gated diode
metrology
Gated diode is a test structure for junction characterization — combining a PN junction with a gate electrode to enable comprehensive characterization of junction properties…
1,045 technical terms and definitions
metrology
Gated diode is a test structure for junction characterization — combining a PN junction with a gate electrode to enable comprehensive characterization of junction properties…
multimodal ai
Gated Fusion is a multimodal fusion mechanism that learns dynamic, input-dependent weights for combining information from different modalities — using sigmoid gating functions…
neural architecture
Gated linear layers is the module pattern where a linear transform is modulated by a learned gate branch before output - it provides fine-grained control over feature flow…
gated recurrent, units gru simplified, bleu gru lstm passed, gated recurrent units gru & simplified gating, gated recurrent units, recurrent units gru, gru simplified gating, recurrent units
Gated Recurrent Units: GRU & Simplified Gating Introduction & Motivation GRU: simplified LSTM with two gates (reset, update). Fewer parameters; comparable performance. No separate…
neural architecture
Gated CNN is a convolutional architecture that uses gated linear units (GLU) instead of standard activation functions — enabling content-dependent feature selection through…
computer vision
Gather-Excite (GE) is a spatial attention mechanism that gathers local spatial context and then excites (modulates) feature responses — extending the squeeze-and-excitation…
Gating in transformers is the use of learned multiplicative controls that regulate which information paths are amplified or suppressed - gating mechanisms improve selectivity…
model architecture
Gating Networks are lightweight neural network modules — typically single linear layers followed by softmax or sigmoid activations — that compute routing weights determining how…
neural architecture
Gating Networks are lightweight neural network modules — typically single linear layers followed by softmax or sigmoid activations — that compute routing weights determining how…
scientific ml
Gauge Equivariant Networks (Gauge CNNs) are convolutional neural networks designed for data defined on non-Euclidean manifolds (curved surfaces, meshes, sphere) that guarantee…
gauge r r measurement variation prediction machine learning, gauge r, r measurement variation, gauge r&r measurement variation prediction, gauge r&r measurement, gauge r&r
Gauge R&R Measurement Variation Prediction with Machine Learning Introduction & Motivation Gauge R&R Measurement Variation Prediction with Machine Learning addresses a central…
gap, chemistry ai
Gaussian Approximation Potentials (GAP) are an advanced class of Machine Learning Force Fields built entirely upon Bayesian statistics and Gaussian Process Regression (GPR) rather…
3d vision
Gaussian covariance is the matrix parameter that defines the size, shape, and orientation of each Gaussian primitive in 3D space - it controls how each primitive spreads influence…
Gaussian Mixture Model Anomaly Detection Introduction & Motivation Gaussian Mixture Model Anomaly Detection addresses a central problem in anomaly detection and {target} scoring…
GMM, mixture of gaussians, soft clustering, mixture model, Karl Pearson 1894, responsibilities, BIC model selection
A Gaussian mixture model (GMM) is a probabilistic model that describes data as drawn from a weighted blend of several normal-distribution components, each with its own mean…
gaussian mixture model clustering prediction, gaussian mixture model, mixture model clustering, model clustering prediction, gaussian mixture, mixture model, model clustering
Gaussian Mixture Model Clustering Prediction with Machine Learning Introduction & Motivation Gaussian Mixture Model Clustering Prediction with Machine Learning addresses a central…
gaussian mixture, models probabilistic clustering, aic ari asr bic em gmm, gaussian mixture models probabilistic clustering & soft assignment, gaussian mixture models
Gaussian Mixture Models: Probabilistic Clustering & Soft Assignment Introduction & Motivation Gaussian mixture models represent data as mixture of K Gaussian distributions…
GP regression, kriging, kernel function, Rasmussen and Williams 2006, bayesian optimization, RBF kernel, Matern kernel
A Gaussian process (GP) is a probability distribution over functions, defined by the property that the function's values at any finite collection of input points are jointly…
Gaussian Process Residual Thresholding for Anomalies Introduction & Motivation Gaussian Process Residual Thresholding for Anomalies addresses a central problem in anomaly…
gaussian process classification prediction, gaussian process classification, process classification prediction, gaussian process, process classification, classification prediction
Gaussian Process Classification Prediction with Machine Learning Introduction & Motivation Gaussian Process Classification Prediction with Machine Learning addresses a central…
Gaussian Process Deep Kernel Learning Introduction & Motivation Gaussian Process Deep Kernel Learning addresses a central problem in bayesiandl modeling with calibrated predictive…
Gaussian Process Deep Kernel Learning (Extended Study) Introduction & Motivation Gaussian Process Deep Kernel Learning (Extended Study) addresses a central problem in bayesiandl…
Gaussian Process Deep Kernel Learning (Extended Study) Introduction & Motivation Gaussian Process Deep Kernel Learning (Extended Study) addresses a central problem in bayesiandl…
Bayesian Gaussian Process Latent Variable Models GPLVM Introduction & Motivation Bayesian Gaussian Process Latent Variable Models GPLVM addresses a central problem in uncertainty…
data analysis
Gaussian Process Regression (GPR) is a non-parametric Bayesian regression method that provides both predictions and uncertainty estimates — modeling the process response as…
Gaussian Process Regression with Composed Kernels Introduction & Motivation Gaussian Process Regression with Composed Kernels addresses a central problem in uncertainty methods…
Gaussian Process Regression Introduction & Motivation Gaussian Process Regression addresses a central problem in uncertainty methods and prediction intervals: how to Quantify…
gaussian process regression prediction, gaussian process regression, process regression prediction, gaussian process, process regression, regression prediction
Gaussian Process Regression Prediction with Machine Learning Introduction & Motivation Gaussian Process Regression Prediction with Machine Learning addresses a central problem…
GP-SSM Gaussian Process State Space Models Introduction & Motivation GP-SSM Gaussian Process State Space Models addresses a central problem in uncertainty methods and prediction…
gaussian processes kernel methods rbf svm bayesian inference, gaussian processes, kernel methods rbf, 100k 10k 1m 800mb 80gb bfgs, gaussian processes kernel, methods rbf svm
Gaussian Processes and Kernel Methods: RBF, SVM, Bayesian Inference 1. Introduction & Motivation Gaussian Processes (GPs) and kernel methods provide powerful, theoretically…
gaussian processes modeling optimization, gaussian processes, processes modeling, cdf ei gp pdf rbf x1, gaussian processes modeling, processes modeling optimization, modeling optimization
Gaussian Processes for Modeling and Optimization Introduction & Motivation Gaussian processes (GPs) provide non-parametric Bayesian approaches for modeling complex functions…
gaussian processes kernel methods non parametric regression, gaussian processes, kernel methods non, 1d gp passed rbf uci x1, gaussian processes kernel, processes kernel methods
Gaussian Processes: Kernel Methods & Non-parametric Regression Introduction & Motivation Gaussian Processes: non-parametric Bayesian model. Prior over functions; updated…
3d vision
Gaussian splatting is the real-time neural rendering method that represents scenes with anisotropic 3D Gaussian primitives projected and blended in screen space - it offers…
multimodal ai
Gaussian Splatting is a 3D scene representation using anisotropic Gaussian primitives for real-time radiance rendering - It enables high-quality view synthesis with strong runtime…
3d vision
Gaussian splatting training is the optimization workflow that fits Gaussian primitive parameters to multi-view images using differentiable rasterization losses - it learns…
gaze estimation eye tracking, gaze estimation eye, estimation eye tracking, gaze estimation, estimation eye, eye tracking
Gaze Estimation Eye Tracking Introduction & Motivation Gaze Estimation Eye Tracking addresses a central problem in vision process control and gaze-direction-eye-tracking…
gc-san, recommendation systems
GC-SAN is a hybrid recommendation model that combines graph convolution with self-attention for session sequences - Graph structure captures transition relations while…
gcd euclidean algorithm, gcd euclidean, euclidean algorithm
GCD Euclidean Algorithm Introduction & Motivation GCD Euclidean Algorithm addresses a central problem in algorithms process control and gcd-computation-logarithmic prediction: how…
gce-gnn, recommendation systems
GCE-GNN is a session-recommendation graph model that fuses local session transitions with global item-transition structure. - It combines immediate click context with corpus-level…
gcn, graph neural networks
GCN Spectral is graph convolution based on spectral filtering over graph Laplacian eigenstructures. - It interprets message passing as frequency-domain filtering of signals…
gcpn, graph neural networks
GCPN is a graph-convolutional policy network for goal-directed molecular graph generation - Reinforcement-learning policies edit graph structures to optimize property-driven…
gdas, neural architecture search
GDAS is gumbel differentiable architecture search that relaxes discrete operator selection into gradient-based optimization. - It enables simultaneous optimization of architecture…
ccpa, data protection
GDPR and CCPA GDPR and CCPA are data protection regulations requiring consent data minimization right to deletion and privacy by default for AI systems. GDPR applies to EU…
tapeout signoff, design release, gds submission
GDS Tapeout Checklist is the comprehensive signoff validation process that verifies every aspect of a chip design is correct, complete, and foundry-compliant before submitting…
gdsii, design
GDSII (Graphic Data System II) is the standard binary file format for storing IC layout data — representing the physical design as a hierarchical collection of polygons, paths…
ge2e, audio & speech
GE2E Loss is generalized end-to-end loss for directly optimizing speaker-verification similarity structure. - It trains embeddings so same-speaker utterances are close…
gedi, generative discriminator, text generation
GeDi (Generative Discriminator) is the controllable generation technique that uses class-conditional language models as discriminators to guide text generation toward or away…
gated linear unit, transformer ffn
Activation functions are the reason depth means anything. Stack a hundred linear layers with no nonlinearity between them and the whole thing collapses algebraically into a single…
swiglu, activation
GELU (Gaussian Error Linear Unit) and SwiGLU are activation functions that outperform ReLU in transformer architectures through smooth, probabilistic gating mechanisms — where…
neural architecture
Activation functions are the reason depth means anything. Stack a hundred linear layers with no nonlinearity between them and the whole thing collapses algebraically into a single…