2,942 technical terms and definitions
expert routing, top-k routing, load balancing moe, mixture of experts training
Sparse Mixture-of-Experts (MoE) Gating is the routing mechanism that selects which expert networks process each token in an MoE model — enabling scaling to trillions of parameters…
model optimization sparse subnetwork
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
winning subnetworks, model training sparse
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
sparse principal component analysis (spca) prediction, sparse principal component, principal component analysis, component analysis (spca), analysis (spca) prediction
Sparse Principal Component Analysis (SPCA) Prediction with Machine Learning Introduction & Motivation Sparse Principal Component Analysis (SPCA) Prediction with Machine Learning…
rag
Sparse retrieval is the lexical search approach that ranks documents using sparse term-based representations and exact token overlap - it remains highly effective for precise…
rag
Sparse Retrieval is a lexical retrieval approach based on term matching statistics such as BM25 and inverted indexes - It is a core method in modern retrieval and RAG execution…
Sparse Reward Problem Solving Introduction & Motivation Sparse Reward Problem Solving addresses a central problem in reinforcement policy learning and reward-signal-recovery…
sparse tensor acceleration, sparse tensor, tensor acceleration
Sparse Tensor Acceleration Introduction & Motivation Sparse Tensor Acceleration addresses a central problem in hardware-accelerators process control…
Sparse and High-Dimensional Time Series Introduction & Motivation Sparse and High-Dimensional Time Series addresses a central problem in timeseries forecasting…
dynamic sparse training, rigl sparse training, sparse neural optimization, train sparse from scratch
Dynamic Sparse Training (DST) is a family of training methods that maintain or evolve network sparsity during training, rather than training dense and pruning afterward. The most…
model optimization
Sparse Training is training regimes that enforce sparsity throughout optimization instead of pruning after training - It reduces training and deployment cost by maintaining sparse…
sparse attention
Sliding-window and sparse attention are techniques that cut the cost of the Transformer's attention by computing only a chosen subset of query-key pairs instead of all of them.…
model architecture
Sparse Upcycling is the model scaling technique that converts a pre-trained dense transformer into a Mixture of Experts (MoE) model by replicating the feed-forward network (FFN)…
Sparse Variational Gaussian Processes Introduction & Motivation Sparse Variational Gaussian Processes addresses a central problem in bayesiandl modeling with calibrated predictive…
Sparse Variational Gaussian Processes (Extended Study) Introduction & Motivation Sparse Variational Gaussian Processes (Extended Study) addresses a central problem in bayesiandl…
Sparse Variational Gaussian Processes (Extended Study) Introduction & Motivation Sparse Variational Gaussian Processes (Extended Study) addresses a central problem in bayesiandl…
model optimization
Sparse Weight Averaging is a model-averaging method adapted for sparse parameter settings to improve generalization - It stabilizes sparse model performance across optimization…
gradient sparsity patterns, structured unstructured sparsity, dynamic sparsity adaptation, sparsity ratio selection
Sparsification Methods are the techniques for inducing and exploiting sparsity in gradients, activations, or weights during distributed training — ranging from unstructured…
pruning, zero, structured, unstructured, compression
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
hardware exploitation of sparsity, hardware exploitation sparsity, hardware exploitation, exploitation sparsity
Hardware Exploitation of Sparsity Introduction & Motivation Hardware Exploitation of Sparsity addresses a central problem in ml-hardware process control…
hardware exploitation of weight and activation sparsity, hardware exploitation weight, exploitation weight activation, weight activation sparsity, hardware exploitation, exploitation weight
Hardware Exploitation of Weight and Activation Sparsity Introduction & Motivation Hardware Exploitation of Weight and Activation Sparsity addresses a central problem in sparse-ml…
model optimization
Spatial Attention is attention weighting over spatial positions to highlight informative regions in feature maps - It helps models focus compute on task-relevant locations. What…
manufacturing operations
Spatial Autocorrelation is a statistical measure of how strongly neighboring dies share similar pass-fail outcomes - It is a core method in modern semiconductor wafer-map…
spatial bin pattern signature classification prediction, spatial bin pattern, bin pattern signature, pattern signature classification, spatial bin, bin pattern
Spatial Bin Pattern Signature Classification Prediction with Machine Learning Introduction & Motivation Spatial Bin Pattern Signature Classification Prediction with Machine…
spatial computing performance, spatial computing, computing performance
Spatial Computing Performance Introduction & Motivation Spatial Computing Performance addresses a central problem in spatial-computing process control…
spatial computing hardware, spatial architecture, cgra, wafer scale engine, dataflow processor
Spatial computing definition and engineering boundary. in hardware architecture places many operations and storage resources at distinct physical locations and configures data…
yield enhancement
Spatial Correlation is the tendency of defect or parametric outcomes to be related by physical location on wafer or die - It reveals underlying process gradients, localized…
manufacturing
Spatial correlation in yield is the statistical relationship where neighboring dies on a wafer show similar pass-fail behavior because they share local process conditions - when…
spatial kriging wafer metrology interpolation machine learning, spatial kriging, wafer metrology interpolation, spatial kriging for wafer metrology interpolation
Spatial Kriging for Wafer Metrology Interpolation with Machine Learning Introduction & Motivation Spatial Kriging for Wafer Metrology Interpolation with Machine Learning addresses…
spc
Spatial monitoring is the analysis of location-dependent process behavior across wafers, chambers, or tools to detect patterned variation - it focuses on where variation occurs…
reasoning
Spatial reasoning is the cognitive ability to understand and manipulate spatial relationships between objects — including their positions, orientations, distances, sizes, shapes…
computer vision
Spatial reasoning in computer vision involves understanding geometric relationships between objects like above below left right near far inside and outside. This requires models…
metrology
Spatial signature is the characteristic pattern of failures on a wafer — the unique fingerprint of a process issue, equipment problem, or systematic defect that appears…
advanced test & probe
Spatial Signature is the wafer-map pattern of failing or drifting measurements across physical die locations - It helps isolate process, equipment, and probe-related systematic…
spatial signature analysis drift prediction, spatial signature analysis, signature analysis drift, analysis drift prediction, spatial signature, signature analysis
Spatial Signature Analysis Drift Prediction with Machine Learning Introduction & Motivation Spatial Signature Analysis Drift Prediction with Machine Learning addresses a central…
spatial signature clustering drift prediction machine learning, spatial signature, clustering drift prediction, spatial signature clustering drift prediction
Spatial Signature Clustering Drift Prediction with Machine Learning Introduction & Motivation Spatial Signature Clustering Drift Prediction with Machine Learning addresses…
spatial wafer level yield model prediction with machine learning, spatial wafer level yield model prediction machine learning, spatial wafer, level yield model, yield model
Spatial Wafer-Level Yield Model Prediction with Machine Learning Introduction & Motivation Spatial Wafer-Level Yield Model Prediction with Machine Learning addresses a central…
spatial yield map anomaly prediction, spatial yield map, yield map anomaly, map anomaly prediction, spatial yield, yield map, map anomaly, anomaly prediction
Spatial Yield Map Anomaly Prediction with Machine Learning Introduction & Motivation Spatial Yield Map Anomaly Prediction with Machine Learning addresses a central problem…
Spatial Scan Statistics and Spatial-Temporal Clusters Introduction & Motivation Spatial Scan Statistics and Spatial-Temporal Clusters addresses a central problem in anomaly…
Spatio-Temporal Graph Wavelet Networks Introduction & Motivation Spatio-Temporal Graph Wavelet Networks addresses a central problem in graph network representation…
computer vision
Spatiotemporal Detection (or Video Object Detection) is the task of tracking and classifying objects across both space and time — essentially drawing a "tube" (sequence…
statistical process control, control chart, shewhart, cpk, process capability, ewma, cusum, gauge r&r, run rules, process control
Statistical Process Control (SPC) is the methodology of using statistical methods to monitor and control manufacturing processes — applying control charts, capability indices…
process capability spc
Process capability in SPC measures a process's ability to produce output within specification limits — it quantifies how well the natural variation of the process fits within…
spc control chart alarm rate prediction, spc control chart, control chart alarm, chart alarm rate, alarm rate prediction, spc control, control chart, chart alarm, alarm rate
SPC Control Chart Alarm Rate Prediction with Machine Learning Introduction & Motivation SPC Control Chart Alarm Rate Prediction with Machine Learning addresses a central problem…
spc control chart drift prediction, spc control chart, control chart drift, chart drift prediction, spc control, control chart, chart drift, drift prediction
SPC Control Chart Drift Prediction with Machine Learning Introduction & Motivation SPC Control Chart Drift Prediction with Machine Learning addresses a central problem…
spc control chart false alarm prediction, spc control chart, control chart false, chart false alarm, false alarm prediction, spc control, control chart, chart false, false alarm
SPC Control Chart False Alarm Prediction with Machine Learning Introduction & Motivation SPC Control Chart False Alarm Prediction with Machine Learning addresses a central problem…
spc control limit recalculation prediction machine learning, spc control, limit recalculation prediction, spc, spc control limit recalculation prediction, spc control limit
SPC Control Limit Recalculation Prediction with Machine Learning Introduction & Motivation SPC Control Limit Recalculation Prediction with Machine Learning addresses a central…
spc multivariate ewma control limit optimization prediction, spc multivariate ewma, multivariate ewma control, ewma control limit, spc multivariate
SPC Multivariate EWMA Control Limit Optimization Prediction with Machine Learning Introduction & Motivation SPC Multivariate EWMA Control Limit Optimization Prediction…
capability spc
SPC Process Capability is the statistical measure of how well a process meets its specifications — comparing the process spread (variation) to the specification range, quantified…
spc rule set false alarm rate optimization prediction, spc rule set, rule set false, set false alarm, false alarm rate, alarm rate optimization, spc rule
SPC Rule Set False Alarm Rate Optimization Prediction with Machine Learning Introduction & Motivation SPC Rule Set False Alarm Rate Optimization Prediction with Machine Learning…