1,008 technical terms and definitions
low rank adaptation, lora adapter, peft lora, lora rank selection
Low-Rank Adaptation (LoRA) is the parameter-efficient fine-tuning technique that adds small, trainable low-rank decomposition matrices to frozen pretrained weights — factoring…
generative models
LoRA for diffusion enables efficient fine-tuning to learn specific styles, subjects, or concepts with minimal resources. Application: Customize Stable Diffusion for particular…
generative models
LoRA for diffusion is the parameter-efficient fine-tuning method that trains low-rank adapter matrices instead of full model weights - it enables fast customization with smaller…
peft lora fine tuning, lora adapters, parameter efficient fine tuning, qlora workflow, adapter based llm customization
LoRA (Low-Rank Adaptation) is a parameter-efficient fine-tuning method that freezes the original model weights and trains small low-rank adapter matrices inserted into selected…
parameter efficient fine tuning peft, lora adapter training, qlora quantized lora, lora rank alpha
LoRA (Low-Rank Adaptation) is the parameter-efficient fine-tuning technique that adapts a large pre-trained model to new tasks by injecting small, trainable low-rank decomposition…
peft parameter efficient, adapter fine tuning, qlora quantized lora, fine tuning efficient
LoRA (Low-Rank Adaptation) is the parameter-efficient fine-tuning technique that adapts large language models to specific tasks by injecting small trainable low-rank matrices into…
Low-Rank Adaptation LoRA for Parameter-Efficient Tuning Introduction & Motivation Low-Rank Adaptation LoRA for Parameter-Efficient Tuning addresses a central problem in transfer…
generative models
LoRA merging is the process of combining one or more LoRA adapter weights into a base model or composite adapter set - it creates reusable model variants without retraining…
loss function computation precision and gradient flow, loss function computation, function computation precision, computation precision gradient, precision gradient flow
Loss Function Computation Precision and Gradient Flow Introduction & Motivation Loss Function Computation Precision and Gradient Flow addresses a central problem in training…
objective, minimize
A loss function is the single number a model's entire training process is trying to minimize — it measures how wrong a prediction is, and every weight update during training…
cross entropy, objective
Cross-entropy loss is the standard objective function for language model training, measuring the difference between predicted token probability distributions and actual (one-hot)…
quality
The Taguchi Loss Function is a revolutionary quality engineering philosophy formulated by Genichi Taguchi that fundamentally destroyed the prevailing industrial "goalpost"…
cost function, objective function
Loss Function — the mathematical function that measures how wrong the model's predictions are, providing the signal that guides training through gradient descent. Classification…
cross entropy loss, focal loss, triplet loss, contrastive loss function
Loss Functions are the mathematical objectives that quantify the discrepancy between model predictions and desired outputs, guiding the optimization process through gradient…
optimization objectives, custom loss functions, training objectives, loss landscape analysis
Loss Function Design and Optimization — Loss functions define the mathematical objective that neural networks minimize during training, translating task requirements into…
loss function design and selection, loss function design, function design selection, loss function, function design, design selection
Loss Function Design and Selection Introduction & Motivation Loss Function Design and Selection addresses a central problem in ml-training process control and loss-expressiveness…
loss function design, loss function, function design
Loss Function Design Introduction & Motivation Loss Function Design addresses a central problem in systems process control and loss-type-regression-classification prediction: how…
ml loss, training objective, cross entropy, focal loss, mse, mae, huber, contrastive loss
Loss function maps predictions and targets or preferences to an optimization signal. The loss defines what learning rewards and penalizes, so it shapes convergence, calibration…
quality & reliability
Loss Function Quality is a quality-economics model that maps deviation from target to monetary or operational loss - It is a core method in modern semiconductor quality…
loss functions cross entropy focal loss class imbalance, loss functions, cross entropy focal, ap ce cifar coco l1 nlp, loss functions cross-entropy focal loss & class imbalance
Loss Functions: Cross-Entropy, Focal Loss & Class Imbalance Introduction & Motivation Loss function: optimization objective. Cross-entropy: standard classification. Focal loss…
loss functions cross entropy focal loss contrastive, loss functions, cross entropy focal, cifar nt passed, loss functions cross-entropy focal loss & contrastive, cross-entropy focal loss
Loss Functions: Cross-Entropy, Focal Loss & Contrastive Introduction & Motivation Loss functions: model training objectives. Cross-entropy: classification standard. Focal loss…
loss functions different tasks, loss functions, functions different, loss functions different, functions different tasks, different tasks
Loss Functions for Different Tasks Introduction & Motivation Loss Functions: measure prediction error. Cross-entropy, MSE, Triplet loss. Applications: objective definition…
hidden loss manufacturing, manufacturing operations, efficiency loss
Hidden Loss is productivity loss not visible in standard reports due to data granularity or classification gaps - It conceals real capacity constraints and improvement…
theory
Loss Landscape Analysis is the study of the geometry of a neural network's loss function in parameter space — visualizing and characterizing the shape of the high-dimensional loss…
theory
Loss Landscape Smoothness refers to the geometric properties of the loss function surface in parameter space — smooth landscapes (low curvature, wide minima) correlate with better…
model training
Mixed-precision training is the standard recipe that lets modern models train in half the memory and roughly twice the throughput without losing accuracy. The idea is simple…
dynamic loss scaling, gradient scaling fp16, loss scale overflow, gradient underflow prevention
Loss Scaling Techniques are the numerical methods for preventing gradient underflow in FP16 training by multiplying the loss by a large scale factor (1024-65536) before…
instability, training
Loss spikes during training indicate instability that can derail optimization, typically caused by learning rate issues, bad data batches, gradient explosions, or numerical…
training phenomena
Loss Spikes are sudden, sharp increases in training loss that temporarily disrupt the training process — the loss dramatically increases for a few steps or epochs, then rapidly…
signal & power integrity
Loss Tangent is a dielectric property that quantifies energy dissipation under alternating electric fields - It governs frequency-dependent channel attenuation in PCB, package…
rag
Lost in the Middle is a positional degradation effect where models under-attend to information placed in the middle of long contexts - It is a core method in modern RAG…
challenges
Lost in the middle is the long-context failure pattern where models attend less to information placed in middle prompt positions than to beginning or end positions - this bias can…
production
A semiconductor lot is an identified group of wafers managed together for manufacturing control. The lot gives scheduling, route execution, quality decisions, and material history…
lot die genealogy traceability machine learning, lot die, genealogy traceability machine, lot and die genealogy traceability, lot die genealogy, die genealogy traceability
Lot and Die Genealogy Traceability with Machine Learning Introduction & Motivation Lot and Die Genealogy Traceability with Machine Learning addresses a central problem…
lot cycle time flow time prediction fab logistics, lot cycle, time flow time, pm wip, lot cycle time, cycle time flow, flow time prediction, time prediction fab, cycle time
Lot Cycle Time and Flow Time Prediction for Fab Logistics Introduction & Motivation Lot Cycle Time and Flow Time Prediction for Fab Logistics addresses a central problem in wafer…
lot dispatch priority starvation risk prediction, lot dispatch priority, dispatch priority starvation, priority starvation risk, starvation risk prediction
Lot Dispatch Priority Starvation Risk Prediction with Machine Learning Introduction & Motivation Lot Dispatch Priority Starvation Risk Prediction with Machine Learning addresses…
lot dispatch rule optimization prediction machine learning, lot dispatch, rule optimization prediction, lot dispatch rule optimization prediction, lot dispatch rule
Lot Dispatch Rule Optimization Prediction with Machine Learning Introduction & Motivation Lot Dispatch Rule Optimization Prediction with Machine Learning addresses a central…
lot dispatch rule yield impact prediction, lot dispatch rule, dispatch rule yield, rule yield impact, yield impact prediction, lot dispatch, dispatch rule, rule yield
Lot Dispatch Rule Yield Impact Prediction with Machine Learning Introduction & Motivation Lot Dispatch Rule Yield Impact Prediction with Machine Learning addresses a central…
lot genealogy data integrity drift prediction, lot genealogy data, genealogy data integrity, data integrity drift, integrity drift prediction, lot genealogy, genealogy data
Lot Genealogy Data Integrity Drift Prediction with Machine Learning Introduction & Motivation Lot Genealogy Data Integrity Drift Prediction with Machine Learning addresses…
lot genealogy graph embedding yield prediction machine learning, lot genealogy, graph embedding yield, mes, lot genealogy graph embedding yield prediction
Lot Genealogy Graph Embedding Yield Prediction with Machine Learning Introduction & Motivation Lot Genealogy Graph Embedding Yield Prediction with Machine Learning addresses…
lot genealogy tracking yield attribution prediction, lot genealogy tracking, genealogy tracking yield, tracking yield attribution, yield attribution prediction, lot genealogy
Lot Genealogy Tracking Yield Attribution Prediction with Machine Learning Introduction & Motivation Lot Genealogy Tracking Yield Attribution Prediction with Machine Learning…
manufacturing operations
Lot Hold is an operational status that freezes lot movement pending engineering, quality, or equipment disposition - It is a core method in modern engineering execution workflows.…
lot hold duration prediction, lot hold duration, hold duration prediction, lot hold, hold duration, duration prediction
Lot Hold Duration Prediction with Machine Learning Introduction & Motivation Lot Hold Duration Prediction with Machine Learning addresses a central problem in manufacturing hold…
batch combination, manufacturing scheduling
Lot merging is a fab scheduling operation that combines multiple smaller wafer lots into a single larger lot for joint processing, trading equipment-changeover time for the loss…
traceability
Lot number is the unique production identifier assigned to a group of units processed under common manufacturing conditions - it is the backbone of semiconductor traceability…
manufacturing operations
Lot Number is the identifier assigned to a wafer batch moving together through manufacturing operations - It is a core method in modern engineering execution workflows. What Is…
lot priority queue wait time prediction, lot priority queue, priority queue wait, queue wait time, wait time prediction, lot priority, priority queue, queue wait, wait time
Lot Priority Queue Wait Time Prediction with Machine Learning Introduction & Motivation Lot Priority Queue Wait Time Prediction with Machine Learning addresses a central problem…
supply chain & logistics
Lot Sizing is determination of order or production quantity per batch to balance cost and service - It affects setup frequency, inventory levels, and responsiveness. What Is Lot…
operations
Lot splitting is the operation of dividing a parent lot into smaller child lots for parallel processing, experimentation, or expedited movement - it increases routing flexibility…
lot-to-lot process drift prediction, lot-to-lot process drift, process drift prediction, lot-to-lot process, process drift, drift prediction
Lot-to-Lot Process Drift Prediction with Machine Learning Introduction & Motivation Lot-to-Lot Process Drift Prediction with Machine Learning addresses a central problem…