervised, prototype-based classification algorithm, introduced by Teuvo Kohonen, that assigns each input the label of its nearest prototype vector.

Learning with errors problem

The learning with errors (LWE) problem asks one to recover a secret vector from noisy linear equations modulo an integer, and serves as the central hardness assumption for lattice-based cryptography.

Learning without Forgetting

Learning without Forgetting is a 2016 continual learning method by Zhizhong Li and Derek Hoiem that trains a neural network on new tasks without forgetting old ones.

Least frequently used (cache algorithm)

Least frequently used (LFU) is a cache replacement algorithm that evicts the entry with the lowest access count, used in operating systems, caching libraries, and web proxies.

Least mean squares algorithm

The least mean squares algorithm, introduced by Widrow and Hoff in 1960, is an adaptive filtering method that minimizes mean squared error via stochastic gradient descent.

Least mean squares filter

The least mean squares filter is an adaptive filtering algorithm that adjusts filter weights by stochastic gradient to minimize error, used by the million in echo cancellers and equalizers.

Least-squares support-vector machine

A least-squares support-vector machine (LS-SVM) is a reformulation of the support-vector machine that replaces the hinge loss with squared error, so training reduces to solving a linear system.

Lei Geral de Proteção de Dados

The Lei Geral de Proteção de Dados (LGPD) is Brazil's comprehensive data protection law, regulating personal data processing, signed in 2018 and enforced by the ANPD.

Lemmatization

Lemmatization is the natural language processing task of grouping a word's inflected forms under a single base form, so "builds", "building", and "built" all reduce to "build".

Lempel–Ziv compression

Lempel–Ziv compression is a family of lossless data compression algorithms that replace repeated substrings with references to earlier occurrences, introduced by Ziv and Lempel in 1977.

Lempel–Ziv–Welch

Lempel–Ziv–Welch, or LZW, is a lossless dictionary-based data compression algorithm published by Terry Welch in 1984 and used in GIF, TIFF, PDF, and Unix compress.

LeNet

LeNet is a family of convolutional neural networks from Yann LeCun's team at AT&T Bell Labs for reading handwritten digits, culminating in LeNet-5 in 1998.

Lenna

Lenna, also spelled Lena, is a 512 × 512 digitized photo of Swedish model Lena Forsén that became a standard test image in image processing.

Levenshtein distance

Levenshtein distance, also called edit distance, is a string metric counting the minimum single-symbol insertions, deletions, or substitutions needed to transform one string into another.