27,049 technical terms and definitions
device isolation cmos, sti process fill, lcos isolation, isolation oxide semiconductor
Shallow trench isolation (STI), high-aspect-ratio dielectric gap fill, chemical mechanical polishing (CMP), and channel mechanical stress engineering constitute the primary…
sti process flow, sti oxide fill, trench isolation scaling, sti stress effect
Shallow trench isolation (STI), high-aspect-ratio dielectric gap fill, chemical mechanical polishing (CMP), and channel mechanical stress engineering constitute the primary…
trench etch liner oxidation, sti gap fill cmp, sti stress isolation, active area definition
Shallow trench isolation (STI), high-aspect-ratio dielectric gap fill, chemical mechanical polishing (CMP), and channel mechanical stress engineering constitute the primary…
shallow trench isolation (sti) stress, sti mechanical stress, piezoresistive stress sti, device physics
Shallow trench isolation (STI), high-aspect-ratio dielectric gap fill, chemical mechanical polishing (CMP), and channel mechanical stress engineering constitute the primary…
shapley, explanation
SHAP (SHapley Additive exPlanations) is the game-theoretic framework for explaining machine learning model predictions by computing each feature's fair marginal contribution…
multimodal ai
Shap-E is a generative model that produces implicit 3D representations from text or image inputs - It supports direct sampling of renderable 3D assets. What Is Shap-E? Definition…
shap, data analysis
SHAP (SHapley Additive exPlanations) is a game-theoretic approach that assigns each feature an importance score for a particular prediction — based on Shapley values…
shap, shapley additive explanations, explainable ai
SHAP (SHapley Additive exPlanations) attributes prediction to input features using game-theoretic Shapley values. Core concept: From cooperative game theory - fairly distribute…
SHAP Shapley Additive Explanations Introduction & Motivation SHAP Shapley Additive Explanations addresses a central problem in interpretability and explanation of xai predictions…
SHAP Shapley Additive Explanations (Extended Study) Introduction & Motivation SHAP Shapley Additive Explanations (Extended Study) addresses a central problem in interpretability…
SHAP Shapley Additive Explanations (Extended Study) Introduction & Motivation SHAP Shapley Additive Explanations (Extended Study) addresses a central problem in interpretability…
SHAP Shapley Additive Explanations (Extended Study) Introduction & Motivation SHAP Shapley Additive Explanations (Extended Study) addresses a central problem in interpretability…
shap, interpretability
SHAP Values is feature attributions based on Shapley value principles from cooperative game theory - They quantify each feature contribution to a prediction with additive…
SHAP Values for Model Explanation Introduction & Motivation SHAP Values for Model Explanation addresses a central problem in explainability interpretation and model understanding…
computer vision
Shape Bias is the reliance on global shape features (contours, silhouettes, structural geometry) for object recognition — shape-biased models, like human visual perception…
computer vision
Shape Completion is the computer vision task of predicting complete 3D geometry from partial observations — reconstructing missing surfaces, occluded regions, and unseen…
computer vision
Shape correspondence is the problem of finding matching points or regions across different 3D shapes — establishing relationships between shapes to enable comparison, analysis…
Shape-from-Shading Methods Introduction & Motivation Shape-from-Shading Methods addresses a central problem in vision processing and shape-recovery-accuracy prediction: how…
computer vision
Shape generation is the task of creating new 3D shapes computationally — using algorithms, procedural methods, or machine learning to synthesize novel geometric forms, enabling…
Shape Generation Networks Introduction & Motivation Shape Generation Networks addresses a central problem in generative generation and shape-diversity-quality synthesis: how…
business & standards
Shape Parameter is the Weibull beta parameter that describes how failure rate changes over time - It is a core method in advanced semiconductor reliability engineering programs.…
Shapley Flow for Causal Graph Feature Attributions Introduction & Motivation Shapley Flow for Causal Graph Feature Attributions addresses a central problem in explainability…
Sobol Indices and Functional ANOVA for Feature Interactions Introduction & Motivation Sobol Indices and Functional ANOVA for Feature Interactions addresses a central problem…
SHAP Residual Decomposition for Local Model Errors Introduction & Motivation SHAP Residual Decomposition for Local Model Errors addresses a central problem in explainability…
shapley value feature contribution prediction, shapley value feature, value feature contribution, feature contribution prediction, shapley value, value feature
Shapley Value Feature Contribution Prediction with Machine Learning Introduction & Motivation Shapley Value Feature Contribution Prediction with Machine Learning addresses…
reinforcement learning advanced
Shapley value MARL is multi-agent credit-assignment methods using Shapley-value principles to estimate each agent contribution - Marginal contribution estimates allocate shared…
shapley value time series, shapley value time, value time series, shapley value, value time, time series
Shapley Value Time Series Introduction & Motivation Shapley Value Time Series addresses a central problem in timeseries process control and shapley-feature-contribution-value…
sharding strategy and partitioning, sharding strategy partitioning, sharding strategy, strategy partitioning
Sharding Strategy and Partitioning Introduction & Motivation Sharding Strategy and Partitioning addresses a central problem in distributed-systems process control…
teach, community, blog, conference, open source, knowledge
Sharing AI learnings with the broader community involves documenting and communicating knowledge through blogs, talks, and open source — contributing to collective understanding…
Shared Encoder Task-Specific Decoder Architectures Introduction & Motivation Shared Encoder Task-Specific Decoder Architectures addresses a central problem in multitask learning…
Shared Encoder Task-Specific Decoder Architectures (Extended Study) Introduction & Motivation Shared Encoder Task-Specific Decoder Architectures (Extended Study) addresses…
Shared Encoder Task-Specific Decoder Architectures (Extended Study) Introduction & Motivation Shared Encoder Task-Specific Decoder Architectures (Extended Study) addresses…
moe
Shared expert in MoE is the always-active expert path that processes every token alongside routed sparse experts - it provides a stable general-purpose representation channel…
shared memory, cache, scratchpad
Cache memory is a small, fast storage hierarchy placed near compute units to keep recently used instructions and data from repeatedly traveling to slower, more energy-intensive…
hardware
Shared memory is the software-managed on-chip memory region accessible by threads within a GPU thread block - it enables low-latency data reuse patterns that significantly reduce…
ai agents
Shared Memory Agents is a collaboration style where agents read and write to a common state repository - It is a core method in modern semiconductor AI-agent coordination…
shared memory concurrency, shared memory, memory concurrency
Shared Memory Concurrency Introduction & Motivation Shared Memory Concurrency addresses a central problem in programming process control and lock-contention-performance…
posix shared memory, memory mapped file, mmap, shm_open, interprocess communication
POSIX Shared Memory and Memory-Mapped Files are the inter-process communication (IPC) mechanisms that allow multiple processes to access the same region of physical memory…
cuda shared memory, cooperative loading threads, shared memory synchronization, tile based computation
Shared Memory Programming Patterns are the algorithmic techniques that exploit the fast, programmer-managed shared memory (20 TB/s, 128 KB per SM) available to thread blocks…
multi-task learning
Shared representations is internal feature spaces used by multiple tasks to capture reusable structure - Shared layers learn common patterns that support transfer and reduce…
training techniques
ShareGPT is a corpus source of user-assistant conversation traces used to train and evaluate conversational language models - It is a core method in modern LLM training and safety…
theory
Sharp Minima are regions of the loss landscape where the loss increases rapidly when parameters are perturbed — characterized by large eigenvalues of the Hessian matrix…
semi-supervised learning
Sharpening is a technique that reduces the entropy of a probability distribution by raising it to a power (lowering the temperature) — making confident predictions more confident…
self-supervised learning
Sharpening in self-supervised learning is the temperature-based target transformation that makes teacher probability distributions more confident and less uniform - by lowering…
sam, optimization
SAM (Sharpness-Aware Minimization) is an optimization technique that simultaneously minimizes both the loss value and the loss sharpness — by seeking parameters that lie in flat…
Sharpness-Aware Minimization SAM for Flat Minima Introduction & Motivation Sharpness-Aware Minimization SAM for Flat Minima addresses a central problem in optimization algorithm…
quality
Shear test is the destructive test that applies lateral force to bonded features such as ball bonds to measure interfacial strength and adhesion quality - it complements pull…
ohms per square, thin film sheet resistance, implant sheet resistance
Four-point probe metrology measures sheet resistance by forcing current through two contacts and sensing voltage with two separate contacts, so the voltage channel carries almost…
sheet resistance map, sheet resistance uniformity mapping, wafer sheet resistance map, resistivity mapping four point probe
Four-point probe metrology measures sheet resistance by forcing current through two contacts and sensing voltage with two separate contacts, so the voltage channel carries almost…
quality
Shelf life is the maximum approved storage duration during which components and materials are expected to remain within quality and performance specifications - it is a key…