2,942 technical terms and definitions
stealth laser dicing crack propagation control machine learning, stealth laser, dicing crack propagation, stealth laser dicing crack propagation control, laser dicing
Stealth Laser Dicing Crack Propagation Control with Machine Learning Introduction & Motivation Stealth Laser Dicing Crack Propagation Control with Machine Learning addresses…
optimization
Steepest ascent (or steepest descent for minimization) is an optimization technique that uses the results of a first-order (linear) DOE to determine the direction of fastest…
computer vision
Steerable CNNs are convolutional neural networks where filters are defined as linear combinations of a steerable basis — typically Gaussian derivatives, circular harmonics…
chemistry ai
Steered Molecular Dynamics (SMD) with AI refers to the combination of machine learning methods with steered molecular dynamics simulations, where external forces are applied…
activation, control vector
Activation Steering and Control Vectors What is Activation Steering? Modifying model activations during inference to control output behavior without retraining. Core Concept…
activation, control
Steering Vectors (Activation Engineering) are the interpretability and control technique that modifies model behavior at inference time by adding learned direction vectors…
security
Steganography detection (steganalysis) involves finding hidden messages or data embedded within seemingly innocent digital content such as images, audio files, video, or text.…
Stein Variational Gradient Descent SVGD for Deep Ensembles Introduction & Motivation Stein Variational Gradient Descent SVGD for Deep Ensembles addresses a central problem…
stem, metrology
Spectroscopic ellipsometry and inline optical wafer metrology constitute the non-destructive physical measurement and defect detection disciplines that govern yield control across…
quality & reliability
Stem-and-Leaf Plot is a compact distribution display that preserves individual values while showing grouped structure - It is a core method in modern semiconductor statistical…
stem probe current stability prediction machine learning, stem probe, current stability prediction, stem tem, stem probe current stability prediction, stem probe current
STEM Probe Current Stability Prediction with Machine Learning Introduction & Motivation STEM Probe Current Stability Prediction with Machine Learning addresses a central problem…
nlp
Stemming is a heuristic-based text normalization process that reduces words to their root form (stem) by chopping off ends of words — a crude but fast approximation…
paste printing, smt aperture
Stencil aperture is the individual opening in a solder-paste stencil that defines local deposition shape and volume on a PCB pad - its geometry directly controls transfer…
manufacturing
Stencil design is the engineering of stencil thickness, aperture geometry, and material features to control solder paste deposition quality - it is a key determinant of print…
stencil printing paste transfer efficiency prediction machine learning, stencil printing, paste transfer efficiency, smt, stencil printing paste, printing paste
Stencil Printing Paste Transfer Efficiency Prediction with Machine Learning Introduction & Motivation Stencil Printing Paste Transfer Efficiency Prediction with Machine Learning…
stencil printing solder paste volume prediction, stencil printing solder, printing solder paste, solder paste volume, paste volume prediction, stencil printing, solder paste
Stencil Printing Solder Paste Volume Prediction with Machine Learning Introduction & Motivation Stencil Printing Solder Paste Volume Prediction with Machine Learning addresses…
prompting
Step-back prompting is the prompting strategy that first asks a higher-level conceptual question before returning to the original specific query - stepping back can improve…
rag
Step-Back Prompting is a prompting-retrieval technique that reframes specific questions into higher-level principles before search - It is a core method in modern RAG…
bottom coverage, sidewall step coverage, step coverage ratio, overhang, breadloafing, cvd step coverage, feature coverage, liner coverage, barrier step coverage, step coverage measurement, cvd
Step coverage is a profile collapsed into a number, and the collapse throws away exactly the information that decides whether the film works. Three different films can all report…
reliability
Step stress test is a test method that applies stress in discrete incremental steps to identify failure thresholds - Devices are evaluated at each step so onset of degradation…
lithography
A Stepper is a lithography tool that projects a reticle (mask) pattern onto photoresist-coated wafers using a step-and-repeat process — exposing one die (or a small group of dies)…
stepper lens aberration drift prediction machine learning, stepper lens, aberration drift prediction, cd, stepper lens aberration drift prediction, stepper lens aberration
Stepper Lens Aberration Drift Prediction with Machine Learning Introduction & Motivation Stepper Lens Aberration Drift Prediction with Machine Learning addresses a central problem…
stepper motor driver microstep prediction, stepper motor driver, motor driver microstep, driver microstep prediction, stepper motor, motor driver, driver microstep
Stepper Motor Driver Microstep Prediction with Machine Learning Introduction & Motivation Stepper Motor Driver Microstep Prediction with Machine Learning addresses a central…
robotics
Stereo SLAM is the visual SLAM approach that uses two synchronized cameras with known baseline to estimate depth directly and preserve metric scale - this reduces ambiguity…
stereo vision depth, stereo vision, vision depth
Stereo Vision Depth Introduction & Motivation Stereo Vision Depth addresses a central problem in vision process control and depth-estimation-baseline-disparity prediction: how…
Stereo Vision and Disparity Estimation Introduction & Motivation Stereo Vision and Disparity Estimation addresses a central problem in vision processing…
evaluation
StereoSet is a large-scale benchmark for measuring stereotypical biases in pretrained language models across four domains: gender, race, religion, and profession. It evaluates…
evaluation
StereoSet is the bias benchmark that evaluates whether language models prefer stereotypical completions over anti-stereotypical or unrelated alternatives - it measures stereotype…
evaluation
Stereotype Bias is systematic generation or reinforcement of socially stereotyped associations in model outputs - It is a core method in modern AI fairness and evaluation…
fairness
Stereotype bias in LLMs is the tendency of language models to reproduce or infer socially stereotyped associations from training data - these biases can affect fairness…
Student-Teacher Feature Pyramid Matching STFPM Introduction & Motivation Student-Teacher Feature Pyramid Matching STFPM addresses a central problem in anomaly detection…
sti cmp dishing prediction machine learning, sti cmp, dishing prediction machine, cmp sti, sti cmp dishing prediction, sti cmp dishing, cmp dishing prediction, cmp dishing, dishing prediction
STI CMP Dishing Prediction with Machine Learning Introduction & Motivation STI CMP Dishing Prediction with Machine Learning addresses a central problem in shallow trench isolation…
shallow trench isolation, trench fill planarization, STI dishing erosion, cmp
Shallow trench isolation (STI), high-aspect-ratio dielectric gap fill, chemical mechanical polishing (CMP), and channel mechanical stress engineering constitute the primary…
sti cmp step height prediction, sti cmp step, cmp step height, step height prediction, sti cmp, cmp step, step height, height prediction
STI CMP Step Height Prediction with Machine Learning Introduction & Motivation STI CMP Step Height Prediction with Machine Learning addresses a central problem in shallow trench…
sti, process integration
STI formation is the shallow-trench-isolation process used to electrically isolate neighboring active regions - Etch fill and planarization steps create dielectric trenches that…
sti gap fill void prediction machine learning, sti gap, fill void prediction, cvd hdp sti, sti gap fill void prediction, sti gap fill, gap fill void, gap fill, fill void, void prediction
STI Gap Fill Void Prediction with Machine Learning Introduction & Motivation STI Gap Fill Void Prediction with Machine Learning addresses a central problem in shallow trench…
facility
Semiconductor cleanroom engineering, ultra-pure water synthesis, and advanced facility distribution networks constitute the critical physical infrastructure required to sustain…
process
Stiction is the adhesion-related sticking of released MEMS structures to nearby surfaces due to capillary, van der Waals, or electrostatic forces - it is a major yield…
stimulus generation randomization, stimulus generation, generation randomization
Stimulus Generation Randomization Introduction & Motivation Stimulus Generation Randomization addresses a central problem in verification process control…
packaging
Stitch bond is the second wire-bond connection formed by pressing wire onto substrate or lead without forming a free-air ball - it completes the electrical path after the first…
stl, time series models
STL Decomposition is seasonal-trend decomposition using LOESS for robust and flexible component extraction. - It handles nonstationary seasonality better than fixed-parameter…
stochastic arithmetic, bitstream computing, probabilistic bitstream
Stochastic computing is a representation in which numerical values are encoded by the statistics of bitstreams and arithmetic is performed with simple logic. Stochastic computing…
stochastic computing for approximation, stochastic computing approximation, stochastic computing, computing approximation
Stochastic Computing for Approximation Introduction & Motivation Stochastic Computing for Approximation addresses a central problem in stochastic-comp process control…
lithography
Stochastic defects are random, unpredictable patterning failures caused by the statistical nature of photoresist chemistry at the nanoscale. Unlike systematic defects (which occur…
computer vision
Stochastic Depth is the layer-wise dropout that randomly skips transformer blocks during training so very deep Vision Transformers do not overfit or suffer exploding gradients…
neural architecture
Stochastic Differential Equations (SDEs) in neural architecture are continuous-depth models that incorporate noise directly into the dynamics — , combining deterministic drift…
lithography
Stochastic Effects in Lithography are random, statistically distributed variations in photon absorption and photochemical reactions in photoresist that produce local pattern…
stochastic euv defect rate prediction, stochastic euv defect, euv defect rate, defect rate prediction, stochastic euv, euv defect, defect rate, rate prediction
Stochastic EUV Defect Rate Prediction with Machine Learning Introduction & Motivation Stochastic EUV Defect Rate Prediction with Machine Learning addresses a central problem…
euv shot noise, euv local critical dimension uniformity, euv edge roughness, euv defect inspection, euv
Extreme Ultraviolet lithography operates at a soft X-ray wavelength of 13.5nm where optical diffraction limits are dramatically reduced compared to 193nm immersion, yet patterning…
Stochastic Games and Nash Equilibrium Introduction & Motivation Stochastic Games and Nash Equilibrium addresses a central problem in reinforcement policy learning…