Technology and the built world

Deduplication-yields-compression equivalence

The deduplication-yields-compression equivalence is the theoretical claim that removing duplicate documents from a language-model training corpus is lossless compression, since minimizing log-loss equals minimizing encoding bits.

Deep active learning

Deep active learning trains deep neural networks with fewer labeled examples by letting the model choose which unlabeled samples a human annotator should label next, in repeated pool-based rounds.

Deep belief network

A deep belief network (DBN), or deep belief net, is a generative neural network with many layers of hidden variables, introduced by Hinton, Osindero, and Teh in 2006.

Deep borehole disposal

Deep borehole disposal is a concept for disposing of radioactive waste in boreholes drilled several kilometers into crystalline rock, sealing waste far deeper than mined repositories.

Deep clustering

Deep clustering is a family of machine learning methods that jointly learns a neural network representation and a clustering of unlabeled data, exemplified by Deep Embedded Clustering (DEC).

Deep convolutional GAN

A deep convolutional GAN (DCGAN) is a generative adversarial network built from convolutional layers, introduced by Radford, Metz, and Chintala in 2015 and long the baseline GAN.

Deep Deterministic Policy Gradient

Deep Deterministic Policy Gradient (DDPG) is a model-free, off-policy actor-critic reinforcement learning algorithm for continuous action spaces, introduced in 2015 by Timothy Lillicrap and colleagues at DeepMind.

Deep Discoverer

Deep Discoverer, nicknamed D2, is a 6,000-meter-rated ocean exploration remotely operated vehicle owned by NOAA and operated from the ship Okeanos Explorer since 2013 alongside the camera sled Seirios.

Deep drawing

Deep drawing is a sheet metal forming process in which a punch presses a flat blank into a die to form a hollow body such as a cup or sink.

Deep energy retrofit

A deep energy retrofit (DER) is a whole-building renovation that cuts a building's energy use far more than a conventional retrofit, often by more than 50 percent.

Deep ensembles

A deep ensemble is a set of independently trained neural networks whose averaged predictions provide uncertainty estimates, introduced by Lakshminarayanan and colleagues at DeepMind in 2016.

Oct 22, 2026

Deep eutectic solvents for PET depolymerization

Deep eutectic solvents for PET depolymerization are mixtures of a hydrogen-bond donor and acceptor, typically choline chloride with urea or an alcohol, that act as both solvent and catalyst to break PET into monomers.

Deep excavation support systems

Deep excavation support systems combine retaining walls, such as sheet piles, secant piles, and diaphragm walls, with bracing, tiebacks, or floor slabs to stabilize deep cuts and protect adjacent structures.

Deep fryer

A deep fryer is a kitchen appliance that cooks food submerged in hot oil, typically at 150 to 200 °C, from countertop units to industrial lines.

Deep generative model

A deep generative model is a neural network method that learns the probability distribution of training data and draws new samples resembling it, including GANs, VAEs, and diffusion models.

Deep geological repository

A deep geological repository is an underground facility, typically several hundred meters deep, for permanent disposal of spent nuclear fuel and high-level waste using engineered and natural barriers, with Finland's Onkalo the first operating one.

Deep Glider

The Deepglider is an autonomous underwater glider from the University of Washington that profiles the ocean from the surface to 6,000 meters using buoyancy rather than a propeller.

Deep hashing

Deep hashing is a machine learning method that trains a deep neural network to map inputs, typically images, to compact binary codes for fast similarity search.

Deep Heat Mining Basel

Deep Heat Mining Basel was a Swiss enhanced geothermal project beneath Basel, abandoned in 2009 after induced earthquakes, including a magnitude 3.4 event in December 2006.

Deep hole drilling

Deep hole drilling is a machining process for holes whose depth greatly exceeds their diameter, using self-piloting tools and high-pressure coolant; its variants include gun drilling, BTA, and ejector drilling.

Deep Impact (spacecraft)

Deep Impact was a NASA spacecraft that deliberately struck comet Tempel 1 on July 4, 2005, the first impact with a comet's nucleus, and later flew by Hartley 2.

Sep 21, 2026

Deep Jariwala

Deep Jariwala is an American-based materials scientist and electrical engineer, a University of Pennsylvania professor known for 2D semiconductors and AlScN ferroelectric memory who joins Oak Ridge in 2027.

Deep knowledge tracing

Deep knowledge tracing (DKT) is a machine learning method, reported by Chris Piech and colleagues in 2015, that uses a recurrent neural network to model a student's evolving knowledge state.

Deep learning

Deep learning is a subset of machine learning using multi-layer neural networks that learn patterns from data without hand-programmed features, powering speech and image recognition.

Deep learning channel estimation

Deep learning channel estimation is the use of neural networks to infer the state of a wireless radio channel, emerging as a research field in the late 2010s.

Deep learning speech synthesis

Deep learning speech synthesis generates spoken audio from text using neural networks, replacing rule-based and concatenative methods and producing speech nearly indistinguishable from human speech, including zero-shot voice cloning.

Deep learning super sampling

Deep learning super sampling (Nvidia DLSS) is an Nvidia AI technology that raises game frame rates by reconstructing high-resolution images from fewer rendered pixels on RTX GPUs.

Deep learning-based CSI feedback

Deep learning-based CSI feedback uses a neural network at the phone to compress channel state information and one at the base station to reconstruct it, cutting FDD massive MIMO feedback overhead.

Deep learning-based defect detection

Deep learning-based defect detection uses deep neural networks to find, localize, and classify defects in industrial products from image or sensor data, replacing hand-crafted image-processing inspection.