15,418 technical terms and definitions
deep learning fundamentals, deep neural network, neural network training, ai training, ml training
Deep learning is the subfield of machine learning that uses neural networks with many layers (deep architectures) to learn hierarchical representations of data — automatically…
Deep Learning for Individual Treatment Effect Estimation Introduction & Motivation Deep Learning for Individual Treatment Effect Estimation addresses a central problem…
Deep Learning for Individual Treatment Effect Estimation (Extended Study) Introduction & Motivation Deep Learning for Individual Treatment Effect Estimation (Extended Study)…
Deep Learning for Individual Treatment Effect Estimation (Extended Study) Introduction & Motivation Deep Learning for Individual Treatment Effect Estimation (Extended Study)…
Deep Learning Architectures for Forecasting Introduction & Motivation Deep Learning Architectures for Forecasting addresses a central problem in timeseries forecasting…
deep learning neural network yield prediction prediction, deep learning neural, learning neural network, neural network yield, network yield prediction
Deep Learning Neural Network Yield Prediction Prediction with Machine Learning Introduction & Motivation Deep Learning Neural Network Yield Prediction Prediction with Machine…
Deep Learning: Neural Network Architectures, Backpropagation, and Optimization Deep learning extends classical neural networks with multiple layers of learned representations…
loss surface neural network, saddle point optimization, sharpness aware minimization, loss landscape geometry
Deep Learning Optimization Landscape is the geometric study of the loss function surface in neural network parameter space — where understanding the structure of minima (sharp vs.…
deep learning recommendation embedding prediction, deep learning recommendation, learning recommendation embedding, recommendation embedding prediction, deep learning
Deep Learning Recommendation Embedding Prediction with Machine Learning Introduction & Motivation Deep Learning Recommendation Embedding Prediction with Machine Learning addresses…
Deep Learning for Recommender Systems Introduction & Motivation Deep Learning for Recommender Systems addresses a central problem in recsys systems and {target} optimization: how…
temporal fusion transformer, time series forecasting deep learning, sequence prediction temporal, transformer time series
Deep learning is the subfield of machine learning that uses neural networks with many layers (deep architectures) to learn hierarchical representations of data — automatically…
deep learning time series, deep learning time, learning time series, deep learning, learning time, time series
Deep Learning Time Series Introduction & Motivation Deep Learning Time Series addresses a central problem in timeseries process control and deep-architecture-multilayer-learning…
deep level transient spectroscopy drift prediction machine learning, deep level, transient spectroscopy drift, dlts, deep level transient, level transient
Deep Level Transient Spectroscopy Drift Prediction with Machine Learning Introduction & Motivation Deep Level Transient Spectroscopy Drift Prediction with Machine Learning…
deep-level transient spectroscopy trap signature prediction, deep-level transient spectroscopy, transient spectroscopy trap, spectroscopy trap signature
Deep-Level Transient Spectroscopy Trap Signature Prediction with Machine Learning Introduction & Motivation Deep-Level Transient Spectroscopy Trap Signature Prediction…
deep metric learning triplet optimization prediction, deep metric learning, metric learning triplet, learning triplet optimization, triplet optimization prediction
Deep Metric Learning Triplet Optimization Prediction with Machine Learning Introduction & Motivation Deep Metric Learning Triplet Optimization Prediction with Machine Learning…
deep pipeline and branch misprediction penalty scaling, deep pipeline branch, pipeline branch misprediction, branch misprediction penalty, misprediction penalty scaling
Deep Pipeline and Branch Misprediction Penalty Scaling Introduction & Motivation Deep Pipeline and Branch Misprediction Penalty Scaling addresses a central problem in cpu-arch…
deep q learning dqn, deep learning dqn, deep learning, learning dqn
Deep Q Learning DQN Introduction & Motivation Deep Q Learning DQN addresses a central problem in robotics process control and deep-neural-network-q-value prediction: how…
Deep Q-Network Architecture Introduction & Motivation Deep Q-Network Architecture addresses a central problem in reinforcement policy learning and dqn-stability-improvement…
Deep Q-Networks (DQN) Introduction & Motivation Deep Q-Networks (DQN) addresses a central problem in sequential decision making via deeprl: how to Learn a policy that maximizes…
Deep Q-Networks (DQN) (Extended Study) Introduction & Motivation Deep Q-Networks (DQN) (Extended Study) addresses a central problem in sequential decision making via deeprl: how…
Deep Q-Networks (DQN) (Extended Study) Introduction & Motivation Deep Q-Networks (DQN) (Extended Study) addresses a central problem in sequential decision making via deeprl: how…
Deep Q-Networks (DQN) (Extended Study) Introduction & Motivation Deep Q-Networks (DQN) (Extended Study) addresses a central problem in sequential decision making via deeprl: how…
Monotonic Deep Quantile Regression Networks Introduction & Motivation Monotonic Deep Quantile Regression Networks addresses a central problem in uncertainty methods and prediction…
sim to real transfer, domain randomization robot, drl robot manipulation, reinforcement learning locomotion
Deep Reinforcement Learning (DRL) for Robotics is the application of neural network-based reinforcement learning agents to robotic control tasks including manipulation…
deep rie sidewall angle prediction machine learning, deep rie, sidewall angle prediction, rf rie, deep rie sidewall angle prediction, deep rie sidewall, rie sidewall angle
Deep RIE Sidewall Angle Prediction with Machine Learning Introduction & Motivation Deep RIE Sidewall Angle Prediction with Machine Learning addresses a central problem in deep…
Deep SHAP DeepLIFT Additive Attributions Introduction & Motivation Deep SHAP DeepLIFT Additive Attributions addresses a central problem in explainability interpretation and model…
deep silicon etch undercut control prediction, deep silicon etch, silicon etch undercut, etch undercut control, undercut control prediction, deep silicon, silicon etch
Deep Silicon Etch Undercut Control Prediction with Machine Learning Introduction & Motivation Deep Silicon Etch Undercut Control Prediction with Machine Learning addresses…
deep space electronics thermal cycling prediction, deep space electronics, space electronics thermal, electronics thermal cycling, thermal cycling prediction, deep space
Deep Space Electronics Thermal Cycling Prediction with Machine Learning Introduction & Motivation Deep Space Electronics Thermal Cycling Prediction with Machine Learning addresses…
deep submicron cmos scaling 1990s step 3 engineer the lightly doped drain structure, engineer the lightly doped drain structure
Deep Submicron CMOS Scaling (1990s): Step 3 — Engineer the Lightly Doped Drain (LDD) Structure 1. The Core Idea: Grade the Field Instead of Fighting It Directly A conventional…
deep submicron cmos scaling 1990s step 16 rebalance threshold voltage against a scaled supply rail, rebalance threshold voltage against a scaled supply rail
Deep Submicron CMOS Scaling (1990s): Step 16 — Rebalance Threshold Voltage Against a Scaled Supply Rail 1. Why Threshold Voltage Cannot Simply Stay Fixed as Supply Falls…
deep submicron cmos scaling 1990s step 15 scale supply voltage from five volts toward lower rails, scale supply voltage from five volts toward lower rails
Deep Submicron CMOS Scaling (1990s): Step 15 — Scale Supply Voltage From Five Volts Toward 3.3 Volts and Below 1. Why 5V Persisted Longer Than Pure Scaling Theory Wanted Step 1…
deep submicron cmos scaling 1990s step 6 weigh oxide thinning against reliability and leakage, weigh oxide thinning against reliability and leakage
Deep Submicron CMOS Scaling (1990s): Step 6 — Weigh Oxide Thinning Against Reliability and Leakage Tradeoffs 1. Combining Two Independent Field-Driven Risks Steps 2 through 4…
Deep Kernel SVDD for Nonlinear Boundary Formulation Introduction & Motivation Deep Kernel SVDD for Nonlinear Boundary Formulation addresses a central problem in anomaly detection…
Deep Support Vector Data Description Deep SVDD Introduction & Motivation Deep Support Vector Data Description Deep SVDD addresses a central problem in anomaly detection…
Deep Support Vector Data Description Introduction & Motivation Deep Support Vector Data Description addresses a central problem in anomaly detection and {target} scoring: how…
Deep Taylor Decomposition Introduction & Motivation Deep Taylor Decomposition addresses a central problem in interpretability and explanation of xai predictions: how to Produce…
Deep Taylor Decomposition (Extended Study) Introduction & Motivation Deep Taylor Decomposition (Extended Study) addresses a central problem in interpretability and explanation…
Deep Taylor Decomposition (Extended Study) Introduction & Motivation Deep Taylor Decomposition (Extended Study) addresses a central problem in interpretability and explanation…
Deep Transfer Clustering for Novel Category Discovery Introduction & Motivation Deep Transfer Clustering for Novel Category Discovery addresses a central problem in transfer…
deep uv scanner pulse energy stability prediction machine learning, deep uv, scanner pulse energy, cd duv uv, deep uv scanner pulse energy stability prediction
Deep UV Scanner Pulse Energy Stability Prediction with Machine Learning Introduction & Motivation Deep UV Scanner Pulse Energy Stability Prediction with Machine Learning addresses…
computer vision
Deep ViT training is the set of optimization practices required to keep very deep vision transformers stable, diverse, and performant over long training runs - as depth increases…
Deep Walk Graph Embedding Introduction & Motivation Deep Walk Graph Embedding addresses a central problem in graph network representation and random-walk-coverage learning: how…
time series models
DeepAR is an autoregressive probabilistic forecasting model that predicts future distributions using recurrent networks - The model conditions on past observations and covariates…
DeepAR Recurrent Probabilistic Forecasting Introduction & Motivation DeepAR Recurrent Probabilistic Forecasting addresses a central problem in timeseries forecasting…
ai generated image detection, synthetic media forensics, face forgery detection
Deepfake Detection is the set of AI and forensic techniques used to identify synthetically generated or manipulated images, videos, and audio — analyzing artifacts in frequency…
ai safety
DeepFool is an adversarial attack that finds the minimum perturbation needed to cross the decision boundary — iteratively linearizing the decision boundary and computing…
DeepFool Adversarial Perturbations Introduction & Motivation DeepFool Adversarial Perturbations addresses a central problem in robustness of advrobust models under adversarial…
DeepFool Adversarial Perturbations (Extended Study) Introduction & Motivation DeepFool Adversarial Perturbations (Extended Study) addresses a central problem in robustness…
DeepFool Adversarial Perturbations (Extended Study) Introduction & Motivation DeepFool Adversarial Perturbations (Extended Study) addresses a central problem in robustness…
DeepFool Adversarial Perturbations (Extended Study) Introduction & Motivation DeepFool Adversarial Perturbations (Extended Study) addresses a central problem in robustness…