universal-domain-adaptation-unida machine learning
Universal Domain Adaptation for Unknown Label Sets Introduction & Motivation Universal Domain Adaptation for Unknown Label Sets addresses a central problem in transfer learning…
29,259 technical terms and definitions
Universal Domain Adaptation for Unknown Label Sets Introduction & Motivation Universal Domain Adaptation for Unknown Label Sets addresses a central problem in transfer learning…
Universal Domain Adaptation Introduction & Motivation Universal Domain Adaptation addresses a central problem in transfer learning and (target) adaptation: how to Apply (subject)…
llm architecture
Universal Transformers are a generalization of the standard transformer architecture that applies the same transformer layer (with shared weights) repeatedly to the input sequence…
reinforcement learning advanced
Universal Value Function is value-function approximation that generalizes across states and goals in one model. - It predicts expected return for arbitrary goal conditions instead…
uvfa, reinforcement learning
UVFA (Universal Value Function Approximators) is a framework for generalizing value functions across goals — extending standard value functions V(s) to V(s, g) that estimate…
neural architecture
Universally Slimmable Networks (US-Nets) are an extension of slimmable networks that support any arbitrary width multiplier, not just preset values — enabling continuous…
universities, academic, research, student, professor, education
Yes, we actively support universities and research institutions through our Academic Program offering 50% discounts on MPW services, free design tool training, and technical…
audio & speech
UnivNet is a universal GAN-based neural vocoder designed for multi-speaker and multi-domain audio synthesis. - It targets strong waveform quality without per-speaker fine-tuning…
unk, nlp
UNK token is the special placeholder token used when input text contains symbols or words not represented by the tokenizer vocabulary - it provides fallback handling…
forget, remove
Machine Unlearning What is Machine Unlearning? Removing specific knowledge, behaviors, or data influence from a trained model without full retraining. Why Unlearning? Reason…
ai safety
Unlearning removes specific knowledge or capabilities from trained models for safety, privacy, or compliance. Motivations: Remove copyrighted content, forget personal data (GDPR…
time series models
Unobserved components is latent time-series components such as trend and cycle that are inferred from observed signals - State-space estimation recovers hidden components…
Rosenbaum Bounds for Sensitivity to Unmeasured Confounders Introduction & Motivation Rosenbaum Bounds for Sensitivity to Unmeasured Confounders addresses a central problem…
bare wafer, substrate inspection, particle detection, surface defect, metrology, substrate
Unpatterned wafer inspection is the metrology process of examining bare silicon wafers before any patterning — using optical, laser scattering, or surface scanning techniques…
unpatterned wafer particle count drift prediction machine learning, unpatterned wafer, particle count drift, unpatterned wafer particle count drift prediction
Unpatterned Wafer Particle Count Drift Prediction with Machine Learning Introduction & Motivation Unpatterned Wafer Particle Count Drift Prediction with Machine Learning addresses…
manufacturing operations
Unplanned Downtime is unexpected equipment stoppage that interrupts production outside scheduled events - It is a major source of availability loss and schedule instability. What…
emergency repair, equipment breakdown
Unplanned Maintenance refers to emergency equipment repairs triggered by unexpected failures, as opposed to scheduled preventive maintenance. What Is Unplanned Maintenance?…
Unrolled GAN Training Introduction & Motivation Unrolled GAN Training addresses a central problem in generative generation and mode-collapse-prevention synthesis: how to Design…
time series models
Unscented Kalman is nonlinear Kalman filtering using deterministic sigma-point transforms instead of Jacobians. - It better captures nonlinear moment propagation with minimal…
Unscented Kalman Filter with Deterministic Sigma-Points Introduction & Motivation Unscented Kalman Filter with Deterministic Sigma-Points addresses a central problem…
production
Unscheduled downtime is unexpected equipment failure or malfunction that halts semiconductor manufacturing without advance planning — the most disruptive and costly type of tool…
unscheduled downtime risk prediction, unscheduled downtime risk, downtime risk prediction, unscheduled downtime, downtime risk, risk prediction
Unscheduled Downtime Risk Prediction with Machine Learning Introduction & Motivation Unscheduled Downtime Risk Prediction with Machine Learning addresses a central problem…
manufacturing operations
Unscheduled Maintenance is reactive maintenance triggered by unexpected equipment faults or alarms - It is a core method in modern semiconductor operations execution workflows.…
TF-IDF, text embeddings, transformer attention is all you need, object storage, NoSQL document database
Unstructured data is data with no predefined schema — free-text documents, emails, images, audio, video, social media posts — where the content doesn't arrive pre-organized into…
model optimization
Unstructured pruning removes individual weights wherever they happen to be least important, anywhere in the network, producing an irregular sparsity pattern that does not align…
model optimization
Unstructured pruning's irregular sparsity pattern requires dedicated sparse-matrix storage formats and compute kernels to translate into actual inference speedup, since standard…
Autoregressive Predictive Coding APC for Acoustic Feature Extraction Introduction & Motivation Autoregressive Predictive Coding APC for Acoustic Feature Extraction addresses…
transfer learning
Unsupervised domain adaptation (UDA) transfers knowledge from a labeled source domain to an unlabeled target domain, addressing distribution shift without requiring any annotated…
unsupervised domain adaptation alignment prediction, unsupervised domain adaptation, domain adaptation alignment, adaptation alignment prediction, unsupervised domain
Unsupervised Domain Adaptation Alignment Prediction with Machine Learning Introduction & Motivation Unsupervised Domain Adaptation Alignment Prediction with Machine Learning…
Unsupervised Image Translation Introduction & Motivation Unsupervised Image Translation addresses a central problem in generative generation and translation-quality-without-pairs…
clustering and dimensionality reduction, anomaly detection unsupervised
Unsupervised learning is the training approach where a model finds structure in data with no labels at all — no correct answer is ever shown, so instead of minimizing the gap to…
pca tsne umap feature manifold, anomaly detection isolation forest autoencoder, vae gan diffusion generative modeling, silhouette elbow cluster validation
Unsupervised Learning Clustering Dimensionality focuses on extracting structure from unlabeled data, enabling teams to discover segments, latent patterns, and outliers when…
unsupervised learning clustering quality prediction, unsupervised learning clustering, learning clustering quality, clustering quality prediction, unsupervised learning
Unsupervised Learning Clustering Quality Prediction with Machine Learning Introduction & Motivation Unsupervised Learning Clustering Quality Prediction with Machine Learning…
Unsupervised Learning in Vision Introduction & Motivation Unsupervised Learning in Vision addresses a central problem in vision processing and representation-discovery-quality…
Unsupervised Metric Learning for Anomaly Introduction & Motivation Unsupervised Metric Learning for Anomaly addresses a central problem in anomaly detection and (target) scoring…
Unsupervised Pretraining for Semi-Supervised Introduction & Motivation Unsupervised Pretraining for Semi-Supervised addresses a central problem in semisupervised…
Variational Disentanglement for Controllable Transfer Introduction & Motivation Variational Disentanglement for Controllable Transfer addresses a central problem in transfer…
Selective Pseudo-Labeling via Local Manifold Density Introduction & Motivation Selective Pseudo-Labeling via Local Manifold Density addresses a central problem in semisupervised…
USAD Unsupervised Anomaly Detection for Time Series Introduction & Motivation USAD Unsupervised Anomaly Detection for Time Series addresses a central problem in anomaly detection…
training
Up-sampling is increasing the effective frequency of underrepresented data classes or domains during training - Sampling multipliers are used to raise gradient contribution…
industry
Upcycles and downcycles are the periodic boom-and-bust demand cycles characteristic of the semiconductor industry, driven by supply-demand imbalances, inventory dynamics…
graph neural networks
Update Functions is node-state transformation rules that integrate prior state with aggregated neighborhood messages. - They control memory, nonlinearity, and stability…
unified power format, power intent, multi voltage design, power domain specification, ieee 1801
UPF (Unified Power Format, IEEE 1801) is the standardized specification language for describing the power intent of an integrated circuit — defining power domains, supply…
upf, unified power format, design
UPF (Unified Power Format) is the IEEE 1801 industry standard for specifying power intent in integrated circuit designs — providing a structured, Tcl-based language to define…
uph, units per hour, production
Units per hour (UPH) measures wafers or lots processed per hour, quantifying tool or process step throughput in semiconductor manufacturing. Calculation: UPH = (Wafers processed)…
Uplift Modeling and Transformed Outcome Trees Introduction & Motivation Uplift Modeling and Transformed Outcome Trees addresses a central problem in causal inference and (target)…
Uplift Modeling for Marketing Introduction & Motivation Uplift Modeling for Marketing addresses a central problem in estimating causal effects with causalml methods: how…
Uplift Modeling for Marketing (Extended Study) Introduction & Motivation Uplift Modeling for Marketing (Extended Study) addresses a central problem in estimating causal effects…
Uplift Modeling for Marketing (Extended Study) Introduction & Motivation Uplift Modeling for Marketing (Extended Study) addresses a central problem in estimating causal effects…
UPMEM DPU, DRAM Processing Unit, PIM-enabled DIMM, UPMEM DIMM, DDR4 PIM
UPMEM builds a PIM-enabled DIMM that is pin-compatible with a standard DDR4 slot, so it plugs into an ordinary server motherboard rather than requiring an interposer, a new memory…