1,510 technical terms and definitions
model serving, deployment tensorflow serving, api cpu gpu ml onnx passed, model serving & deployment tensorflow serving onnx & production, model serving deployment, serving onnx
Model deployment is the gap between a model that works in a training notebook and a model that answers real requests under a real latency budget, and almost everything in that gap…
model serving framework selection, model serving framework, serving framework selection, model serving, serving framework, framework selection
Model Serving Framework Selection Introduction & Motivation Model Serving Framework Selection addresses a central problem in ml-ops process control…
ml model deployment, model optimization serving, onnx runtime inference, triton inference server
ML Model Serving and Inference Optimization is the engineering discipline of deploying trained models into production systems that process real-time requests at scale — where…
tensorrt onnx runtime, deep learning deployment, inference acceleration, model optimization serving latency
Deep Learning Model Serving and Inference Optimization is the engineering discipline of deploying trained neural networks into production environments with minimal latency…
model serving inference optimization, model serving inference, serving inference optimization, model serving, serving inference, inference optimization
Model Serving Inference Optimization Introduction & Motivation Model Serving Inference Optimization addresses a central problem in systems process control…
model serving with memory contention and shared l3 cache, model serving memory, serving memory contention, memory contention shared, contention shared l3, shared l3 cache, shared l3
Model Serving with Memory Contention and Shared L3 Cache Introduction & Motivation Model Serving with Memory Contention and Shared L3 Cache addresses a central problem…
model serving and inference deployment, model serving inference, serving inference deployment, model serving, serving inference, inference deployment
Model Serving and Inference Deployment Introduction & Motivation Model Serving and Inference Deployment addresses a central problem in ml-inference process control…
infrastructure
Model Serving Platform is the infrastructure layer that deploys trained machine learning models as scalable, production-ready prediction services — abstracting away the complexity…
inference serving architecture, production model deployment, serving infrastructure, model serving frameworks
Model Serving Systems are the production infrastructure for deploying trained neural networks as scalable, reliable services — providing request handling, batching, load…
model training
Model size refers to the amount of storage space required to store a neural network's weights and associated metadata, determining the hardware requirements for loading, serving…
model merging
Model Soup is a model merging technique that averages the weights of multiple fine-tuned models — taking several models fine-tuned with different hyperparameters from the same…
privacy
Model stealing (model extraction) is an adversarial attack that reconstructs a functional replica of a proprietary machine learning model by systematically querying its prediction…
model merging
Model Stitching is a technique that combines layers from different pre-trained models into a single network — inserting a small "stitching layer" (typically a 1×1 convolution…
explainable ai
Model stitching for understanding is the technique that connects layers from different models with learned adapters to test representational compatibility - it probes whether…
extraction, protect
Model Extraction and Protection What is Model Extraction? Attacks that steal ML models by querying them and training a copy, enabling intellectual property theft and attack…
training, pre-training, fine-tuning, rlhf, tokenization, scaling laws, distributed training
Large Language Model Training Modern LLM training follows a systematic approach from data to deployment: Training Pipeline Overview Large Language Model training is a multi-stage…
training steps, training duration
An epoch is one complete pass through the entire training dataset, a fundamental unit of training progress. Definition: Every example seen exactly once = one epoch. Multiple…
how are llms trained, how neural networks are trained, model training loop, how ai models are trained, gradient descent training, deep learning training
Training is the process of teaching a machine-learning model by repeatedly showing it data and adjusting its internal parameters — its weights — until its predictions match…
training monitoring
Early stopping halts training when validation performance stops improving, preventing overfitting. Mechanism: Monitor validation metric each epoch/N steps. If no improvement…
model uncertainty quantification, model uncertainty, uncertainty quantification
Model Uncertainty Quantification Introduction & Motivation Model Uncertainty Quantification addresses a central problem in ml-analysis process control…
quantifying model uncertainty for reliable predictions, quantifying model uncertainty, model uncertainty reliable, uncertainty reliable predictions, quantifying model
Quantifying model uncertainty for reliable predictions Introduction & Motivation Quantifying model uncertainty for reliable predictions addresses a central problem in Machine…
Model Uncertainty vs Data Uncertainty Introduction & Motivation Model Uncertainty vs Data Uncertainty addresses a central problem in uncertainty methods and prediction intervals…
security
Model Verification in the context of AI security is the process of verifying that a deployed model has not been tampered with, corrupted, or replaced — ensuring model integrity…
mlops
Model versioning systematically tracks different versions of trained machine learning models along with their associated metadata — training data, hyperparameters, evaluation…
model versioning system, model versioning, versioning system
Model Versioning System Introduction & Motivation Model Versioning System addresses a central problem in ml-ops process control and version-storage-overhead prediction: how…
pipeline parallelism explained, tensor parallelism explained, splitting large models across gpus, distributed training strategies, ai training cluster architecture
Data parallelism and model parallelism are the two fundamentally different ways to split a training job across many chips, and they solve two completely different problems — one…
ai safety
Watermarking embeds a hidden, verifiable signal into a model's output or its weights, and the design constraint that shapes every scheme is the same: the signal has to survive…
llm watermark, text watermarking, green red token watermark, watermark detection
AI Model and Output Watermarking encompasses techniques for embedding invisible, detectable signatures into AI model weights or generated outputs (text, images, audio), enabling…
model weight distribution drift prediction, model weight distribution, weight distribution drift, distribution drift prediction, model weight, weight distribution
Model Weight Distribution Drift Prediction with Machine Learning Introduction & Motivation Model Weight Distribution Drift Prediction with Machine Learning addresses a central…
parameters, safetensors, checkpoint, open weights, GGUF, quantization, pickle, NTIA open weights report
Model weights are the learned numerical parameters of a neural network, the millions or billions of numbers that training adjusts and that together determine what the model does.…
AI welfare, Taking AI Welfare Seriously, Long et al. 2024, moral patienthood, AI moral status, Anthropic model welfare program, digital minds
Model welfare is the study of whether AI systems might have interests, experiences or other properties that would make them deserving of moral consideration, and of what, if…
modem throughput spectral efficiency prediction, modem throughput spectral, throughput spectral efficiency, spectral efficiency prediction, modem throughput
Modem Throughput Spectral Efficiency Prediction with Machine Learning Introduction & Motivation Modem Throughput Spectral Efficiency Prediction with Machine Learning addresses…
ai safety
Moderation API is the service interface for classifying text or media against safety policy categories before or after model generation - it enables automated enforcement…
neural architecture
Modern Hopfield Networks is the contemporary variant of Hopfield networks with continuous-valued patterns and improved scaling for large dense memories — Modern Hopfield Networks…
modular exponentiation fast, modular exponentiation, exponentiation fast
Modular Exponentiation Fast Introduction & Motivation Modular Exponentiation Fast addresses a central problem in algorithms process control and exponentiation-log-exponent…
Modular Multi-Task Networks Introduction & Motivation Modular Multi-Task Networks addresses a central problem in multitask learning across several related prediction objectives…
Modular Multi-Task Networks (Extended Study) Introduction & Motivation Modular Multi-Task Networks (Extended Study) addresses a central problem in multitask learning across…
Modular Multi-Task Networks (Extended Study) Introduction & Motivation Modular Multi-Task Networks (Extended Study) addresses a central problem in multitask learning across…
conditional computation, mixture of experts, neural modularity, expert routing
Modular Networks are neural architectures built from multiple specialized computational components rather than one monolithic dense model, allowing the system to activate only…
neural architecture
Modular Neural Networks are neural architectures composed of distinct, independently trained or jointly trained modules — each learning a reusable function or skill — that can be…
modular robot reconfigurable, modular robot, robot reconfigurable
Modular Robot Reconfigurable Introduction & Motivation Modular Robot Reconfigurable addresses a central problem in robotics process control and modular-unit-connection-interface…
Modular Transfer Learning Introduction & Motivation Modular Transfer Learning addresses a central problem in transfer learning and {target} adaptation: how to Apply {subject}…
modulation error ratio prediction, modulation error ratio, error ratio prediction, modulation error, error ratio, ratio prediction
Modulation Error Ratio Prediction with Machine Learning Introduction & Motivation Modulation Error Ratio Prediction with Machine Learning addresses a central problem in modulation…
module in package thermal resistance prediction, module package thermal, package thermal resistance, thermal resistance prediction, module package, package thermal
Module In Package Thermal Resistance Prediction with Machine Learning Introduction & Motivation Module In Package Thermal Resistance Prediction with Machine Learning addresses…
module organization namespace, module organization, organization namespace
Module Organization Namespace Introduction & Motivation Module Organization Namespace addresses a central problem in programming process control and module-hierarchy-nesting-depth…
modulus of elasticity variation prediction, modulus elasticity variation, elasticity variation prediction, modulus elasticity, elasticity variation, variation prediction
Modulus of Elasticity Variation Prediction with Machine Learning Introduction & Motivation Modulus of Elasticity Variation Prediction with Machine Learning addresses a central…
mixture of experts, experts, gating, sparse model, mixtral, routing, efficiency
Mixture of Experts (MoE) is the sparse-activation architecture that scales a neural network to trillions of parameters while keeping per-token compute fixed — each input activates…
moisture absorption rate prediction, moisture absorption rate, absorption rate prediction, moisture absorption, absorption rate, rate prediction
Moisture Absorption Rate Prediction with Machine Learning Introduction & Motivation Moisture Absorption Rate Prediction with Machine Learning addresses a central problem…
moisture absorption material prediction, moisture absorption material, absorption material prediction, moisture absorption, absorption material, material prediction
Moisture Absorption Material Prediction with Machine Learning Introduction & Motivation Moisture Absorption Material Prediction with Machine Learning addresses a central problem…
MSL compliance, dry pack system, desiccant humidity indicator, seal integrity verification, silent seal failure, floor life assumption, incoming inspection moisture
A moisture barrier bag is the specialized low-permeability packaging used to protect moisture-sensitive semiconductor components during storage and transport, functioning as…