Artificial intelligence and data

Discrete phase model

The discrete phase model (DPM) is an Euler–Lagrange method in computational fluid dynamics that tracks particles, droplets, or bubbles through a continuous carrier fluid in dilute flows.

Discrete sine transform

The discrete sine transform (DST) is a family of invertible linear transforms expressing a sequence as a sum of sines, the odd-symmetry counterpart of the discrete cosine transform.

Discrete-time Fourier transform

The discrete-time Fourier transform (DTFT) maps a discrete-time sequence to a continuous, periodic function of frequency; the DFT samples it at finitely many frequencies, computed efficiently by the FFT.

Discriminative model

A discriminative model is a machine learning model that learns a direct mapping from input features to output labels, the conditional probability p(y|x), with examples like logistic regression, support vector machines, and neural network classifiers.

Disentangled representation learning

Disentangled representation learning trains generative or self-supervised models so each latent variable responds to a single underlying factor of variation, a goal popularized by Bengio, Courville, and Vincent in 2013.

Disjoint-set data structure

The disjoint-set data structure, also called union-find, maintains a partition of elements into disjoint subsets; with union by rank and path compression, each operation runs in effectively constant amortized time.

Disk encryption theory

As a branch of cryptography, Disk encryption theory studies encryptable storage sectors under the constraint that ciphertext must match plaintext size, shaping FDE modes and security definitions.

DiskANN

DiskANN is a family of disk-based approximate nearest-neighbor search algorithms developed at Microsoft Research, able to index and search a billion vectors on a single workstation.

Disposition Matrix

The Disposition Matrix is a US government database, first reported in 2012, that catalogs terrorism suspects and the plans to track, capture, or kill them.

Distance transform

The distance transform assigns each point of a binary image the distance to the nearest object pixel, under metrics like Euclidean or city-block, supporting skeletonization, segmentation, and path planning.

Distant supervision

Distant supervision is a technique for automatically labeling training data by aligning a knowledge base with an unlabeled corpus, introduced for relation extraction by Mintz et al. at Stanford in 2009.

DistilBERT

DistilBERT is a smaller, faster version of the BERT language model, introduced in October 2019 by Hugging Face using knowledge distillation during pre-training rather than task-specific compression.

Distributed AI Research Institute

The Distributed AI Research Institute (DAIR) is an independent, globally distributed nonprofit AI research institute founded by Timnit Gebru in December 2021 to study the harms of AI systems, free from big tech funding.

Distributed computing

Distributed computing is a system in which components on networked computers communicate and coordinate by passing messages, letting independent nodes share work and cooperate toward a common result.

Distributed constraint optimization

Distributed constraint optimization (DCOP) is a framework for multi-agent cooperation where agents control parts of a problem's variables and communicate by message passing to optimize a global objective.

Distributed federated learning over wireless

Distributed federated learning over wireless trains a shared machine learning model across edge devices, with over-the-air (OTA) aggregation letting many devices transmit simultaneously on the same spectrum.

Distributed hash table

A distributed hash table (DHT) is a distributed system storing key-value pairs across peer nodes, where any node can efficiently retrieve the value for a given key.

Distributed ledger

A distributed ledger, also known as decentralized ledger technology (DLT), is a transaction record replicated across a network of computers and updated by consensus, not a central administrator.

Distributed source coding

Distributed source coding is a family of compression techniques in which encoders compress correlated sources independently and a joint decoder exploits the correlation, with no loss versus joint encoding per Slepian and Wolf.

Distributed state estimation

Distributed state estimation is a method where networked sensors cooperatively estimate a system's state by exchanging information with neighbors, used in smart grids and target tracking.

Distributed training of deep neural networks

Distributed training of deep neural networks is the set of parallelism techniques, data, tensor, pipeline, and sharded, used to train one model across thousands of GPUs at once.

Distributed transaction

A distributed transaction is a unit of work spanning two or more independent resource managers, such as databases or microservices, that must commit or roll back as a whole.

Distribution regression

Distribution regression is a supervised learning method that predicts a scalar or vector output from a probability distribution, known only through a bag of drawn samples.

Distribution shift

Distribution shift, also known as dataset shift, is the situation in machine learning where test data differ statistically from the data a model was trained on.

Distributional hypothesis

The distributional hypothesis is the linguistic claim, stated by Zellig Harris in 1954, that words occurring in the same contexts tend to have similar meanings, underlying word embeddings in NLP.

Distributionally robust optimization

Distributionally robust optimization (DRO) is a decision-making framework for uncertainty in which the probability distribution itself is unknown, so decisions perform best under the worst plausible distribution.

Divide-and-conquer algorithm

The divide-and-conquer method solves a problem by recursively breaking it into smaller subproblems, solving them independently, and combining the solutions; merge sort and quicksort are classic examples.

dlib

dlib is a portable C++ toolkit of machine learning algorithms with Python bindings, created by Davis King and best known for face detection and face recognition components.

GeneralOct 26, 2026

dlt

dlt (data load tool), the dlthub Python ELT library, distinct from Databricks' Delta Live Tables: open-source, Apache 2.0, extract-normalize-load pipelines with schema inference, incremental loading, and warehouse destinations.