27,049 technical terms and definitions
learning rate, schedules warmup cosine, bert lr nlp passed, learning rate schedules warmup cosine decay & step decay, learning rate schedules, rate schedules warmup, cosine decay step
Learning Rate Schedules: Warmup, Cosine Decay & Step Decay Introduction & Motivation Learning rate schedule: dynamic adjustment during training. Warmup: ramp from low to target…
warmup strategies, cosine annealing, cyclical learning rates, adaptive optimization
The learning rate is the single most consequential number in a training run: it sets how far each optimizer step moves the weights. Set it too high and the loss diverges; set it…
learning rate scheduling annealing and adaptive learning decay, learning rate scheduling, rate scheduling annealing, scheduling annealing adaptive, annealing adaptive learning
Learning Rate Scheduling Annealing and Adaptive Learning Decay Introduction & Motivation Learning Rate Scheduling Annealing and Adaptive Learning Decay addresses a central problem…
learning rate scheduling strategies, learning rate scheduling, rate scheduling strategies, learning rate, rate scheduling, scheduling strategies
Learning Rate Scheduling Strategies Introduction & Motivation Learning Rate Scheduling Strategies addresses a central problem in ml-training process control…
learning rate scheduling, learning rate, rate scheduling
Learning Rate Scheduling Introduction & Motivation Learning Rate Scheduling addresses a central problem in systems process control and schedule-strategy-decay-warmup prediction…
Learning Rate Schedule Optimization Introduction & Motivation Learning Rate Schedule Optimization addresses a central problem in optimization algorithm tuning and improvement: how…
learning rate, rate scheduling, cifar lr nlp, learning rate scheduling, rate scheduling strategies, scheduling strategies
Learning Rate Scheduling Strategies Introduction & Motivation Learning rate scheduling: vary learning rate during training. Improve convergence and final accuracy. Applications…
cosine annealing schedule, training schedule, optimization convergence, temperature scheduling
The learning rate is the single most consequential number in a training run: it sets how far each optimizer step moves the weights. Set it too high and the loss diverges; set it…
Learning Rate Warmup Strategies Introduction & Motivation Learning Rate Warmup Strategies addresses a central problem in optimization algorithm tuning and improvement: how…
Learning to Learn by Gradient Descent Introduction & Motivation Learning to Learn by Gradient Descent addresses a central problem in metalearning learning and rapid task…
Learning to Learn by Gradient Descent (Extended Study) Introduction & Motivation Learning to Learn by Gradient Descent (Extended Study) addresses a central problem in metalearning…
Learning to Learn by Gradient Descent (Extended Study) Introduction & Motivation Learning to Learn by Gradient Descent (Extended Study) addresses a central problem in metalearning…
machine learning
Learning to rank (LTR) uses machine learning to optimize ranking — training models to order items by relevance, popularity, or other objectives, fundamental to search engines…
learning-to-rank point-wise prediction, learning-to-rank point-wise, point-wise prediction
Learning-to-Rank Point-Wise Prediction with Machine Learning Introduction & Motivation Learning-to-Rank Point-Wise Prediction with Machine Learning addresses a central problem…
learning rank ranking systems information retrieval, learning rank, ranking systems information, dcg ir letor mrr mslr ndcg, learning to rank ranking systems & information retrieval
Learning to Rank: Ranking Systems & Information Retrieval Introduction & Motivation Learning to Rank: predict item order. Pointwise, pairwise, listwise approaches. Applications…
recommendation systems
Learning to Rank for Recommendation is a supervised ranking framework that optimizes item ordering for user relevance - It directly targets ranking quality instead of only…
lupi, machine learning
Learning Using Privileged Information (LUPI) constitutes the formal, rigorous mathematical framework originally formulated by Vladimir Vapnik (the legendary inventor of…
Least Confidence Active Learning Query Strategy Introduction & Motivation Least Confidence Active Learning Query Strategy addresses a central problem in {subject} learning…
least-loaded-first load strategy, least-loaded-first load, load strategy
Least-Loaded-First Load Strategy Introduction & Motivation Least-Loaded-First Load Strategy addresses a central problem in distributed-systems process control…
Least Squares GAN Introduction & Motivation Least Squares GAN addresses a central problem in generative generation and training-stability-improvement synthesis: how to Design…
prompting techniques
Least-to-Most is a decomposition technique that solves complex problems by ordering and answering simpler subproblems first - It is a core method in modern LLM workflow execution.…
prompt engineering
Least-to-Most Prompting is the structured prompt engineering technique that teaches language models to solve complex problems by first decomposing them into progressively simpler…
prompting
Least-to-most prompting is the reasoning method that decomposes a difficult problem into simpler subproblems solved in progressive order - each intermediate result becomes context…
Leave-One-Covariate-Out LOCO Local Feature Importance Introduction & Motivation Leave-One-Covariate-Out LOCO Local Feature Importance addresses a central problem in explainability…
led die bond thermal resistance prediction machine learning, led die, bond thermal resistance, led, led die bond thermal resistance prediction, led die bond, die bond thermal
LED Die Bond Thermal Resistance Prediction with Machine Learning Introduction & Motivation LED Die Bond Thermal Resistance Prediction with Machine Learning addresses a central…
led die bonding alignment prediction machine learning, led die, bonding alignment prediction, led, led die bonding alignment prediction, led die bonding, die bonding alignment
LED Die Bonding Alignment Prediction with Machine Learning Introduction & Motivation LED Die Bonding Alignment Prediction with Machine Learning addresses a central problem in LED…
light emitting diode, microLED, solid state lighting, electroluminescence
Light-emitting diode. is a forward-biased semiconductor junction that converts injected electrical carriers into photons through spontaneous radiative recombination.…
led wavelength binning drift prediction machine learning, led wavelength, binning drift prediction, led, led wavelength binning drift prediction, led wavelength binning
LED Wavelength Binning Drift Prediction with Machine Learning Introduction & Motivation LED Wavelength Binning Drift Prediction with Machine Learning addresses a central problem…
abstract layout, technology lef, cell lef, library exchange format
LEF (Library Exchange Format) is an ASCII file format that describes the physical properties of standard cells and technology rules — providing the place-and-route tool with…
law, domain
Legal-BERT is a family of BERT models pre-trained on large legal corpora including legislation, court cases, and contracts, designed to understand the specialized vocabulary…
legal ai
Legal document analysis uses AI to automatically review, interpret, and extract insights from contracts and legal texts — applying NLP to parse dense legal language, identify key…
legal ai
Legal question answering uses AI to provide answers to questions about the law — interpreting legal queries, searching relevant authorities, and generating synthesized answers…
legal ai
Legal research with AI uses natural language processing to find relevant cases, statutes, and legal authorities — enabling lawyers to search legal databases using plain English…
Legal Systems: Contracts, Torts, and Constitutional Structure Law organizes collective life through rules, institutions, procedures, and remedies. Legal systems resolve disputes…
evaluation
LegalBench is the collaborative benchmark of 162 legal reasoning tasks — assembled by legal scholars and NLP researchers to comprehensively evaluate AI capability across the full…
legged robot climbing, legged robot, robot climbing
Legged Robot Climbing Introduction & Motivation Legged Robot Climbing addresses a central problem in robotics process control and leg-coordination-gait-sequence prediction: how…
lele, litho-etch-litho-etch, lithography
Multi-patterning is the family of manufacturing techniques that print circuit features at a finer pitch than a single lithographic exposure can resolve, by splitting the pattern…
word normalization, nlp preprocessing
Lemmatization is an NLP technique that reduces words to their dictionary base form (lemma) — converting "running", "ran", "runs" to "run" using linguistic rules, improving search…
lending protocol liquidation, lending protocol, protocol liquidation
Lending Protocol Liquidation Introduction & Motivation Lending Protocol Liquidation addresses a central problem in blockchain process control and collateral-requirement-safety…
llm architecture
Length Extrapolation is the ability of a transformer model to maintain generation quality on sequences significantly longer than those encountered during training — a property…
signal & power integrity
Length Matching is routing practice that equalizes electrical path length among timing-critical nets - It controls skew and preserves timing alignment in buses and differential…
text generation
Length normalization is the score-adjustment technique that compensates for sequence-length bias when ranking generated hypotheses in search-based decoding - it prevents unfair…
design
LOD (Length of Diffusion) Effect is a layout-dependent effect where the distance from a transistor's channel to the nearest STI edge affects its performance — because…
inference
Length penalty adjusts sequence scores in beam search to control output length preferences. Problem: Log probabilities accumulate negatively - longer sequences have lower scores…
text generation
Length penalty is the decoding score modifier that explicitly encourages or discourages longer sequences during hypothesis ranking - it provides direct control over generated…
optimization
Length Penalty is a scoring adjustment that controls preference toward shorter or longer candidate sequences - It is a core method in modern semiconductor AI serving…
manufacturing
Line edge roughness (LER) and line width roughness (LWR) are stochastic variations in the edges and width of patterned features, causing transistor variability that worsens…
ler/lwr, metrology
LER/LWR Metrology combines Line Edge Roughness and Line Width Roughness characterization — measuring nanometer-scale variations in patterned feature edges and widths that impact…
lessr, recommendation systems
LESSR is lossless-enhanced session recommendation preserving order-aware transition information. - It retains sequential ordering while incorporating shortcut links…
content creation
Level design is the art and science of creating game environments and spatial experiences — designing layouts, challenges, pacing, and player flow to create engaging, fun…