15,433 technical terms and definitions
edge node placement and optimization, edge node placement, node placement optimization, edge node, node placement, placement optimization
Edge Node Placement and Optimization Introduction & Motivation Edge Node Placement and Optimization addresses a central problem in edge-computing process control…
graph neural networks
Edge Pooling is a graph neural network pooling method that operates on edges rather than nodes, iteratively contracting the highest-scoring edges to merge pairs of connected nodes…
graph neural networks
Edge Pooling is graph coarsening by contracting high-scoring edges to reduce graph size. - It preserves local connectivity while building hierarchical representations for deeper…
supermask training, strong lottery ticket, sparse neural networks, mask optimization
Edge-Popup is a sparse neural network training method that learns a binary connectivity mask over a randomly initialized network while keeping the underlying weights fixed…
Edge Prediction and Link Scoring Introduction & Motivation Edge Prediction and Link Scoring addresses a central problem in graph network representation…
edge reliability and fault tolerance, edge reliability fault, reliability fault tolerance, edge reliability, reliability fault, fault tolerance
Edge Reliability and Fault Tolerance Introduction & Motivation Edge Reliability and Fault Tolerance addresses a central problem in edge-computing process control…
edge ring erosion prediction machine learning, edge ring, erosion prediction machine, cd rf, edge ring erosion prediction, edge ring erosion, ring erosion prediction, ring erosion
Edge Ring Erosion Prediction with Machine Learning Introduction & Motivation Edge Ring Erosion Prediction with Machine Learning addresses a central problem in plasma etch edge…
edge roll off measurement drift prediction with machine learning, edge roll off measurement drift prediction machine learning, edge roll, off measurement drift, edge roll-off
Edge Roll-Off Measurement Drift Prediction with Machine Learning Introduction & Motivation Edge Roll-Off Measurement Drift Prediction with Machine Learning addresses a central…
edge device training, edge device, device training
Edge Device Training Introduction & Motivation Edge Device Training addresses a central problem in ml-training process control and training-time-on-edge prediction: how to Predict…
edge trim measurement drift prediction, edge trim measurement, trim measurement drift, measurement drift prediction, edge trim, trim measurement, measurement drift, drift prediction
Edge Trim Measurement Drift Prediction with Machine Learning Introduction & Motivation Edge Trim Measurement Drift Prediction with Machine Learning addresses a central problem…
edge video processing and compression, edge video processing, video processing compression, edge video, video processing, processing compression
Edge Video Processing and Compression Introduction & Motivation Edge Video Processing and Compression addresses a central problem in edge-computing process control…
edi, supply chain & logistics
EDI is electronic data interchange for standardized machine-to-machine business document exchange - It automates transactional communication and reduces manual processing errors.…
edit distance and alignment, edit distance alignment, edit distance, distance alignment
Edit Distance and Alignment Introduction & Motivation Edit Distance and Alignment addresses a central problem in algorithms process control and distance-metric-correctness…
edit distance levenshtein similarity prediction, edit distance levenshtein, distance levenshtein similarity, levenshtein similarity prediction, edit distance
Edit Distance Levenshtein Similarity Prediction with Machine Learning Introduction & Motivation Edit Distance Levenshtein Similarity Prediction with Machine Learning addresses…
Edited Nearest Neighbors ENN for Label Noise Removal Introduction & Motivation Edited Nearest Neighbors ENN for Label Noise Removal addresses a central problem in {subject}…
model merging
Editing Models via Task Vectors is a model modification framework that decomposes fine-tuned model knowledge into portable, composable vectors — enabling transfer, removal…
generative models
Editing real images with GANs is the workflow that projects real photos into GAN latent space and applies controlled transformations to generate edited outputs - it extends…
edram cell retention time prediction machine learning, edram cell, retention time prediction, dram, edram cell retention time prediction, edram cell retention, cell retention time
eDRAM Cell Retention Time Prediction with Machine Learning Introduction & Motivation eDRAM Cell Retention Time Prediction with Machine Learning addresses a central problem…
embedded dram leakage current and data retention time, embedded dram leakage, dram leakage current, leakage current data, current data retention, data retention time, embedded dram
Embedded DRAM Leakage Current and Data Retention Time Introduction & Motivation Embedded DRAM Leakage Current and Data Retention Time addresses a central problem in memory process…
healthcare ai
EEG analysis with AI uses deep learning to interpret brain wave recordings — automatically detecting seizures, sleep stages, brain disorders, and cognitive states…
eeprom endurance cycle limit prediction, eeprom endurance cycle, endurance cycle limit, cycle limit prediction, eeprom endurance, endurance cycle, cycle limit, limit prediction
EEPROM Endurance Cycle Limit Prediction with Machine Learning Introduction & Motivation EEPROM Endurance Cycle Limit Prediction with Machine Learning addresses a central problem…
efem reticle pod particle ingress prediction machine learning, efem reticle, pod particle ingress, efem ffu smif, efem and reticle pod particle ingress prediction
EFEM and Reticle Pod Particle Ingress Prediction with Machine Learning Introduction & Motivation EFEM and Reticle Pod Particle Ingress Prediction with Machine Learning addresses…
efem load port wafer mapping fault prediction, efem load port, load port wafer, port wafer mapping, wafer mapping fault, mapping fault prediction, efem load, load port
EFEM Load Port Wafer Mapping Fault Prediction with Machine Learning Introduction & Motivation EFEM Load Port Wafer Mapping Fault Prediction with Machine Learning addresses…
efem robot alignment drift prediction machine learning, efem robot, alignment drift prediction, efem, efem robot alignment drift prediction, efem robot alignment, robot alignment
EFEM Robot Alignment Drift Prediction with Machine Learning Introduction & Motivation EFEM Robot Alignment Drift Prediction with Machine Learning addresses a central problem…
efem robot end-effector wear prediction, efem robot end-effector, robot end-effector wear, end-effector wear prediction, efem robot, robot end-effector, end-effector wear
EFEM Robot End-Effector Wear Prediction with Machine Learning Introduction & Motivation EFEM Robot End-Effector Wear Prediction with Machine Learning addresses a central problem…
effective number of bits (enob) prediction, effective number bits, number bits (enob), bits (enob) prediction, effective number, number bits, bits (enob), (enob) prediction
Effective Number of Bits (ENOB) Prediction with Machine Learning Introduction & Motivation Effective Number of Bits (ENOB) Prediction with Machine Learning addresses a central…
llm architecture
Efficient Attention Variants are a family of modified attention mechanisms designed to reduce the O(N²) computational and memory cost of standard Transformer self-attention…
model serving, inference optimization, deployment efficiency, serving infrastructure
Efficient Inference and Model Serving — Efficient inference transforms trained deep learning models into production-ready systems that deliver low-latency predictions at scale…
speculative decoding llm, continuous batching inference, llm inference optimization, kv cache efficient serving
Efficient Inference (KV Cache, Speculative Decoding, Continuous Batching) is the set of systems-level optimizations that reduce the latency, throughput, and cost of serving large…
model compression deployment, pruning quantization distillation, mobile neural network, edge ai inference
Efficient Neural Network Inference is the systems engineering discipline that minimizes the computational cost, memory footprint, and latency of deploying trained neural networks…
Efficient NAS Methods Introduction & Motivation Efficient NAS Methods addresses a central problem in optimization algorithm tuning and improvement: how to Optimize {target}…
Efficient Network Architecture Design Introduction & Motivation Efficient Network Architecture Design addresses a central problem in vision processing…
enas, neural architecture
Efficient Neural Architecture Search (ENAS) is a neural architecture search method that reduces the computational cost of finding optimal network architectures from thousands…
EfficientNet Compound Scaling Search Introduction & Motivation EfficientNet Compound Scaling Search addresses a central problem in automated design of nas architectures: how…
EfficientNet Compound Scaling Search (Extended Study) Introduction & Motivation EfficientNet Compound Scaling Search (Extended Study) addresses a central problem in automated…
EfficientNet Compound Scaling Search (Extended Study) Introduction & Motivation EfficientNet Compound Scaling Search (Extended Study) addresses a central problem in automated…
neural architecture search
EfficientNet NAS is an architecture design approach combining NAS-derived baselines with compound model scaling. - Depth, width, and input resolution are scaled together…
efficientnet resource-constrained scaling and compound scaling, efficientnet resource-constrained scaling, resource-constrained scaling compound, scaling compound scaling
EfficientNet Resource-Constrained Scaling and Compound Scaling Introduction & Motivation EfficientNet Resource-Constrained Scaling and Compound Scaling addresses a central problem…
model optimization
EfficientNet Scaling is a compound model scaling strategy that jointly adjusts depth, width, and resolution - It improves accuracy-efficiency balance more systematically than…
efuse programming current requirement prediction, efuse programming current, programming current requirement, current requirement prediction, efuse programming
eFuse Programming Current Requirement Prediction with Machine Learning Introduction & Motivation eFuse Programming Current Requirement Prediction with Machine Learning addresses…
efuse programming reliability prediction, efuse programming reliability, programming reliability prediction, efuse programming, programming reliability, reliability prediction
eFuse Programming Reliability Prediction with Machine Learning Introduction & Motivation eFuse Programming Reliability Prediction with Machine Learning addresses a central problem…
efuse reliability cycling endurance prediction, efuse reliability cycling, reliability cycling endurance, cycling endurance prediction, efuse reliability, reliability cycling
eFuse Reliability Cycling Endurance Prediction with Machine Learning Introduction & Motivation eFuse Reliability Cycling Endurance Prediction with Machine Learning addresses…
Exponential GARCH for Leverage Effect Estimation Introduction & Motivation Exponential GARCH for Leverage Effect Estimation addresses a central problem in timeseries forecasting…
egnn, graph neural networks
EGNN is an E(n)-equivariant graph neural network that updates node features and coordinates without expensive tensor irreps - Message passing jointly updates latent features…
Egocentric Action Recognition Introduction & Motivation Egocentric Action Recognition addresses a central problem in multimodal learning and action-recognition-accuracy alignment…
Egocentric Vision-Language Models Introduction & Motivation Egocentric Vision-Language Models addresses a central problem in multimodal learning…
explainable ai
Eigen-CAM is a class activation mapping method based on principal component analysis (PCA) of the feature maps — using the first principal component of the activation maps as…
autoscaling training jobs, dynamic worker scaling, fault adaptive training, elastic dl runtime
Elastic Distributed Training is the training runtime capability that allows workers to join or leave without restarting the full job. What It Covers Core concept: rebalances data…
ai safety
Elastic Net Attack (EAD) is an adversarial attack that combines and perturbation penalties — optimizing subject to misclassification, producing perturbations that are both sparse…
elastic net l1+l2 regularization prediction, elastic net l1+l2, net l1+l2 regularization, l1+l2 regularization prediction, elastic net, net l1+l2, l1+l2 regularization
Elastic Net L1+L2 Regularization Prediction with Machine Learning Introduction & Motivation Elastic Net L1+L2 Regularization Prediction with Machine Learning addresses a central…