27,049 technical terms and definitions
adaboost adaptive boosting prediction, adaboost adaptive boosting, adaptive boosting prediction, adaboost adaptive, adaptive boosting, boosting prediction
AdaBoost Adaptive Boosting Prediction with Machine Learning Introduction & Motivation AdaBoost Adaptive Boosting Prediction with Machine Learning addresses a central problem…
AdaDelta Dimensionless Adaptive Learning Rate Introduction & Motivation AdaDelta Dimensionless Adaptive Learning Rate addresses a central problem in optimization algorithm tuning…
optimization
Adafactor is a memory-efficient adaptive optimizer designed for training large models — replacing Adam's per-parameter second moment buffer with a factored approximation, reducing…
adagrad accumulated gradient scaling and adaptive features, adagrad accumulated gradient, accumulated gradient scaling, gradient scaling adaptive, scaling adaptive features
AdaGrad Accumulated Gradient Scaling and Adaptive Features Introduction & Motivation AdaGrad Accumulated Gradient Scaling and Adaptive Features addresses a central problem…
AdaGrad Adaptive Gradient Subgradient Scaling Introduction & Motivation AdaGrad Adaptive Gradient Subgradient Scaling addresses a central problem in optimization algorithm tuning…
adamw, optimizer, weight decay, training, lr, momentum
An optimizer is the rule that turns gradients into weight updates. Backpropagation tells you the direction of steepest descent for every parameter; the optimizer decides how far…
model training
Adam optimizer combines momentum and adaptive learning rates, the default choice for most deep learning. Algorithm: Maintains exponential moving averages of gradient (m)…
adamw, rmsprop, optimizer comparison
An optimizer is the rule that turns gradients into weight updates. Backpropagation tells you the direction of steepest descent for every parameter; the optimizer decides how far…
adam optimizer adaptive learning rate and moment estimation, adam optimizer adaptive, optimizer adaptive learning, adaptive learning rate, learning rate moment, rate moment
Adam Optimizer Adaptive Learning Rate and Moment Estimation Introduction & Motivation Adam Optimizer Adaptive Learning Rate and Moment Estimation addresses a central problem…
Adam Optimizer Parameter Tuning Introduction & Motivation Adam Optimizer Parameter Tuning addresses a central problem in optimization algorithm tuning and improvement: how…
model training
An optimizer is the rule that turns gradients into weight updates. Backpropagation tells you the direction of steepest descent for every parameter; the optimizer decides how far…
AdamW Optimizer with Decoupled Weight Decay Introduction & Motivation AdamW Optimizer with Decoupled Weight Decay addresses a central problem in optimization algorithm tuning…
computer vision
AdamW is the universally adopted, mathematically corrected optimizer for training Vision Transformers and all modern Transformer-based architectures — critically fixing…
continual learning
Adapter-based continual learning is continual learning that adds lightweight adapter modules for each new task instead of retraining full models - Adapters isolate task updates…
AdapterFusion for Dynamic Multi-Task Knowledge Transfer Introduction & Motivation AdapterFusion for Dynamic Multi-Task Knowledge Transfer addresses a central problem in transfer…
fine-tuning
Adapter layers are small trainable modules inserted into frozen pretrained models, enabling parameter-efficient fine-tuning by learning task-specific transformations without…
adapter fine tuning, lora, houlsby adapter, parallel adapter, parameter efficient fine tuning, peft
Adapter tuning customizes a frozen or mostly frozen pretrained model by training small task-specific parameter modules. It lowers optimizer memory, communication, storage…
learnable activation, prelu
Adaptive activation refers to activation functions whose shape or parameters are learned during training rather than fixed in advance. This makes the network more flexible because…
design
Adaptive aging compensation is the runtime control strategy that counteracts performance loss from device aging using monitored silicon condition - it adjusts voltage, frequency…
ai safety
Adaptive Attacks are adversarial attacks specifically designed to overcome a particular defense mechanism — tailoring the attack strategy to exploit the defense's specific…
Adaptive Dynamic Batch Sizing in Active Learning Introduction & Motivation Adaptive Dynamic Batch Sizing in Active Learning addresses a central problem in {subject} learning…
abb, design
Adaptive body bias is the dynamic control technique that adjusts transistor body voltage to tune threshold voltage after manufacturing and during operation - it improves yield…
design & verification
Adaptive Body Bias is dynamic body-bias control that adjusts threshold tuning based on silicon condition and operating state - It compensates process and environmental variation…
adaptive body bias effectiveness prediction, adaptive body bias, body bias effectiveness, bias effectiveness prediction, adaptive body, body bias, bias effectiveness
Adaptive Body Bias Effectiveness Prediction with Machine Learning Introduction & Motivation Adaptive Body Bias Effectiveness Prediction with Machine Learning addresses a central…
adaptive body bias (abb) for supply noise margin improvement, adaptive body bias, body bias (abb), bias (abb) supply, (abb) supply noise, supply noise margin, noise margin improvement
Adaptive Body Bias (ABB) for Supply Noise Margin Improvement Introduction & Motivation Adaptive Body Bias (ABB) for Supply Noise Margin Improvement addresses a central problem…
design
Adaptive body biasing (ABB) is a closed-loop technique that dynamically adjusts the body bias voltage of transistors based on real-time measurements of process, temperature…
adaptive computation time, act, optimization
Adaptive Computation Time (ACT) is a mechanism introduced by Alex Graves that allows recurrent neural networks and transformers to learn how many computational steps to perform…
spc
Adaptive control charts is the SPC approach that dynamically adjusts sampling or decision parameters based on current process behavior - it balances detection speed and monitoring…
adaptive control convergence prediction, adaptive control convergence, control convergence prediction, adaptive control, control convergence, convergence prediction
Adaptive Control Convergence Prediction with Machine Learning Introduction & Motivation Adaptive Control Convergence Prediction with Machine Learning addresses a central problem…
adaptive control learning, adaptive control, control learning
Adaptive Control Learning Introduction & Motivation Adaptive Control Learning addresses a central problem in robotics process control and parameter-estimation-online prediction…
adaptive control system identification prediction, adaptive control system, control system identification, system identification prediction, adaptive control
Adaptive Control System Identification Prediction with Machine Learning Introduction & Motivation Adaptive Control System Identification Prediction with Machine Learning addresses…
Adaptive Coordinate Descent with Gauss-Southwell Rule Introduction & Motivation Adaptive Coordinate Descent with Gauss-Southwell Rule addresses a central problem in optimization…
adaptive discriminator augmentation, ada, generative models
Adaptive Discriminator Augmentation (ADA) is a training technique for GANs that applies a carefully controlled set of augmentations to both real and generated images before…
doe
Adaptive DOE is a design of experiments approach that dynamically modifies the experimental plan based on incoming results — using algorithms (Bayesian optimization, reinforcement…
signal & power integrity
Adaptive Equalization is equalization that automatically adjusts parameters in response to channel and noise variation - It maintains link quality as operating conditions drift…
adaptive filter convergence rate prediction, adaptive filter convergence, filter convergence rate, convergence rate prediction, adaptive filter, filter convergence
Adaptive Filter Convergence Rate Prediction with Machine Learning Introduction & Motivation Adaptive Filter Convergence Rate Prediction with Machine Learning addresses a central…
Adaptive Fine-Tuning Strategies Introduction & Motivation Adaptive Fine-Tuning Strategies addresses a central problem in transfer learning and {target} adaptation: how to Apply…
optimization
Adaptive Inference is the dynamic adjustment of a neural network's computational effort based on the difficulty of each input — allocating more computation to hard inputs and less…
model optimization
Adaptive Inference is runtime mechanisms that adapt model pathways, precision, or depth to meet efficiency targets - It supports context-aware tradeoffs between quality…
generative models
AdaIN (Adaptive Instance Normalization) is a style transfer technique that transfers style by matching the mean and variance of content feature maps to those of style feature maps…
generative models
Adaptive instance normalization in StyleGAN is the modulation mechanism that scales and shifts normalized feature maps using style parameters derived from latent codes - it is…
architecture
Adaptive Layer Depth is a dynamic neural network architecture technique where the number of transformer layers executed varies per input token or sample, allowing confident…
GradNorm Gradient Normalization for Multi-Task Balances Introduction & Motivation GradNorm Gradient Normalization for Multi-Task Balances addresses a central problem…
nlp
Adaptive Masking refers to strategies where the masking rate or pattern changes during training based on the model's performance or curriculum — focusing learning on "hard" tokens…
adaptive metrology sampling plan optimization machine learning, adaptive metrology, sampling plan optimization, adaptive metrology sampling plan optimization
Adaptive Metrology Sampling Plan Optimization with Machine Learning Introduction & Motivation Adaptive Metrology Sampling Plan Optimization with Machine Learning addresses…
Adaptive Manifold Mixup for Semi-Supervised Classification Introduction & Motivation Adaptive Manifold Mixup for Semi-Supervised Classification addresses a central problem…
adaptive model concept drift, adaptive model concept, model concept drift, adaptive model, model concept, concept drift
Adaptive Model Concept Drift Introduction & Motivation Adaptive Model Concept Drift addresses a central problem in timeseries process control and drift-adaptation-model-update…
rag
Adaptive RAG is the retrieval-augmented generation design that dynamically adjusts retrieval depth, tools, and generation strategy based on query difficulty and confidence…
rag
Adaptive RAG is a routing strategy that selects retrieval depth and generation pathways based on query complexity - It is a core method in modern RAG and retrieval execution…
adaptive routing latency and path prediction accuracy, adaptive routing latency, routing latency path, latency path prediction, path prediction accuracy, adaptive routing, routing latency
Adaptive Routing Latency and Path Prediction Accuracy Introduction & Motivation Adaptive Routing Latency and Path Prediction Accuracy addresses a central problem in network…