Gradient Flow Preservation
model training
Gradient Flow Preservation is a design principle for pruning and sparse training — ensuring that removing weights does not disrupt the backpropagation signal, keeping gradient…
519 technical terms and definitions
model training
Gradient Flow Preservation is a design principle for pruning and sparse training — ensuring that removing weights does not disrupt the backpropagation signal, keeping gradient…
gradient flow stability in deep networks prediction, gradient flow stability, flow stability deep, stability deep networks, deep networks prediction, gradient flow
Gradient Flow Stability in Deep Networks Prediction with Machine Learning Introduction & Motivation Gradient Flow Stability in Deep Networks Prediction with Machine Learning…
Evolution Strategies for Gradient-Free Meta-Learning Introduction & Motivation Evolution Strategies for Gradient-Free Meta-Learning addresses a central problem in fewshot…
Nelder-Mead Simplex Direct Search Algorithm Introduction & Motivation Nelder-Mead Simplex Direct Search Algorithm addresses a central problem in optimization algorithm tuning…
Score-CAM Gradient-Free Visual Activation Mapping Introduction & Motivation Score-CAM Gradient-Free Visual Activation Mapping addresses a central problem in explainability…
ai safety
Gradient Masking is a phenomenon where a defense accidentally or intentionally makes the model's gradients uninformative — causing gradient-based attacks to fail while the model…
Gradient Masking Pitfalls Introduction & Motivation Gradient Masking Pitfalls addresses a central problem in robustness of advrobust models under adversarial conditions: how…
Gradient Masking Pitfalls (Extended Study) Introduction & Motivation Gradient Masking Pitfalls (Extended Study) addresses a central problem in robustness of advrobust models under…
Gradient Masking Pitfalls (Extended Study) Introduction & Motivation Gradient Masking Pitfalls (Extended Study) addresses a central problem in robustness of advrobust models under…
Gradient Norm Expectation for Deep Model Active Selection Introduction & Motivation Gradient Norm Expectation for Deep Model Active Selection addresses a central problem…
generative models
Gradient Penalty is a regularization technique used primarily in GAN training (WGAN-GP) — penalizing the norm of the discriminator's gradient with respect to its input, enforcing…
distributed training
Gradient quantization for communication reduces the precision of gradient tensors before transmitting them between workers in distributed training, dramatically reducing network…
domain adaptation
The Gradient Reversal Layer (GRL) is the ingenious mathematical trick at the beating heart of Adversarial Domain Adaptation (specifically DANN), functioning as a simple, custom…
Gradient Similarity and Dot-Product Task Affinity Introduction & Motivation Gradient Similarity and Dot-Product Task Affinity addresses a central problem in transfer learning…
Gradient Surgery for Multi-Task Learning (PCGrad) Introduction & Motivation Gradient Surgery for Multi-Task Learning (PCGrad) addresses a central problem in multitask learning…
Gradient Surgery for Multi-Task Learning (PCGrad) (Extended Study) Introduction & Motivation Gradient Surgery for Multi-Task Learning (PCGrad) (Extended Study) addresses a central…
Gradient Surgery for Multi-Task Learning (PCGrad) (Extended Study) Introduction & Motivation Gradient Surgery for Multi-Task Learning (PCGrad) (Extended Study) addresses a central…
PCGrad Projected Conflicting Gradients Multi-Task Introduction & Motivation PCGrad Projected Conflicting Gradients Multi-Task addresses a central problem in optimization algorithm…
distributed training
Gradient synchronization is the distributed operation that aligns per-worker gradients into a shared update before parameter step - it ensures data-parallel replicas remain…
GradNorm Loss Balancing Introduction & Motivation GradNorm Loss Balancing addresses a central problem in multitask learning across several related prediction objectives: how…
GradNorm Loss Balancing (Extended Study) Introduction & Motivation GradNorm Loss Balancing (Extended Study) addresses a central problem in multitask learning across several…
GradNorm Loss Balancing (Extended Study) Introduction & Motivation GradNorm Loss Balancing (Extended Study) addresses a central problem in multitask learning across several…
Gradual Domain Adaptation along Intermediate Trajectories Introduction & Motivation Gradual Domain Adaptation along Intermediate Trajectories addresses a central problem…
defects
Grain Boundaries are interfaces separating crystallites (grains) of the same material that have different crystallographic orientations — they are regions of atomic disorder where…
grain boundary analysis, grain boundary character distribution, gbcd, five parameter grain boundary, grain boundary misorientation, grain boundary plane characterization
A grain boundary is only a few atomic spacings wide, yet a connected network of those interfaces can govern the resistivity of an interconnect, the lifetime of a solder joint…
grain boundary density prediction, grain boundary density, boundary density prediction, grain boundary, boundary density, density prediction
Grain Boundary Density Prediction with Machine Learning Introduction & Motivation Grain Boundary Density Prediction with Machine Learning addresses a central problem in grain…
defects
Grain Boundary Energy is the excess free energy per unit area associated with the disordered atomic arrangement at a grain boundary compared to the perfect crystal interior — this…
high-angle grain boundary, defects, crystal defects
High-Angle Grain Boundary (HAGB) is a grain boundary with a misorientation angle exceeding approximately 15 degrees, where the atomic structure is fundamentally disordered…
grain boundary, boundary modeling, csl dft gb gbdb ml
Grain Boundary Modeling Introduction & Motivation Predicting grain boundary properties and segregation enables design of materials with optimized microstructure and mechanical…
defects
Grain Boundary Segregation is the thermodynamically driven accumulation of solute atoms (dopants, impurities, or alloying elements) at grain boundaries where the disordered atomic…
beol
Grain Growth in Copper is the microstructural evolution process where small copper grains coalesce into larger ones — driven by the reduction of grain boundary energy, occurring…
Gram Matrix for Style Representation Introduction & Motivation Gram Matrix for Style Representation addresses a central problem in generative generation…
grammar-based fuzzing
Grammar-Based Fuzzing Introduction & Motivation Grammar-Based Fuzzing addresses a central problem in verification process control and grammar-coverage-percentage prediction: how…
graph neural networks
Grammar-Based Generation is graph generation constrained by production grammars that encode valid construction rules - It guarantees syntactic validity by restricting generation…
gran, graph neural networks
GRAN is a graph-recurrent attention network for autoregressive graph generation - Attention-guided block generation improves scalability and structural coherence of generated…
time series models
Granger causality is a predictive causality test where one series is causal for another if it improves future prediction - Lagged regression comparisons evaluate whether added…
Granger Causality for Time Series Introduction & Motivation Granger Causality for Time Series addresses a central problem in estimating causal effects with causalml methods: how…
Granger Causality for Time Series (Extended Study) Introduction & Motivation Granger Causality for Time Series (Extended Study) addresses a central problem in estimating causal…
Granger Causality for Time Series (Extended Study) Introduction & Motivation Granger Causality for Time Series (Extended Study) addresses a central problem in estimating causal…
granger causality inference, granger causality, causality inference
Granger Causality Inference Introduction & Motivation Granger Causality Inference addresses a central problem in timeseries process control…
Granger Causality Testing Introduction & Motivation Granger Causality Testing addresses a central problem in timeseries forecasting and causal-lag-detection prediction: how…
Granger Causality and Directed Information Flow Introduction & Motivation Granger Causality and Directed Information Flow addresses a central problem in timeseries forecasting…
time series models
Granger Non-Causality is hypothesis testing framework for whether one time series lacks incremental predictive power for another. - It evaluates predictive causality direction…
neural, networks, GNN, message, passing
Graph Neural Networks (GNN) is a class of neural network architectures designed to process graph-structured data through message passing between nodes — enabling learning on…
Graph Adversarial Attack Methods Introduction & Motivation Graph Adversarial Attack Methods addresses a central problem in graph network representation and attack-success-rate…
Graph Adversarial Robustness Testing Introduction & Motivation Graph Adversarial Robustness Testing addresses a central problem in graph network representation…
Graph Attention Explanation Introduction & Motivation Graph Attention Explanation addresses a central problem in explainability interpretation and model understanding: how…
Graph Attention Label Propagation with Edge Softmax Introduction & Motivation Graph Attention Label Propagation with Edge Softmax addresses a central problem in semisupervised…
Graph Attention Network Design Introduction & Motivation Graph Attention Network Design addresses a central problem in graph network representation…
graph attention network node importance prediction, graph attention network, attention network node, network node importance, node importance prediction, graph attention
Graph Attention Network Node Importance Prediction with Machine Learning Introduction & Motivation Graph Attention Network Node Importance Prediction with Machine Learning…