2,263 technical terms and definitions
proximal gradient method composite prediction, proximal gradient method, gradient method composite, method composite prediction, proximal gradient, gradient method
Proximal Gradient Method Composite Prediction with Machine Learning Introduction & Motivation Proximal Gradient Method Composite Prediction with Machine Learning addresses…
Proximal Gradient Methods Introduction & Motivation Proximal Gradient Methods addresses a central problem in optimization algorithm tuning and improvement: how to Optimize…
ppo, reinforcement learning
PPO (Proximal Policy Optimization) is the most widely used policy gradient RL algorithm — simplifying TRPO's constrained optimization into a clipped surrogate objective that…
Proximal Policy Optimization (PPO) Introduction & Motivation Proximal Policy Optimization (PPO) addresses a central problem in reinforcement policy learning…
Proximal Policy Optimization (PPO) Introduction & Motivation Proximal Policy Optimization (PPO) addresses a central problem in sequential decision making via deeprl: how to Learn…
proximal policy optimization ppo, proximal policy optimization, policy optimization ppo, proximal policy, policy optimization, optimization ppo
Proximal Policy Optimization PPO Introduction & Motivation Proximal Policy Optimization PPO addresses a central problem in robotics process control…
proximal policy optimization ppo prediction, proximal policy optimization, policy optimization ppo, optimization ppo prediction, proximal policy, policy optimization
Proximal Policy Optimization PPO Prediction with Machine Learning Introduction & Motivation Proximal Policy Optimization PPO Prediction with Machine Learning addresses a central…
Proximal Policy Optimization (PPO) (Extended Study) Introduction & Motivation Proximal Policy Optimization (PPO) (Extended Study) addresses a central problem in sequential…
Proximal Policy Optimization (PPO) (Extended Study) Introduction & Motivation Proximal Policy Optimization (PPO) (Extended Study) addresses a central problem in sequential…
signal & power integrity
Proximity Effect is additional conductor loss caused by current redistribution from nearby electromagnetic fields - It increases AC resistance in tightly spaced routing…
proximity gap control drift prediction machine learning, proximity gap, control drift prediction, cd, proximity gap control drift prediction, proximity gap control, gap control
Proximity Gap Control Drift Prediction with Machine Learning Introduction & Motivation Proximity Gap Control Drift Prediction with Machine Learning addresses a central problem…
process
Proximity Gettering is a gettering technique that places trap sites within a few microns of the active device region — typically using high-energy carbon, helium, or argon…
proximity lithography, mask gap, contact printing, diffraction limit, shadow printing
Proximity printing is a photolithography method in which the mask is held a small distance above the wafer during exposure rather than pressed directly against it, a compromise…
proxy reverse proxy edge, proxy reverse proxy, reverse proxy edge, proxy reverse, reverse proxy, proxy edge
Proxy Reverse Proxy Edge Introduction & Motivation Proxy Reverse Proxy Edge addresses a central problem in cloud process control and reverse-proxy-header-rewriting prediction: how…
neural architecture
ProxylessNAS is a NAS method that directly searches on the target hardware and target dataset — eliminating the need for proxy tasks (smaller datasets, shorter training) that…
ProxylessNAS Introduction & Motivation ProxylessNAS addresses a central problem in automated design of nas architectures: how to Automatically discover nas architectures that…
neural architecture search
ProxylessNAS is a neural-architecture-search method that performs direct hardware-targeted search without proxy tasks - Differentiable search is executed on target constraints…
ProxylessNAS (Extended Study) Introduction & Motivation ProxylessNAS (Extended Study) addresses a central problem in automated design of nas architectures: how to Automatically…
ProxylessNAS (Extended Study) Introduction & Motivation ProxylessNAS (Extended Study) addresses a central problem in automated design of nas architectures: how to Automatically…
ProxylessNAS (Extended Study) Introduction & Motivation ProxylessNAS (Extended Study) addresses a central problem in automated design of nas architectures: how to Automatically…
sparsity, compression
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…
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…
3d vision
Pruning gaussians is the process of removing low-contribution Gaussian primitives to reduce redundancy and improve rendering efficiency - it keeps Gaussian scene models compact…
network pruning and compression, network pruning compression, network pruning, pruning compression
Network Pruning and Compression Introduction & Motivation Network Pruning and Compression addresses a central problem in ml-training process control and compression-ratio-achieved…
pruning network sparsity and accuracy prediction, pruning network sparsity, network sparsity accuracy, sparsity accuracy prediction, pruning network, network sparsity
Pruning Network Sparsity and Accuracy Prediction with Machine Learning Introduction & Motivation Pruning Network Sparsity and Accuracy Prediction with Machine Learning addresses…
Neural Network Pruning Methods Introduction & Motivation Neural Network Pruning Methods addresses a central problem in vision processing and parameter-reduction prediction: how…
Network Pruning Optimization Introduction & Motivation Network Pruning Optimization addresses a central problem in optimization algorithm tuning and improvement: how to Optimize…
pruning weight sparsity and network compression, pruning weight sparsity, weight sparsity network, sparsity network compression, pruning weight, weight sparsity, sparsity network
Pruning Weight Sparsity and Network Compression Introduction & Motivation Pruning Weight Sparsity and Network Compression addresses a central problem in weight pruning for model…
reinforcement learning
Pseudo-Count Methods are exploration techniques that extend count-based exploration to high-dimensional state spaces — using density models to estimate pseudo-counts hat(N)(s)…
Uncertainty-Paced Pseudo-Labeling with Epistemic Gating Introduction & Motivation Uncertainty-Paced Pseudo-Labeling with Epistemic Gating addresses a central problem…
Pseudo-Label Refinement Strategies Introduction & Motivation Pseudo-Label Refinement Strategies addresses a central problem in semisupervised and label-quality-assessment…
semi-supervised learning
Pseudo-Labeling is a semi-supervised learning technique that leverages a small labeled dataset and a large unlabeled dataset — training an initial model on the labeled data, using…
advanced training
Pseudo-labeling is the assignment of model-predicted labels to unlabeled examples for additional supervised training - Unlabeled data is converted into training pairs using…
Pseudo-Labeling with Confidence Thresholding Introduction & Motivation Pseudo-Labeling with Confidence Thresholding addresses a central problem in semisupervised…
Curriculum Pseudo-Labeling for Domain Adaptation Introduction & Motivation Curriculum Pseudo-Labeling for Domain Adaptation addresses a central problem in transfer learning…
semi-supervised learning
Pseudo-Labeling with Confidence is a semi-supervised learning technique that uses the model's own high-confidence predictions on unlabeled data as training labels — filtering…
rag
Pseudo Relevance Feedback is an iterative retrieval method that assumes top initial results are relevant and uses them to refine the query - It is a core method in modern…
Pseudo-Labeling with Annealed Unsupervised Loss Weight Introduction & Motivation Pseudo-Labeling with Annealed Unsupervised Loss Weight addresses a central problem…
privacy
Pseudonymization is a de-identification technique where identifiers are identified and replaced with realistic-looking fake values (surrogates) rather than being masked or deleted…
training techniques
Pseudonymization is privacy technique that replaces direct identifiers with reversible tokens under controlled key management - It is a core method in modern semiconductor AI…
psk phase error sensitivity prediction, psk phase error, phase error sensitivity, error sensitivity prediction, psk phase, phase error, error sensitivity, sensitivity prediction
PSK Phase Error Sensitivity Prediction with Machine Learning Introduction & Motivation PSK Phase Error Sensitivity Prediction with Machine Learning addresses a central problem…
psnr, evaluation
PSNR is the Peak Signal-to-Noise Ratio metric that quantifies reconstruction fidelity from mean squared pixel error on a logarithmic scale - it remains a standard baseline…
ptc thermistor self-heating prediction, ptc thermistor self-heating, thermistor self-heating prediction, ptc thermistor, thermistor self-heating, self-heating prediction
PTC Thermistor Self-Heating Prediction with Machine Learning Introduction & Motivation PTC Thermistor Self-Heating Prediction with Machine Learning addresses a central problem…
metrology
Ptychography is a computational imaging technique that recovers both the amplitude and phase of a transmitted wave by scanning a coherent probe across overlapping positions…
public key infrastructure trust, public key infrastructure, key infrastructure trust, public key, key infrastructure, infrastructure trust
Public Key Infrastructure Trust Introduction & Motivation Public Key Infrastructure Trust addresses a central problem in cryptography process control…
domain, biomedical
BioMedLM (PubMedGPT) Overview BioMedLM is a 2.7 billion parameter language model trained by Stanford (CRFM) and MosaicML. It is designed specifically for biomedical text…
biomedical qa, medical benchmark
PubMedQA is a biomedical question answering benchmark dataset — testing AI models on yes/no/maybe questions derived from PubMed research abstracts, requiring understanding…
power usage effectiveness, datacenter efficiency, data center efficiency, datacenter energy efficiency, cooling efficiency, wue, cue
Power usage effectiveness, universally shortened to PUE, is the single number the datacenter industry uses to grade how much of the electricity a facility draws actually reaches…
physically unclonable function, physical unclonable function, hardware fingerprint, device identity puf
PUF is a physically unclonable function that derives device-specific responses from irreducible manufacturing variation. PUFs can support identity, enrollment, attestation, key…