1,686 technical terms and definitions
dynamic shape batching and inference latency prediction, dynamic shape batching, shape batching inference, batching inference latency, inference latency prediction, dynamic shape
Dynamic Shape Batching and Inference Latency Prediction Introduction & Motivation Dynamic Shape Batching and Inference Latency Prediction addresses a central problem in inference…
metrology
Dynamic SIMS is the high-flux primary ion beam mode of Secondary Ion Mass Spectrometry used for depth profiling, where a continuous, high-current primary ion beam (O2^+ or Cs^+)…
robotics
Dynamic SLAM is the localization and mapping paradigm designed for environments containing moving objects, where static-world assumptions no longer hold - it separates dynamic…
Dynamic Sparse Training Introduction & Motivation Dynamic Sparse Training addresses a central problem in reducing the size and cost of compression models: how to Reduce the size…
Dynamic Sparse Training (Extended Study) Introduction & Motivation Dynamic Sparse Training (Extended Study) addresses a central problem in reducing the size and cost…
Dynamic Sparse Training (Extended Study) Introduction & Motivation Dynamic Sparse Training (Extended Study) addresses a central problem in reducing the size and cost…
dynamic switching power prediction, dynamic switching power, switching power prediction, dynamic switching, switching power, power prediction
Dynamic Switching Power Prediction with Machine Learning Introduction & Motivation Dynamic Switching Power Prediction with Machine Learning addresses a central problem in dynamic…
Dynamic Task Prioritization Introduction & Motivation Dynamic Task Prioritization addresses a central problem in multitask learning across several related prediction objectives…
Dynamic Task Prioritization (Extended Study) Introduction & Motivation Dynamic Task Prioritization (Extended Study) addresses a central problem in multitask learning across…
Dynamic Task Prioritization (Extended Study) Introduction & Motivation Dynamic Task Prioritization (Extended Study) addresses a central problem in multitask learning across…
Constrained Dynamic Time Warping and FastDTW Introduction & Motivation Constrained Dynamic Time Warping and FastDTW addresses a central problem in timeseries forecasting…
dynamic time warping (dtw) similarity prediction, dynamic time warping, time warping (dtw), warping (dtw) similarity, (dtw) similarity prediction, dynamic time, time warping
Dynamic Time Warping (DTW) Similarity Prediction with Machine Learning Introduction & Motivation Dynamic Time Warping (DTW) Similarity Prediction with Machine Learning addresses…
optimization
Dynamic Token Pruning is a token pruning approach where the pruning decisions are made dynamically at each layer based on learned criteria — allowing different layers to prune…
Dynamic Treatment Regime Estimation Introduction & Motivation Dynamic Treatment Regime Estimation addresses a central problem in causal inference and {target} analysis: how…
dvs camera, event camera, asynchronous vision sensor, event-based vision, silicon retina camera
Dynamic Vision Sensor (DVS) and Event Cameras are bio-inspired image sensors that output asynchronous per-pixel brightness-change events instead of fixed-rate frames, enabling…
low power chip design, dvfs controller, power management ic, pmic frequency scaling
Dynamic Voltage and Frequency Scaling (DVFS) is the critical active power management technique in modern SoCs and microprocessors that dynamically adjusts the operating voltage…
dynamic voltage frequency scaling, dvfs, design
Dynamic Voltage and Frequency Scaling (DVFS) is the technique of simultaneously adjusting both the supply voltage and clock frequency of a processor or functional block at runtime…
dynamic voltage scaling margin and guard band prediction, dynamic voltage scaling, voltage scaling margin, scaling margin guard, margin guard band, guard band prediction
Dynamic Voltage Scaling Margin and Guard Band Prediction with Machine Learning Introduction & Motivation Dynamic Voltage Scaling Margin and Guard Band Prediction with Machine…
neural architecture
Dynamic Width Networks are neural networks that adaptively select how many channels or neurons are active in each layer for each input — using fewer channels for simple inputs…
Dynamically Expandable Networks DEN via Selective Retraining Introduction & Motivation Dynamically Expandable Networks DEN via Selective Retraining addresses a central problem…
aws nosql, serverless database
DynamoDB is a fully managed NoSQL database by AWS providing microsecond latency and infinite scalability — handling any scale of data and traffic automatically without managing…
DYNOTEARS Dynamic Structure Learning for Time Series Introduction & Motivation DYNOTEARS Dynamic Structure Learning for Time Series addresses a central problem in causal inference…
graph neural networks
DyRep is a dynamic graph representation model that separates structural and communication events. - It jointly learns long-term network evolution and short-term interaction…
graph neural networks
DySAT is a dynamic-graph attention model that uses temporal and structural self-attention - Separate attention layers capture within-snapshot structure and across-time evolution…
defect induced leakage current trap assisted tunneling, defect concentration implant damage residual
Every ion that implants into silicon also smashes atoms out of their lattice sites along the way — and the damage that doesn't fully anneal out leaves behind deep-level defects…
nucleation growth precipitation kinetics cluster formation
Push implant dose past the solid solubility limit (see our activation-limits article), and the excess dopant doesn't just sit around inertly — it actively clusters together during…
laser scanning, surface particle scanner, defect inspection
Spectroscopic ellipsometry and inline optical wafer metrology constitute the non-destructive physical measurement and defect detection disciplines that govern yield control across…
dsp, digital signal processor, signal processing, mixed signal verification
Digital signal processing is the numerical manipulation of sampled signals to filter, transform, detect, compress, modulate, or reconstruct information. Every layer of an AI…
plasma etching, RIE, reactive ion etching, ICP etching, plasma physics and etching
Dry etching is the Coburn–Winters synergy: ion bombardment perpendicular to the wafer surface enhances the chemical etch rate of silicon in XeF from 1 nm/min to 55 nm/min — a 9.2…
ai data center, hyperscale data center, gpu cluster infrastructure, liquid cooling
A data center is the physical and operational system that turns electrical power, network connectivity, and cooling capacity into dependable computing. For artificial…
dps etch chamber, plasma density vs ion bombardment energy, dual rf source etch, icp etch tool architecture, plasma etch tool design
A decoupled plasma source is the etch-tool architecture that solves a fundamental tension in plasma etching: generating a dense enough plasma to etch efficiently, while…
A decoupling capacitor is a small capacitor placed physically close to a chip's power pins that acts as a local reservoir of charge, supplying the sudden bursts of current…
A die shrink is the process of re-implementing an existing chip design on a smaller, more advanced manufacturing process node, reducing the physical size of the chip while…
A duplexer is a component that allows a radio device to transmit and receive signals simultaneously using a single shared antenna, by separating the outgoing and incoming signals…
Defect density is a measure of how many manufacturing defects occur per unit area of a wafer, used as a key indicator of a fabrication process's health and a critical input…
Dual damascene is an interconnect fabrication technique that etches both a via hole and its overlying metal trench into the insulating layer before a single metal fill, forming…