283 technical terms and definitions
metrology, target-to-device offset, intrafield overlay variation, e-beam overlay, in-die target, computational overlay, machine learning overlay, hybrid overlay correction, advanced node overlay budget
On-device overlay measures registration directly on real, functional device structures rather than on dedicated overlay targets sitting in the scribe line — because at advanced…
edge ai
On-Device Training is the training or fine-tuning of ML models directly on edge devices — enabling continuous learning and personalization without sending data to a server…
on-die power supply noise sensor calibration prediction, on-die power supply, power supply noise, supply noise sensor, noise sensor calibration, on-die power
On-Die Power Supply Noise Sensor Calibration Prediction with Machine Learning Introduction & Motivation On-Die Power Supply Noise Sensor Calibration Prediction with Machine…
on-die termination accuracy prediction, on-die termination accuracy, termination accuracy prediction, on-die termination, termination accuracy, accuracy prediction
On-Die Termination Accuracy Prediction with Machine Learning Introduction & Motivation On-Die Termination Accuracy Prediction with Machine Learning addresses a central problem…
on-die termination impedance drift prediction, on-die termination impedance, termination impedance drift, impedance drift prediction, on-die termination, termination impedance
On-Die Termination Impedance Drift Prediction with Machine Learning Introduction & Motivation On-Die Termination Impedance Drift Prediction with Machine Learning addresses…
on-die thermal monitoring accuracy prediction, on-die thermal monitoring, thermal monitoring accuracy, monitoring accuracy prediction, on-die thermal, thermal monitoring
On-Die Thermal Monitoring Accuracy Prediction with Machine Learning Introduction & Motivation On-Die Thermal Monitoring Accuracy Prediction with Machine Learning addresses…
optimizing on-die voltage regulator (vr) design and placement, optimizing on-die voltage, on-die voltage regulator, voltage regulator (vr), regulator (vr) design, on-die voltage
Optimizing on-die voltage regulator (VR) design and placement Introduction & Motivation Optimizing on-die voltage regulator (VR) design and placement addresses a central problem…
environmental & sustainability
On-Site Solar is local photovoltaic generation deployed within facility boundaries - It offsets grid electricity demand and supports decarbonization targets. What Is On-Site…
onboard charger efficiency drift prediction, onboard charger efficiency, charger efficiency drift, efficiency drift prediction, onboard charger, charger efficiency
Onboard Charger Efficiency Drift Prediction with Machine Learning Introduction & Motivation Onboard Charger Efficiency Drift Prediction with Machine Learning addresses a central…
neural architecture search
Once-for-All is a NAS framework that trains one elastic supernetwork and derives many specialized subnetworks by slicing it - Progressive training supports depth width…
neural architecture
Once-for-All (OFA) is a NAS approach that trains a single large "supernet" that supports many sub-networks — enabling deployment of different-sized architectures for different…
Once-For-All Networks Introduction & Motivation Once-For-All Networks addresses a central problem in automated design of nas architectures: how to Automatically discover nas…
Once-For-All Networks (Extended Study) Introduction & Motivation Once-For-All Networks (Extended Study) addresses a central problem in automated design of nas architectures: how…
Once-For-All Networks (Extended Study) Introduction & Motivation Once-For-All Networks (Extended Study) addresses a central problem in automated design of nas architectures: how…
Pretrained Autoencoder Initialization for Deep SVDD Introduction & Motivation Pretrained Autoencoder Initialization for Deep SVDD addresses a central problem in anomaly detection…
one class svm anomaly, one class svm, class svm anomaly, one class, class svm, svm anomaly
One Class SVM Anomaly Introduction & Motivation One Class SVM Anomaly addresses a central problem in timeseries process control and support-vector-machine-boundary prediction: how…
One-Class Support Vector Machines Introduction & Motivation One-Class Support Vector Machines addresses a central problem in anomaly detection and {target} scoring: how to Detect…
one-class svm novelty detection prediction, one-class svm novelty, svm novelty detection, novelty detection prediction, one-class svm, svm novelty, novelty detection
One-Class SVM Novelty Detection Prediction with Machine Learning Introduction & Motivation One-Class SVM Novelty Detection Prediction with Machine Learning addresses a central…
time series models
One-Class SVM TS is one-class support-vector modeling for identifying anomalies in time-series feature space. - It learns a decision boundary around normal behavior using only…
One-Cycle Learning Rate Policy and Super-Convergence Introduction & Motivation One-Cycle Learning Rate Policy and Super-Convergence addresses a central problem in optimization…
one-shot learning single sample prediction, one-shot learning single, learning single sample, single sample prediction, one-shot learning, learning single, single sample
One-Shot Learning Single Sample Prediction with Machine Learning Introduction & Motivation One-Shot Learning Single Sample Prediction with Machine Learning addresses a central…
neural architecture
One-Shot NAS is a weight-sharing NAS approach where a single "supernet" is trained that contains all candidate architectures as sub-networks — enabling architecture evaluation…
One-Shot Neural Architecture Search Introduction & Motivation One-Shot Neural Architecture Search addresses a central problem in automated design of nas architectures: how…
One-Shot Neural Architecture Search (Extended Study) Introduction & Motivation One-Shot Neural Architecture Search (Extended Study) addresses a central problem in automated design…
One-Shot Neural Architecture Search (Extended Study) Introduction & Motivation One-Shot Neural Architecture Search (Extended Study) addresses a central problem in automated design…
model optimization
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
model optimization
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
neural architecture search
One-Shot Weight Sharing is NAS paradigm training a supernet where many candidate architectures share parameters. - It enables rapid candidate evaluation without retraining each…
one-way quantum computing, one-way quantum, quantum computing
One-Way Quantum Computing Introduction & Motivation One-Way Quantum Computing addresses a central problem in quantum-computing process control…
Online Bayesian Changepoint Detection Adams-MacKay Introduction & Motivation Online Bayesian Changepoint Detection Adams-MacKay addresses a central problem in timeseries…
Online Continual Learning OCL in a Single Epoch Regime Introduction & Motivation Online Continual Learning OCL in a Single Epoch Regime addresses a central problem in continual…
online convex optimization (oca) multiplicative prediction, online convex optimization, convex optimization (oca), optimization (oca) multiplicative, online convex
Online Convex Optimization (OCA) Multiplicative Prediction with Machine Learning Introduction & Motivation Online Convex Optimization (OCA) Multiplicative Prediction with Machine…
model compression
Online Distillation is a knowledge distillation approach where teacher and student networks are trained simultaneously — rather than the traditional offline approach where…
online gradient descent (ogd) prediction, online gradient descent, gradient descent (ogd), descent (ogd) prediction, online gradient, gradient descent, descent (ogd), (ogd) prediction
Online Gradient Descent (OGD) Prediction with Machine Learning Introduction & Motivation Online Gradient Descent (OGD) Prediction with Machine Learning addresses a central problem…
Online Knowledge Distillation Introduction & Motivation Online Knowledge Distillation addresses a central problem in reducing the size and cost of compression models: how…
Online Knowledge Distillation (Extended Study) Introduction & Motivation Online Knowledge Distillation (Extended Study) addresses a central problem in reducing the size and cost…
Online Knowledge Distillation (Extended Study) Introduction & Motivation Online Knowledge Distillation (Extended Study) addresses a central problem in reducing the size and cost…
Online Knowledge Distillation (Extended Study) Introduction & Motivation Online Knowledge Distillation (Extended Study) addresses a central problem in reducing the size and cost…
machine learning
Online learning is a machine learning paradigm where the model is updated incrementally as new data arrives, one example (or small batch) at a time, rather than being trained on…
concept drift detection, streaming machine learning, incremental learning, river ml
Online Learning and Concept Drift Adaptation is the machine learning paradigm where models are updated continuously as individual data points or small batches arrive in a stream…
online learning incremental, online learning, learning incremental
Online Learning Incremental Introduction & Motivation Online Learning Incremental addresses a central problem in timeseries process control and incremental-learning-new-data…
online learning and streaming data prediction prediction, online learning streaming, learning streaming data, streaming data prediction, data prediction prediction
Online Learning and Streaming Data Prediction Prediction with Machine Learning Introduction & Motivation Online Learning and Streaming Data Prediction Prediction with Machine…
Online Learning for Time Series Streams Introduction & Motivation Online Learning for Time Series Streams addresses a central problem in timeseries forecasting…
online learning updating, online learning, learning updating
Online Learning Updating Introduction & Motivation Online Learning Updating addresses a central problem in systems process control and learning-latency-convergence-speed…
Online Meta-Learning Introduction & Motivation Online Meta-Learning addresses a central problem in metalearning learning and rapid task adaptation: how to Learn a good…
Online Meta-Learning (Extended Study) Introduction & Motivation Online Meta-Learning (Extended Study) addresses a central problem in metalearning learning and rapid task…
Online Meta-Learning (Extended Study) Introduction & Motivation Online Meta-Learning (Extended Study) addresses a central problem in metalearning learning and rapid task…
open neural network exchange, onnx runtime, model exchange format, execution provider, portable model
ONNX is an open model interchange specification that represents computation graphs, typed tensors, operators, attributes and parameters across training and inference ecosystems.…
model optimization format, portable inference graph
ONNX Format is an open model-interchange format that standardizes computational graph representation across frameworks - It improves portability between training and inference…
onnx model interoperability and framework agnostic representation, onnx model interoperability, model interoperability framework, interoperability framework agnostic, onnx model
ONNX Model Interoperability and Framework Agnostic Representation Introduction & Motivation ONNX Model Interoperability and Framework Agnostic Representation addresses a central…