G (16 terms)
GAN
Two-network setup where generator fools a discriminator.
Advanced
Gating Network
Chooses which experts process each token.
Intermediate
Generalization
How well a model performs on new data drawn from the same (or similar) distribution as training.
Intermediate
Generative Model
Models that learn to generate samples resembling training data.
Advanced
Gesture Recognition
Interpreting human gestures.
Frontier
Global Minimum
Lowest possible loss.
Intermediate
Gradient
Direction of steepest ascent of a function.
Advanced
Gradient Clipping
Limiting gradient magnitude to prevent exploding gradients.
Intermediate
Gradient Descent
Iterative method that updates parameters in the direction of negative gradient to minimize loss.
Intermediate
Gradient Leakage
Recovering training data from gradients.
Intermediate
Gradient Noise
Variability introduced by minibatch sampling during SGD.
Intermediate
Graph Attention Network
GNN using attention to weight neighbor contributions dynamically.
Intermediate
Graph Convolution
Extension of convolution to graph domains using adjacency structure.
Intermediate
Graph Neural Network
Neural networks that operate on graph-structured data by propagating information along edges.
Intermediate
Grounding
Constraining outputs to retrieved or provided sources, often with citation, to improve factual reliability.
Intermediate
Guardrails
Rules and controls around generation (filters, validators, structured outputs) to reduce unsafe or invalid behavior.
Intermediate