geodesic flow kernel
domain adaptation
The Geodesic Flow Kernel (GFK) is an extraordinarily elegant, advanced mathematical approach to early Domain Adaptation that explicitly models the jarring shift between a Source…
1,045 technical terms and definitions
domain adaptation
The Geodesic Flow Kernel (GFK) is an extraordinarily elegant, advanced mathematical approach to early Domain Adaptation that explicitly models the jarring shift between a Source…
Geographic Information Systems: Geodesy, Map Projections, and Spatial Analysis A geographic information system, or GIS, connects observations to location. It stores spatial…
geographic load balancing, geographic load, load balancing
Geographic Load Balancing Introduction & Motivation Geographic Load Balancing addresses a central problem in ml-inference process control and latency-to-user-milliseconds…
Geology: Plate Tectonics, Rocks, and Earth Systems Geology reconstructs Earth's history and explains its active surface through physical, chemical, and biological processes. Plate…
neural architecture
Geometric Deep Learning (GDL) is the unifying mathematical framework that explains how all major neural network architectures — CNNs, GNNs, Transformers, and manifold-learning…
equivariant neural network, symmetry neural, group equivariance, se3 equivariant
Geometric Deep Learning is the theoretical framework and set of architectures that incorporate geometric symmetries (translation, rotation, permutation, scale) as inductive biases…
graph neural network equivariance, se3 equivariant network, point cloud equivariance, e3nn equivariant
Geometric Deep Learning: SE(3)-Equivariant Networks — respecting symmetries in molecular, crystallographic, and point-cloud models Geometric deep learning incorporates domain…
geometric average, compound annual growth rate, CAGR, nth root of product, multiplicative mean, AM-GM inequality, log-average
The geometric mean is the central value of a set of n positive numbers defined as the nth root of their product — multiply all the values together, then take the root whose index…
computational geometry, semiconductor geometry, polygon operations, level set, minkowski, opc geometry, design rule checking, drc, cmp modeling, resist modeling
Semiconductor Manufacturing Process Geometry and Computational Geometry Mathematical Modeling 1. The Fundamental Geometric Challenge Modern semiconductor manufacturing operates…
industry
Geopolitical risk in semiconductors refers to the impact of trade policies, export controls, national security concerns, and regional conflicts on the global semiconductor supply…
Geotechnical Engineering: Soil Mechanics, Foundation Design, and Slope Stability Geotechnical engineering applies soil and rock mechanics to design foundations, retaining…
geothermal energy extraction, geothermal energy, energy extraction
Geothermal Energy Extraction Introduction & Motivation Geothermal Energy Extraction addresses a central problem in energy-generation process control and heat-extraction-efficiency…
channel, PMOS, process, integration, hetero
Germanium Channel PMOS Process and Integration is the use of germanium as the channel material for PMOS transistors — leveraging higher hole mobility to improve PMOS performance…
germanium channel, what is germanium channel
A germanium-channel transistor uses germanium in the region where gate-controlled carriers conduct. That placement differs from using silicon-germanium only in source/drain…
germanium incorporation in sige prediction, germanium incorporation sige, incorporation sige prediction, germanium incorporation, incorporation sige, sige prediction
Germanium Incorporation in SiGe Prediction with Machine Learning Introduction & Motivation Germanium Incorporation in SiGe Prediction with Machine Learning addresses a central…
ge photodiode, ge pd, infrared photodetector silicon, heterojunction photodetector
Germanium Photodetectors in Silicon Photonics Silicon is transparent at the infrared wavelengths used for optical communication (1310 nm, 1550 nm, the C-band), so silicon itself…
germanium pmos channel strain relaxation prediction, germanium pmos channel, pmos channel strain, channel strain relaxation, strain relaxation prediction
Germanium PMOS Channel Strain Relaxation Prediction with Machine Learning Introduction & Motivation Germanium PMOS Channel Strain Relaxation Prediction with Machine Learning…
germanium pmos mobility prediction, germanium pmos mobility, pmos mobility prediction, germanium pmos, pmos mobility, mobility prediction
Germanium pMOS Mobility Prediction with Machine Learning Introduction & Motivation Germanium pMOS Mobility Prediction with Machine Learning addresses a central problem…
gesture recognition real-time, gesture recognition, recognition real-time
Gesture Recognition Real-Time Introduction & Motivation Gesture Recognition Real-Time addresses a central problem in gesture-recognition process control…
gesture recognition robot, gesture recognition, recognition robot
Gesture Recognition Robot Introduction & Motivation Gesture Recognition Robot addresses a central problem in robotics process control and gesture-interpretation-control-command…
Gesture and Pose Recognition Introduction & Motivation Gesture and Pose Recognition addresses a central problem in multimodal learning and gesture-accuracy-classification…
manufacturing operations
Getis-Ord Statistic is a local spatial statistic used to identify where significant hot spots and cold spots occur - It is a core method in modern semiconductor wafer-map…
getter material activation efficiency prediction machine learning, getter material, activation efficiency prediction, getter material activation efficiency prediction
Getter Material Activation Efficiency Prediction with Machine Learning Introduction & Motivation Getter Material Activation Efficiency Prediction with Machine Learning addresses…
packaging
Getter materials is the reactive materials placed inside sealed packages to absorb residual gases and maintain required internal atmosphere - they are commonly used in vacuum…
diffusion
Gettering is the process of trapping metallic impurities (Fe, Cu, Ni, Cr, Co) away from electrically active device regions on the wafer front side by creating preferential…
process
Gettering is the process of intentionally creating defect-rich trap regions in non-critical areas of a silicon wafer to capture and immobilize harmful metallic impurities (Fe, Cu…
gettering process metal contamination reduction prediction, gettering process metal, process metal contamination, metal contamination reduction, gettering process
Gettering Process Metal Contamination Reduction Prediction with Machine Learning Introduction & Motivation Gettering Process Metal Contamination Reduction Prediction with Machine…
gev, audio & speech
GEV Beamforming is generalized eigenvalue beamforming that maximizes signal-to-noise ratio from spatial covariance matrices - It selects filter weights that optimize target versus…
gfpgan, computer vision
GFPGAN is the Generative Facial Prior GAN model for blind face restoration using a pretrained facial prior network - it reconstructs degraded faces by leveraging learned…
c, inference
GGML is a C/C++ tensor library designed for efficient machine learning inference on consumer hardware — created by Georgi Gerganov as the original backend for llama.cpp, GGML…
llama cpp, ggml, local llm inference, quantized llm, llama-server api, model quantization
GGUF (GPT-Generated Unified Format) is the modern model file format used by llama.cpp and related local inference stacks to package LLM weights, tokenizer assets, and runtime…
computer vision
Ghost Convolution is a convolution that generates feature maps using fewer parameters by producing a subset of features through standard convolution and then generating "ghost"…
model optimization
Ghost Module is an efficient feature-generation block that creates additional channels using cheap linear operations - It approximates redundant feature maps at lower cost than…
gibbs sampling markov chain prediction, gibbs sampling markov, sampling markov chain, markov chain prediction, gibbs sampling, sampling markov, markov chain, chain prediction
Gibbs Sampling Markov Chain Prediction with Machine Learning Introduction & Motivation Gibbs Sampling Markov Chain Prediction with Machine Learning addresses a central problem…
gigahertz barrier, what is gigahertz barrier
The gigahertz barrier was a symbolic processor-frequency milestone, not a physical discontinuity. One gigahertz means one billion cycles per second, corresponding to…
global interpreter lock, python gil, cpython gil, python threading gil, gil python multithreading, free-threaded python, python nogil, python cpu parallelism, python thread safety
The GIL—Python's Global Interpreter Lock—is a single mutex that prevents more than one thread from executing CPython bytecode simultaneously, a design choice made in 1992 that…
gin, graph neural networks
GIN is a graph-isomorphism network that uses injective neighborhood aggregation to strengthen graph discrimination - Summation-based aggregation with multilayer perceptrons…
testing, quality
Giskard is an open-source AI quality testing framework that automatically scans ML models and LLM applications for vulnerabilities, bias, hallucinations, and performance…
github, version control, branching, commits, pull requests, code review, merge
Git best practices establish version control workflows that enable safe collaboration, clean history, and reliable code management — using branching strategies, commit…
version control, code
Git is the standard distributed version control system — used by 95% of developers to track changes in source code, enabling multiple people to work on the same project…
message, generate
AI Git Commit Messages is the automated generation of meaningful, standardized commit messages from staged code changes (git diff) — replacing the pervasive developer habit…
mlops
Git LFS (Large File Storage) is a specialized Git extension protocol that transparently replaces large binary files (trained model weights, datasets, compiled binaries…
hosting, collaboration
Mercurial (hg): Distributed Version Control Overview Mercurial is a distributed version control system (DVCS), released in 2005 (the same year as Git). Like Git, it allows every…
ci cd pipeline, continuous integration, workflow automation, devops, github workflow
GitHub Actions is GitHub's native CI/CD and workflow automation platform that executes YAML-defined pipelines in response to repository events — enabling teams to automate…
code ai
GitHub Copilot is an AI pair programmer providing real-time code suggestions and completions in the IDE. How it works: Analyzes context (current file, open files, comments…
devops, self host
GitLab is a complete DevOps platform delivered as a single application — providing Git repository hosting, built-in CI/CD pipelines (widely considered the gold standard)…
gitops declarative deployment, gitops declarative, declarative deployment
GitOps Declarative Deployment Introduction & Motivation GitOps Declarative Deployment addresses a central problem in cloud process control and deployment-from-git-repository…
Glaciology: Ice Dynamics, Mass Balance, and Climate Records Glaciology studies snow, glaciers, ice sheets, sea ice, frozen ground, and the evidence they preserve about climate.…
glam, generalist language model, foundation model
GLaM (Generalist Language Model) is Google's sparse Mixture of Experts language model containing 1.2 trillion parameters that demonstrated how MoE architectures can achieve…
glass core packaging, tgv through glass via substrate
A glass core substrate replaces the organic resin panel at the center of a chip package with a sheet of actual glass, and that one material swap is what lets packages hold flatter…