1,706 technical terms and definitions
adapting models across different fabrication facilities, adapting models across, models across different, across different fabrication, different fabrication facilities, models across
Adapting models across different fabrication facilities Introduction & Motivation Adapting models across different fabrication facilities addresses a central problem in Machine…
domain shift, fine tuning domain, domain generalization, out of distribution
Domain Adaptation in Deep Learning is the transfer learning technique that adapts a model trained on a source domain (with abundant labeled data) to perform well on a target…
Domain Adaptation Multimodal Introduction & Motivation Domain Adaptation Multimodal addresses a central problem in multimodal learning and domain-transfer-quality alignment: how…
recommendation systems
Domain Adaptation Rec is recommendation adaptation under distribution shift between source and target environments. - It addresses temporal, regional, or platform drift without…
rag
Domain Adaptation Retrieval is methods that adapt retrievers to specific domain language, structure, and relevance criteria - It is a core method in modern engineering execution…
Domain Adaptation in Reinforcement Learning Introduction & Motivation Domain Adaptation in Reinforcement Learning addresses a central problem in reinforcement policy learning…
advanced training
Domain adaptation theory is theoretical framework for learning models that generalize from source to shifted target domains - Generalization bounds combine source error…
domain adaptation and transfer, domain adaptation transfer, domain adaptation, adaptation transfer
Domain Adaptation and Transfer Introduction & Motivation Domain Adaptation and Transfer addresses a central problem in ml-training process control and transfer-efficiency-samples…
domain adaptation visual, domain adaptation, adaptation visual
Domain Adaptation Visual Introduction & Motivation Domain Adaptation Visual addresses a central problem in vision process control and domain-shift-distribution-change prediction…
transfer learning
Domain-Adaptive Pre-training (DAPT) is the process of taking a general-purpose pre-trained model (like BERT) and continuing to pre-train it on a large corpus of unlabeled text…
Domain Adaptation Semi-Supervised Introduction & Motivation Domain Adaptation Semi-Supervised addresses a central problem in semisupervised and source-target-alignment…
Domain-Adversarial Training of Neural Networks DANN Introduction & Motivation Domain-Adversarial Training of Neural Networks DANN addresses a central problem in transfer learning…
domain adaptation, gradient reversal layer, domain adversarial training, unsupervised domain adaptation, domain invariant features
Domain Confusion is an adversarial representation-learning technique for domain adaptation where a feature extractor is trained to make source-domain and target-domain examples…
spatial partitioning parallel, ghost cell exchange, load balancing decomposition, overlapping schwarz method
Domain Decomposition Methods — Domain decomposition divides a computational domain into subdomains assigned to different processors, enabling parallel solution of partial…
domain adaptation
Domain Discriminator is a neural network component used in adversarial domain adaptation that learns to classify whether input features come from the source domain or the target…
transfer learning
Domain generalization (DG) trains machine learning models to perform well on entirely unseen target domains without any access to target domain data during training. Unlike domain…
domain generalization
Domain Generalization (DG) represents the absolute "Holy Grail" of robust artificial intelligence, demanding that a model trained on multiple distinct visual environments…
Domain Generalization Approaches Introduction & Motivation Domain Generalization Approaches addresses a central problem in transfer learning and {target} adaptation: how to Apply…
continual learning
Domain-incremental learning is a continual learning scenario where the model's task structure and output space remain the same, but the input data distribution changes across…
domain adaptation
Domain-Invariant Feature Learning is the core strategy in unsupervised domain adaptation that learns feature representations which are informative for the task while being…
training
Domain mixing is the allocation of training weight across domains such as code science dialogue and general web text - Domain proportions shape specialization versus generality…
Visual and Textual Prompt Tuning for Domain Transfer Introduction & Motivation Visual and Textual Prompt Tuning for Domain Transfer addresses a central problem in transfer…
domain generalization
Domain Randomization is an aggressive, brutally effective data augmentation technique heavily utilized in advanced Robotics and "Sim-to-Real" deep reinforcement learning…
Domain Randomization for Transfer Introduction & Motivation Domain Randomization for Transfer addresses a central problem in transfer learning and {target} adaptation: how…
transfer learning
Domain shift (also called distribution shift) occurs when the statistical distribution of test/deployment data differs from the distribution of training data. It is one of…
Domain Shift and Correction Introduction & Motivation Domain Shift and Correction addresses a central problem in vision processing and distribution-alignment-quality prediction…
code ai
Domain-specific language (DSL) generation involves automatically creating specialized programming languages tailored to particular problem domains — providing higher-level…
architecture
Domain-Specific Model is model adapted to a particular industry or knowledge domain for higher task precision - It is a core method in modern semiconductor AI serving…
reliability
Dominant failure mechanism is the highest-impact physical mechanism that accounts for the largest share of observed reliability loss - identifying the dominant mechanism prevents…
reliability
Dominant failure mechanism is the failure process that contributes the largest share of observed failures under defined conditions - Statistical and physical analysis determine…
implant
Doping is how a piece of silicon is turned into a device. Pure, intrinsic silicon is a mediocre conductor with very few free carriers, and on its own it can do nothing useful.…
device physics
Rapid thermal annealing is the step that makes an implanted wafer electrically real. When dopants are driven into silicon by ion implantation, they arrive as a wreck: the crystal…
dopant activation percentage prediction machine learning, dopant activation, percentage prediction machine, dopant activation percentage prediction, dopant activation percentage
Dopant Activation Percentage Prediction with Machine Learning Introduction & Motivation Dopant Activation Percentage Prediction with Machine Learning addresses a central problem…
dopant activation profile drift prediction, dopant activation profile, activation profile drift, profile drift prediction, dopant activation, activation profile
Dopant Activation Profile Drift Prediction with Machine Learning Introduction & Motivation Dopant Activation Profile Drift Prediction with Machine Learning addresses a central…
device physics
Dopant Clustering is the formation of electrically inactive multi-atom complexes when dopant concentration exceeds the solid solubility limit — clusters scatter carriers without…
cross contamination, unintended doping
Dopant Contamination refers to unintended introduction of electrically active impurities during semiconductor processing that alter device characteristics. What Is Dopant…
device physics
Dopant Deactivation is the loss of electrically active substitutional dopants through thermal relaxation, clustering, or precipitation during subsequent processing steps — it…
diffusion
Dopant diffusion is the thermally driven movement of impurity atoms (B, P, As, Sb) through the silicon crystal lattice at elevated temperatures, redistributing dopant…
dopant diffusion profile drift prediction machine learning, dopant diffusion, profile drift prediction, dopant diffusion profile drift prediction, dopant diffusion profile
Dopant Diffusion Profile Drift Prediction with Machine Learning Introduction & Motivation Dopant Diffusion Profile Drift Prediction with Machine Learning addresses a central…
dopant profile tails prediction, dopant profile tails, profile tails prediction, dopant profile, profile tails, tails prediction
Dopant Profile Tails Prediction with Machine Learning Introduction & Motivation Dopant Profile Tails Prediction with Machine Learning addresses a central problem in ion implant…
process variation modeling dopant profile tail distributions for ion implantation processes, process variation modeling, variation modeling dopant, modeling dopant profile, process variation
Process Variation: Modeling dopant profile tail distributions for ion implantation processes Introduction & Motivation Process Variation: Modeling dopant profile tail…
dopant profile tails prediction, dopant profile tails, profile tails prediction, dopant profile, profile tails, tails prediction
Dopant Profile Tails Prediction with Machine Learning Introduction & Motivation Dopant Profile Tails Prediction with Machine Learning addresses a central problem in ion implant…
borophosphosilicate glass, phosphosilicate glass, reflow dielectric, bpsg psg dielectric
BPSG and PSG Dielectrics are the doped silicon oxide insulating films used as interlayer dielectrics and planarization layers in CMOS fabrication — where the addition of boron…
ion implantation, p type, n type, boron, phosphorus, acceptor, donor, n-type, p-type
Doping is how a piece of silicon is turned into a device. Pure, intrinsic silicon is a mediocre conductor with very few free carriers, and on its own it can do nothing useful.…
ion implantation, p type, n type, boron, phosphorus
Doping is how a piece of silicon is turned into a device. Pure, intrinsic silicon is a mediocre conductor with very few free carriers, and on its own it can do nothing useful.…
simulation
Doping Profile Simulation models dopant distribution resulting from ion implantation and thermal diffusion — predicting 1D/2D/3D dopant concentration profiles that determine…
n-type doping, p-type doping, dopant
Doping semiconductor is the controlled introduction of impurity atoms into a nearly pure crystal so engineers can set its electrical behavior. In silicon, this step is…
healthcare ai
Dosage Extraction is the clinical NLP subtask of identifying and parsing numeric dosage information — amounts, units, routes, frequencies, and dosing schedules…
dose mapper correction accuracy drift, dose mapper correction, mapper correction accuracy, correction accuracy drift, dose mapper, mapper correction, accuracy drift
Dose Mapper Correction Accuracy Drift with Machine Learning Introduction & Motivation Dose Mapper Correction Accuracy Drift with Machine Learning addresses a central problem…
dose mapping correction accuracy prediction machine learning, dose mapping, correction accuracy prediction, cd, dose mapping correction accuracy prediction
Dose Mapping Correction Accuracy Prediction with Machine Learning Introduction & Motivation Dose Mapping Correction Accuracy Prediction with Machine Learning addresses a central…