gaussian splatting training
3d vision
Gaussian splatting training is the optimization workflow that fits Gaussian primitive parameters to multi-view images using differentiable rasterization losses - it learns…
15,762 technical terms and definitions
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…
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…
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…
gated linear unit, transformer ffn
GEGLU applies the same gated linear unit (GLU) structure as SwiGLU but uses GELU instead of Swish as the gating activation function, splitting a layer's input into two halves…
neural architecture
GELU (Gaussian Error Linear Unit) weights its input by the cumulative distribution function of the standard normal distribution evaluated at that input, producing a smooth…
Gradient Episodic Memory GEM with Quadratic Programming Introduction & Motivation Gradient Episodic Memory GEM with Quadratic Programming addresses a central problem in continual…
machine learning
Geman-McClure Loss is a robust loss function that strongly discounts the influence of outliers — using the form L(r) = (r^2)/(2(1 + r^2/c^2)) which saturates for large residuals…
foundation model
Gemini is Google's multimodal AI model family designed from the ground up to understand and reason across text, images, audio, video, and code simultaneously, representing…
foundation model
Gemini Vision is Google's family of natively multimodal models — trained from the start on different modalities (images, audio, video, text) simultaneously, rather than stitching…
graph neural networks
GemNet is a geometry-aware molecular graph network for predicting energies and interatomic forces. - It encodes distances and angular interactions so molecular predictions remain…
fairness
Gender swapping is the counterfactual augmentation technique that exchanges gendered terms to test and reduce gender-linked bias effects - it is used for both fairness evaluation…
healthcare ai
Gene-Disease Association Extraction is the biomedical NLP task of automatically identifying relationships between genes, genetic variants, and human diseases from scientific…
healthcare ai
AI medical scribes are speech recognition and NLP systems that automatically document clinical encounters — listening to doctor-patient conversations, extracting key information…
gene editing precision, gene editing, editing precision
Gene Editing Precision Introduction & Motivation Gene Editing Precision addresses a central problem in biotech process control and editing-accuracy-percentage prediction: how…
genealogy tracking data completeness prediction machine learning, genealogy tracking, data completeness prediction, mes, genealogy tracking data completeness prediction
Genealogy Tracking Data Completeness Prediction with Machine Learning Introduction & Motivation Genealogy Tracking Data Completeness Prediction with Machine Learning addresses…
explainable ai
Generalized Additive Models with Neural Networks extend the classic GAM framework by replacing spline-based shape functions with neural network sub-models — each f_i(x_i) is…
generation-recombination noise prediction, generation-recombination noise, noise prediction
Generation-Recombination Noise Prediction with Machine Learning Introduction & Motivation Generation-Recombination Noise Prediction with Machine Learning addresses a central…
gail, imitation learning
GAIL (Generative Adversarial Imitation Learning) is an imitation learning algorithm that uses a GAN-like framework to match the agent's state-action distribution to the expert's…
generative adversarial networks, gan training, generator discriminator, image synthesis gan
The generative adversarial network framework was introduced as a way to train a generative model without requiring an explicit, tractable likelihood function, instead using…
generator discriminator training, gan mode collapse, stylegan image synthesis, adversarial training
Generative Adversarial Networks (GANs) are the generative modeling framework where two neural networks — a generator that creates synthetic data and a discriminator that…
stylegan3 image synthesis, gan training stability, progressive growing gan, modern gan variants
Generative Adversarial Networks (GAN) Modern Variants is the evolution of adversarial generative models from the original min-max framework to sophisticated architectures capable…
gan discriminator generator, wasserstein gan training stability, gan mode collapse solution, conditional gan image generation
Generative Adversarial Networks (GANs) are the class of deep generative models consisting of two competing neural networks — a generator that synthesizes realistic data…
generative adversarial network synthesis prediction, generative adversarial network, adversarial network synthesis, network synthesis prediction, generative adversarial
Generative Adversarial Network Synthesis Prediction with Machine Learning Introduction & Motivation Generative Adversarial Network Synthesis Prediction with Machine Learning…
generative adversarial network ts, generative adversarial network, adversarial network ts, generative adversarial, adversarial network, network ts
Generative Adversarial Network TS Introduction & Motivation Generative Adversarial Network TS addresses a central problem in timeseries process control…
generative adversarial, networks adversarial generative, 1d cifar dcgan esrgan fid gan, generative adversarial networks & adversarial generative modeling, adversarial networks
Adversarial generative modeling, the broader category GANs belong to, trains a generative model using an adversarial signal from a separate discriminating network rather than…
Generative Adversarial Networks (GAN) Introduction & Motivation Generative Adversarial Networks (GAN) addresses a central problem in generative modeling of diffusion data: how…
generative adversarial, networks gan architecture, cifar cnn fid gan is mnist, generative adversarial networks gan architecture & adversarial training, networks gan
GAN architecture pairs a generator network, which maps random noise input to a generated sample, with a discriminator network, which takes either a real or generated sample as…
Generative Adversarial Networks (GAN) (Extended Study) Introduction & Motivation Generative Adversarial Networks (GAN) (Extended Study) addresses a central problem in generative…
Generative Adversarial Networks (GAN) (Extended Study) Introduction & Motivation Generative Adversarial Networks (GAN) (Extended Study) addresses a central problem in generative…
Generative adversarial network variants address specific weaknesses of the original formulation: Wasserstein GAN (WGAN) and its gradient-penalty variant (WGAN-GP) replace…
Generative Adversarial Network Design Introduction & Motivation Generative Adversarial Network Design addresses a central problem in generative generation…
autoregressive vs diffusion, what is generative ai
Generative AI is the branch of AI that produces new content — text, images, audio, code, video — rather than classifying or predicting a label for content that already exists.…
llm hardware design, ai code generation verilog, gpt for chip design, automated rtl generation
Generative AI for RTL Design is the application of large language models and generative AI to automatically create, optimize, and verify hardware description code — where models…
ai generated circuit design, generative adversarial networks eda, variational autoencoder circuits, generative models synthesis
Generative Design Methods are the application of generative AI models including GANs, VAEs, and diffusion models to automatically create chip layouts, circuit topologies…
Generative Model Transfer Learning Introduction & Motivation Generative Model Transfer Learning addresses a central problem in transfer learning and (target) adaptation: how…
data analysis
Generative Models for Defect Synthesis is the use of generative AI (GANs, VAEs, diffusion models) to create realistic synthetic defect images — augmenting limited real defect…
Deep Generative Replay DGR with Scholar-Generator Networks Introduction & Motivation Deep Generative Replay DGR with Scholar-Generator Networks addresses a central problem…
generics parameterized types, generics parameterized, parameterized types
Generics Parameterized Types Introduction & Motivation Generics Parameterized Types addresses a central problem in programming process control and type-erasure-runtime-info…
genetic algorithm design space exploration, genetic algorithm design, algorithm design space, design space exploration, genetic algorithm, algorithm design, design space
Genetic Algorithm Design Space Exploration with Machine Learning Introduction & Motivation Genetic Algorithm Design Space Exploration with Machine Learning addresses a central…
genetic algorithm evolutionary optimization and population evolution, genetic algorithm evolutionary, algorithm evolutionary optimization, genetic algorithm
Genetic Algorithm Evolutionary Optimization and Population Evolution Introduction & Motivation Genetic Algorithm Evolutionary Optimization and Population Evolution addresses…
genetic programming code generation, genetic programming code, programming code generation, genetic programming, programming code, code generation
Genetic Programming Code Generation Introduction & Motivation Genetic Programming Code Generation addresses a central problem in ml process control…
healthcare ai
Genomic variant interpretation uses AI to assess the clinical significance of genetic variants — analyzing DNA sequence changes to determine whether they are benign, pathogenic…
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 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…
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…