15,762 technical terms and definitions
RoPE, angle embeddings, transformer positional encoding, relative position
Rotary Position Embedding (RoPE) is a positional encoding method that encodes token position as rotation angles in complex plane, applying multiplicative rotation to query/key…
positional encoding transformers, rope attention mechanism, relative position encoding, position embedding interpolation
RoPE implementations can be further extended using techniques like position interpolation or the specifically related YaRN method, both deliberately rescaling RoPE's own…
graph neural networks
RotatE is a knowledge graph embedding model that represents each relation as a rotation in complex vector space — mapping entity pairs through element-wise phase rotations…
graph neural networks
RotatE is a complex-space embedding model that represents relations as rotations of entity embeddings - It encodes relation patterns through phase rotations that preserve…
RotNet Unsupervised Representation Learning by Predicting Rotations Introduction & Motivation RotNet Unsupervised Representation Learning by Predicting Rotations addresses…
Rotation Prediction Pretext Task Introduction & Motivation Rotation Prediction Pretext Task addresses a central problem in selfsupervised and rotation-angle-selection…
supply chain & logistics
Rough-Cut Capacity is high-level capacity assessment used to validate feasibility of aggregate production plans - It quickly flags major resource gaps before detailed scheduling…
roughing pump oil degradation prediction machine learning, roughing pump, oil degradation prediction, roughing pump oil degradation prediction, roughing pump oil, pump oil
Roughing Pump Oil Degradation Prediction with Machine Learning Introduction & Motivation Roughing Pump Oil Degradation Prediction with Machine Learning addresses a central problem…
roughing pump vibration signature prediction machine learning, roughing pump, vibration signature prediction, roughing pump vibration signature prediction, pump vibration
Roughing Pump Vibration Signature Prediction with Machine Learning Introduction & Motivation Roughing Pump Vibration Signature Prediction with Machine Learning addresses a central…
round-robin load distribution, round-robin load, load distribution
Round-Robin Load Distribution Introduction & Motivation Round-Robin Load Distribution addresses a central problem in distributed-systems process control and distribution-fairness…
neural architecture
Router Networks are the specialized routing components in Mixture-of-Experts (MoE) architectures that assign tokens to expert sub-networks across distributed computing devices…
routing bit wear prediction, routing bit wear, bit wear prediction, routing bit, bit wear, wear prediction
Routing Bit Wear Prediction with Machine Learning Introduction & Motivation Routing Bit Wear Prediction with Machine Learning addresses a central problem in PCB routing bit wear…
congestion map, detail routing, routing resource, routing overflow
Routing Congestion is the condition where a region of the chip has insufficient routing resources to accommodate all required wire connections — causing routing tools to fail…
routing congestion prediction and machine learning, routing congestion prediction, congestion prediction machine, prediction machine learning, routing congestion, prediction machine
Routing Congestion Prediction and Machine Learning Introduction & Motivation Routing Congestion Prediction and Machine Learning addresses a central problem in design-automation…
routing track assignment congestion prediction, routing track assignment, track assignment congestion, assignment congestion prediction, routing track, track assignment
Routing Track Assignment Congestion Prediction with Machine Learning Introduction & Motivation Routing Track Assignment Congestion Prediction with Machine Learning addresses…
efficient transformer
Routing Transformer is an efficient transformer that uses online k-means clustering to route tokens into clusters — computing attention only within each cluster, reducing…
row buffer locality exploitation and row-buffer hit rate, row buffer locality, buffer locality exploitation, locality exploitation row-buffer, exploitation row-buffer hit, row-buffer hit rate
Row Buffer Locality Exploitation and Row-Buffer Hit Rate Introduction & Motivation Row Buffer Locality Exploitation and Row-Buffer Hit Rate addresses a central problem in memory…
rram resistance drift prediction, rram resistance drift, resistance drift prediction, rram resistance, resistance drift, drift prediction
RRAM Resistance Drift Prediction with Machine Learning Introduction & Motivation RRAM Resistance Drift Prediction with Machine Learning addresses a central problem in resistive…
emerging memories predicting resistance drift in reram devices under cycling, emerging memories predicting, memories predicting resistance, predicting resistance drift, drift reram devices
Emerging Memories: Predicting resistance drift in ReRAM devices under cycling Introduction & Motivation Emerging Memories: Predicting resistance drift in ReRAM devices under…
rram synaptic weight retention prediction, rram synaptic weight, synaptic weight retention, weight retention prediction, rram synaptic, synaptic weight, weight retention
RRAM Synaptic Weight Retention Prediction with Machine Learning Introduction & Motivation RRAM Synaptic Weight Retention Prediction with Machine Learning addresses a central…
neural architecture
RReLU (Randomized Leaky ReLU) is a variant of Leaky ReLU where the negative slope is randomly sampled from a uniform distribution during training — and fixed to the mean of that…
rsa signatures rsa oaep, rsa signatures rsa, signatures rsa oaep, rsa signatures, signatures rsa, rsa oaep
RSA Signatures RSA OAEP Introduction & Motivation RSA Signatures RSA OAEP addresses a central problem in cryptography process control and signature-verification-efficiency…
synthesis constraints sdc, timing constraints setup hold, rtl optimization techniques, verilog coding style synthesis
RTL Coding for Synthesis is the discipline of writing Register Transfer Level hardware descriptions (Verilog/SystemVerilog/VHDL) that are both functionally correct and optimally…
hardware description language synthesis, register transfer level coding, rtl to gate netlist, synthesis optimization constraints
RTL Design and Synthesis Methodology — Register Transfer Level (RTL) design and synthesis form the foundational workflow for translating architectural specifications into…
rtp, rapid thermal processing, diffusion
Rapid thermal processing (RTP) heats and cools a wafer over timescales of seconds rather than the many minutes typical of conventional furnace annealing, using high-intensity lamp…
rtp spike anneal temperature uniformity prediction, rtp spike anneal, spike anneal temperature, anneal temperature uniformity, temperature uniformity prediction
RTP Spike Anneal Temperature Uniformity Prediction with Machine Learning Introduction & Motivation RTP Spike Anneal Temperature Uniformity Prediction with Machine Learning…
rtp temperature uniformity drift prediction machine learning, rtp temperature, uniformity drift prediction, rtp, rtp temperature uniformity drift prediction
RTP Temperature Uniformity Drift Prediction with Machine Learning Introduction & Motivation RTP Temperature Uniformity Drift Prediction with Machine Learning addresses a central…
rtp wafer bow-induced temperature error prediction, rtp wafer bow-induced, wafer bow-induced temperature, bow-induced temperature error, rtp wafer, error prediction
RTP Wafer Bow-Induced Temperature Error Prediction with Machine Learning Introduction & Motivation RTP Wafer Bow-Induced Temperature Error Prediction with Machine Learning…
production system, if-then rules, forward chaining, backward chaining, Rete algorithm, business rules engine, OPS5, guardrails
A rule-based system is a program whose behavior is determined by an explicit set of if-then rules, each pairing a condition with an action or conclusion, together with a mechanism…
explainable ai
Rule Extraction from Neural Networks is the process of distilling the knowledge embedded in a trained neural network into human-readable IF-THEN rules — converting opaque neural…
Rule Extraction from Neural Networks Introduction & Motivation Rule Extraction from Neural Networks addresses a central problem in interpretability and explanation of xai…
Rule Extraction from Neural Networks (Extended Study) Introduction & Motivation Rule Extraction from Neural Networks (Extended Study) addresses a central problem…
Rule Extraction from Neural Networks (Extended Study) Introduction & Motivation Rule Extraction from Neural Networks (Extended Study) addresses a central problem…
Rule Extraction from Neural Networks Introduction & Motivation Rule Extraction from Neural Networks addresses a central problem in explainability interpretation and model…
RuleFit Sparse Combination of Rules and Linear Terms Introduction & Motivation RuleFit Sparse Combination of Rules and Linear Terms addresses a central problem in explainability…
environmental & sustainability
Run-Around Loop is a heat-recovery configuration using a pumped fluid loop between separated exhaust and supply coils - It enables energy recovery when direct air-stream exchange…
production
Run-to-failure is the maintenance policy of intentionally operating an asset until it fails, then repairing or replacing it - it is appropriate only when failure impact is low…
run to run advanced process control for overlay correction with machine learning, run run advanced process control overlay correction machine learning
Run-to-Run Advanced Process Control for Overlay Correction with Machine Learning Introduction & Motivation Run-to-Run Advanced Process Control for Overlay Correction with Machine…
run to run control algorithm tuning prediction with machine learning, run run control algorithm tuning prediction machine learning, run run, control algorithm tuning, r2r
Run-to-Run Control Algorithm Tuning Prediction with Machine Learning Introduction & Motivation Run-to-Run Control Algorithm Tuning Prediction with Machine Learning addresses…
run-to-run control convergence prediction, run-to-run control convergence, control convergence prediction, run-to-run control, control convergence, convergence prediction
Run-to-Run Control Convergence Prediction with Machine Learning Introduction & Motivation Run-to-Run Control Convergence Prediction with Machine Learning addresses a central…
run-to-run controller gain drift prediction, run-to-run controller gain, controller gain drift, gain drift prediction, run-to-run controller, controller gain, gain drift
Run-to-Run Controller Gain Drift Prediction with Machine Learning Introduction & Motivation Run-to-Run Controller Gain Drift Prediction with Machine Learning addresses a central…
time series models
Ruptures Library is a Python toolkit for offline change-point detection across multiple algorithms and cost functions. - It standardizes experimentation with segmentation methods…
rust memory safety systems, rust memory safety, memory safety systems, rust memory, memory safety, safety systems
Rust Memory Safety Systems Introduction & Motivation Rust Memory Safety Systems addresses a central problem in programming process control and memory-safety-guarantee prediction…
ruthenium direct-plate seedless fill prediction, ruthenium direct-plate seedless, direct-plate seedless fill, seedless fill prediction, ruthenium direct-plate
Ruthenium Direct-Plate Seedless Fill Prediction with Machine Learning Introduction & Motivation Ruthenium Direct-Plate Seedless Fill Prediction with Machine Learning addresses…
ruthenium liner adhesion prediction, ruthenium liner adhesion, liner adhesion prediction, ruthenium liner, liner adhesion, adhesion prediction
Ruthenium Liner Adhesion Prediction with Machine Learning Introduction & Motivation Ruthenium Liner Adhesion Prediction with Machine Learning addresses a central problem…
copper resistivity scaling, barrier light free integration, electromigration margin, narrow pitch BEOL, etch CMP process window, surface grain boundary scattering
Ruthenium local interconnect integration uses ruthenium rather than copper or tungsten for the narrowest-pitch local back-end-of-line metal lines, specifically because ruthenium…
rvae, time series models
RVAE is recurrent variational autoencoder using sequence-level latent variables for temporal generation. - It compresses sequence structure into latent codes that support…
foundation model
RWKV is the novel recurrent architecture that combines the efficiency of RNNs with the capability of transformers — RWKV (Receptance Weighted Key Value) is a breakthrough…
S-Learner Single-Model Treatment Effect Estimator Introduction & Motivation S-Learner Single-Model Treatment Effect Estimator addresses a central problem in causal inference…
s-parameter measurement calibration accuracy prediction, s-parameter measurement calibration, measurement calibration accuracy, calibration accuracy prediction
S-Parameter Measurement Calibration Accuracy Prediction with Machine Learning Introduction & Motivation S-Parameter Measurement Calibration Accuracy Prediction with Machine…