27,049 technical terms and definitions
fab spare parts inventory stockout risk prediction, fab spare parts, spare parts inventory, parts inventory stockout, inventory stockout risk, stockout risk prediction
Fab Spare Parts Inventory Stockout Risk Prediction with Machine Learning Introduction & Motivation Fab Spare Parts Inventory Stockout Risk Prediction with Machine Learning…
spare tool requalification readiness prediction, spare tool requalification, tool requalification readiness, requalification readiness prediction, spare tool
Spare Tool Requalification Readiness Prediction with Machine Learning Introduction & Motivation Spare Tool Requalification Readiness Prediction with Machine Learning addresses…
big data, distributed
Apache Spark is the unified distributed computing engine for large-scale data processing that keeps intermediate results in memory rather than writing to disk between stages…
modern mapreduce, distributed dataframe, parallel python, big data framework
Modern Distributed Computing Frameworks (Spark, Dask, Ray) are the evolution of MapReduce into flexible, high-performance distributed execution engines — replacing Hadoop's rigid…
spark distributed computation, spark distributed, distributed computation
Spark Distributed Computation Introduction & Motivation Spark Distributed Computation addresses a central problem in systems process control and spark-dag-optimization prediction…
efficient 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.…
efficient attention, local attention, sliding window attention, linear attention
Sparse Attention is the family of attention mechanism variants that restrict the full N×N attention matrix to a sparse pattern — reducing the quadratic O(N²) time and memory…
sparse attention computational efficiency and sparsity pattern prediction, sparse attention computational, attention computational efficiency, sparse attention
Sparse Attention Computational Efficiency and Sparsity Pattern Prediction Introduction & Motivation Sparse Attention Computational Efficiency and Sparsity Pattern Prediction…
flash attention, ring attention, sliding window attention, efficient attention
Efficient and Sparse Attention Mechanisms are architectural modifications and computational optimizations to the standard O(N²) self-attention mechanism that enable transformers…
local attention sliding window, longformer bigbird attention, efficient attention long context, dilated attention pattern
Sparse Attention Mechanisms are the architectural modifications to the standard Transformer self-attention that replace the O(N²) full attention matrix with structured sparsity…
efficient transformers, linear attention, local attention patterns, subquadratic sequence modeling
Sparse Attention Mechanisms — Building Efficient Transformers for Long Sequences Sparse attention mechanisms address the fundamental O(n²) computational bottleneck of standard…
sae, features
Sparse Autoencoders for Interpretability What are Sparse Autoencoders? SAEs learn to decompose neural network activations into interpretable, monosemantic features.…
feature, decompose
Sparse Autoencoders (SAEs) are the interpretability tools that decompose the internal representations of neural networks into large sets of sparse, interpretable features…
sparse autoencoder activation sparsity and latent code efficiency, sparse autoencoder activation, autoencoder activation sparsity, activation sparsity latent, sparsity latent code
Sparse Autoencoder Activation Sparsity and Latent Code Efficiency Introduction & Motivation Sparse Autoencoder Activation Sparsity and Latent Code Efficiency addresses a central…
sae mechanistic, dictionary learning neural, feature monosemanticity, superposition hypothesis
Sparse Autoencoders (SAEs) for Interpretability are the unsupervised probing technique that trains a wide, sparsely-activated bottleneck network on the internal activations of…
explainable ai
Sparse autoencoders for interpretability is the autoencoder models trained with sparsity constraints to decompose dense neural activations into more interpretable feature bases…
Sparse Variational Gaussian Processes SVGP Inducing Points Introduction & Motivation Sparse Variational Gaussian Processes SVGP Inducing Points addresses a central problem…
robotics
Sparse mapping is the SLAM and SfM representation that stores selected salient landmarks instead of full surfaces to prioritize localization efficiency - it focuses on distinctive…
csr csc format, spmv parallel, sparse linear algebra, sparse storage format
Sparse Matrix Computation is the parallel computing discipline focused on efficient storage and computation with matrices where 90-99.9% of elements are zero — using compressed…
hardware sparsity sparse tensor core, structured sparsity ai, zero skipping hardware, ai inference efficiency
Sparse Matrix Multiplication Hardware represents the critical next-generation evolution of AI accelerators designed to mathematically exploit the reality that highly trained…
spmv, csr format, sparse computation, compressed sparse row
Sparse Matrix-Vector Multiplication (SpMV) is the operation y = A×x where A is a sparse matrix — a fundamental kernel in scientific computing, graph algorithms, and machine…
csr coo ell format, spmv performance gpu, sparse linear algebra, irregular memory access sparse
SpMV Parallelism: Storage Formats and GPU Optimization — addressing irregular memory access and load imbalance in sparse linear algebra Sparse Matrix-Vector Multiplication (SpMV)…
architecture
Sparse Mixture is mixture architecture where only a small subset of experts is activated for each token - It is a core method in modern semiconductor AI serving…
model architecture
Sparse models activate only a subset of parameters for each input, enabling larger total capacity with fixed compute. Core idea: Route each input to subset of model (experts)…
sparse model inference and structured sparsity hardware support, sparse model inference, model inference structured, inference structured sparsity, structured sparsity hardware
Sparse Model Inference and Structured Sparsity Hardware Support Introduction & Motivation Sparse Model Inference and Structured Sparsity Hardware Support addresses a central…
sparse connectivity updates
Dynamic Sparse Training (DST) is a training paradigm where the sparse network topology changes during training — allowing connections to be pruned and regrown dynamically, so…
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…