dreambooth
generative models
DreamBooth fine-tunes diffusion models to generate specific subjects or styles from few example images. Approach: Fine-tune entire model (or LoRA) on images of subject with unique…
1,821 technical terms and definitions
generative models
DreamBooth fine-tunes diffusion models to generate specific subjects or styles from few example images. Approach: Fine-tune entire model (or LoRA) on images of subject with unique…
generative models
DreamBooth is the fine-tuning approach that personalizes a diffusion model to a subject concept using instance images and class-preservation regularization - it can produce strong…
multimodal ai
DreamBooth is a personalization method that fine-tunes diffusion models to generate a specific subject from text prompts - It enables subject-consistent generation from a small…
reinforcement learning
Dreamer is a model-based reinforcement learning agent that achieves state-of-the-art sample efficiency by learning a world model from sensory inputs and training a policy entirely…
reinforcement learning advanced
Dreamer is a model-based reinforcement-learning family that trains policies from imagined latent trajectories - Dreamer learns latent dynamics and optimizes actor-critic…
Dreamer Latent Imagination RL Introduction & Motivation Dreamer Latent Imagination RL addresses a central problem in sequential decision making via deeprl: how to Learn a policy…
Dreamer Latent Imagination RL (Extended Study) Introduction & Motivation Dreamer Latent Imagination RL (Extended Study) addresses a central problem in sequential decision making…
Dreamer Latent Imagination RL (Extended Study) Introduction & Motivation Dreamer Latent Imagination RL (Extended Study) addresses a central problem in sequential decision making…
3d vision
DreamFusion is the text-to-3D optimization framework that distills 2D diffusion priors into a 3D representation through rendered views - it introduced score-distillation guidance…
multimodal ai
DreamFusion is a text-to-3D optimization method using 2D diffusion priors to supervise 3D scene generation - It creates 3D content without paired text-3D training data. What Is…
monitoring, shift
Drift Monitoring for data drift and model drift detects when input distributions or model performance change over time, triggering alerts for investigation and potential…
Feature Store Online Drift Monitoring and Versioning Introduction & Motivation Feature Store Online Drift Monitoring and Versioning addresses a central problem in {subject}…
data drift, concept drift, feature drift, model drift, distribution shift detection
Drift detection definition and system boundary. Drift detection identifies statistically and operationally meaningful change between a reference distribution or relationship…
drift-diffusion transport, drift-diffusion model, semiconductor carrier transport, drift diffusion equations, semiconductor continuity equations, quasi-fermi transport, TCAD drift diffusion
Drift–diffusion transport is the continuum model that converts electric fields, carrier-density gradients, generation, recombination, and contact injection into semiconductor…
production
Drift monitoring tracks slow, gradual changes in equipment performance, process parameters, or output characteristics over time, enabling predictive maintenance and proactive…
drift-field transistor, graded base transistor, Herbert Kroemer, base transit time, built-in electric field, RCA drift transistor, 1953 drift transistor theory
A drift transistor is a bipolar junction transistor whose base is doped unevenly, heavily near the emitter and lightly near the collector, so that a built-in electric field pushes…
Drift Detection vs Anomaly Detection Introduction & Motivation Drift Detection vs Anomaly Detection addresses a central problem in anomaly detection and {target} scoring: how…
diffusion
Drive-in is a thermal step that redistributes dopants already introduced into silicon, spreading them deeper and sideways to form the required electrical profile. The heat does…
drive-in diffusion dopant profile tail prediction, drive-in diffusion dopant, diffusion dopant profile, dopant profile tail, profile tail prediction, dopant profile
Drive-In Diffusion Dopant Profile Tail Prediction with Machine Learning Introduction & Motivation Drive-In Diffusion Dopant Profile Tail Prediction with Machine Learning addresses…
drone flight control stability, drone flight control, flight control stability, drone flight, flight control, control stability
Drone Flight Control Stability Introduction & Motivation Drone Flight Control Stability addresses a central problem in drones process control and control-loop-frequency-hz…
drop, evaluation
DROP is a reading comprehension benchmark requiring discrete reasoning such as counting, comparison, and arithmetic over text - It is a core method in modern AI evaluation…
numerical reasoning, reading comprehension
DROP (Discrete Reasoning Over Paragraphs) is a reading comprehension benchmark requiring numerical reasoning operations like addition, counting, and sorting over text passages.…
drop height survivability prediction, drop height survivability, height survivability prediction, drop height, height survivability, survivability prediction
Drop Height Survivability Prediction with Machine Learning Introduction & Motivation Drop Height Survivability Prediction with Machine Learning addresses a central problem…
yield enhancement
Drop-In is a temporary replacement of product patterns with dedicated monitor structures at selected wafer sites - It provides focused process diagnostics at strategic locations.…
metrology
Spectroscopic ellipsometry and inline optical wafer metrology constitute the non-destructive physical measurement and defect detection disciplines that govern yield control across…
failure analysis advanced
Semiconductor failure analysis (FA), non-destructive inspection, and advanced electrical fault isolation (EFI) constitute the essential metrological and diagnostic disciplines…
inference, approximate
Dropout is the specific regularization technique of randomly zeroing a fraction of a layer's activations on every training step, forcing the network to never depend on any single…
dropout random neuron deactivation and regularization, dropout random neuron, random neuron deactivation, neuron deactivation regularization, dropout random, random neuron
Dropout Random Neuron Deactivation and Regularization Introduction & Motivation Dropout Random Neuron Deactivation and Regularization addresses a central problem in dropout…
Dropout Rate Optimization Introduction & Motivation Dropout Rate Optimization addresses a central problem in optimization algorithm tuning and improvement: how to Optimize…
dropout layer, dropout rate
Dropout — a regularization technique that randomly deactivates neurons during training, forcing the network to learn redundant representations and reducing overfitting. How It…
dropout layer, dropout rate, spatial dropout, droppath, stochastic depth
Dropout regularization randomly masks a fraction of activations during training to discourage brittle co-adaptation. It improves generalization in many models by exposing each…
weight decay, overfitting prevention, stochastic regularization, deep network generalization
Dropout and Regularization Techniques — Regularization methods prevent deep networks from memorizing training data, ensuring learned representations generalize to unseen examples…
dropout and regularization techniques, dropout regularization techniques, dropout regularization, regularization techniques
Dropout and Regularization Techniques Introduction & Motivation Dropout and Regularization Techniques addresses a central problem in ml-training process control…
Dropout and Regularization Introduction & Motivation Dropout and Regularization addresses a central problem in vision processing and overfitting-prevention prediction: how…
dropout regularization, regularization stochastic, bert cifar gpt passed vgg, dropout & regularization stochastic depth, dropout regularization stochastic, regularization stochastic depth
Dropout & Regularization: Stochastic Depth Introduction & Motivation Dropout: randomly zero activations during training. Stochastic depth: randomly skip residual blocks.…
dropout regularization training, dropout regularization, regularization training
Dropout Regularization Training Introduction & Motivation Dropout Regularization Training addresses a central problem in systems process control…
recommendation systems
DropoutNet is a recommendation model that applies dropout-style feature masking to improve cold-start robustness - By randomly masking collaborative features during training…
recommendation systems
DropoutNet Cold is a cold-start recommendation strategy that drops collaborative embeddings during training. - It teaches models to rely on side features when user or item…
moe
Dropped Tokens are tokens that are discarded in sparse Mixture of Experts models when their selected expert has exceeded its processing capacity buffer — causing information loss…
discovery, AI, generative, models, molecule, design, synthesis
Drug Discovery AI Generative Models is applying deep learning to design novel drug molecules with desired properties, accelerating discovery and reducing costs in pharmaceutical…
drug delivery microneedle array yield prediction, drug delivery microneedle, delivery microneedle array, microneedle array yield, array yield prediction, drug delivery
Drug Delivery Microneedle Array Yield Prediction with Machine Learning Introduction & Motivation Drug Delivery Microneedle Array Yield Prediction with Machine Learning addresses…
AI drug discovery, virtual screening, generative molecule design, clinical trial attrition, lead optimization, Eroom's law, halicin
Drug discovery is the process of finding a molecule that safely changes a disease-relevant biological target and then proving, through years of testing, that it helps patients; AI…
graph neural network molecule, generative molecule design, docking score prediction, admet property prediction
Deep Learning for Drug Discovery: From Property Prediction to Generative Design — accelerating small-molecule drug development Deep learning accelerates drug discovery: predicting…
drug discovery quantum, drug discovery, discovery quantum
Drug Discovery Quantum Introduction & Motivation Drug Discovery Quantum addresses a central problem in quantum process control and drug-discovery-protein-binding prediction: how…
healthcare ai
Personalized medicine AI uses machine learning to tailor medical treatment to individual patient characteristics — analyzing genomic data, biomarkers, medical history…
healthcare ai
Drug-Drug Interaction Extraction (DDI Extraction) is the NLP task of automatically identifying pairs of drugs and classifying the type of interaction between them from biomedical…
drug ligand interaction prediction, drug ligand, ligand interaction, 3d admet dude kiba ml rmsd, drug-ligand interaction, interaction prediction
Drug-Ligand Interaction Prediction Introduction & Motivation Predicting binding affinity between drugs and target proteins accelerates drug discovery. ML models learn interaction…
healthcare ai
Drug-Target Interaction (DTI) Prediction is the computational task of predicting whether and how strongly a drug molecule binds to a protein target — modeling the molecular…
supply chain & logistics
Drum-Buffer-Rope is a TOC scheduling method where bottleneck pace controls release and protective buffers absorb variability - It synchronizes flow to the constraint while…
manufacturing operations
Drum Buffer Rope is a constraint-focused scheduling method that synchronizes system flow to the pace of the bottleneck - It coordinates release and protection policies around…