2,221 technical terms and definitions
model optimization, quantization pruning distillation, efficient inference
Model compression refers to a family of techniques that reduce the size, memory footprint, and computational cost of neural networks while preserving as much accuracy as possible.…
model compression and accuracy preservation, model compression accuracy, compression accuracy preservation, model compression, compression accuracy, accuracy preservation
Model Compression and Accuracy Preservation Introduction & Motivation Model Compression and Accuracy Preservation addresses a central problem in ml-inference process control…
edge ai
Model Compression for Edge Deployment is the set of techniques to reduce neural network size and computational requirements — enabling deployment of powerful models on…
edge ai
Model compression for mobile encompasses techniques to reduce model size and computational requirements so that machine learning models can run efficiently on smartphones…
101245 model, model compression, cifar, residual networks & skip connections, residual networks skip, networks skip connections, residual networks, networks skip, skip connections
Residual Networks & Skip Connections Introduction & Motivation Residual Networks: enable deeper architectures. Skip connections, residual blocks. Applications: very deep networks…
model compression, pruning efficient neural, 100mb 10mb ce kl nas passed, model compression & pruning efficient neural networks, model compression pruning, compression pruning efficient
Model Compression & Pruning: Efficient Neural Networks Introduction & Motivation Model compression: reduce model size/inference cost. Pruning: remove weights; structured…
model compression pruning, model compression, compression pruning
Model Compression Pruning Introduction & Motivation Model Compression Pruning addresses a central problem in systems process control and pruning-strategy-magnitude-structured…
model compression quantization pruning knowledge distillation, model compression, quantization pruning knowledge, ar awq bert c4 ce fp16, model compression quantization
Model Compression: Quantization, Pruning, and Knowledge Distillation 1. Introduction & Motivation Model compression reduces the size, memory footprint, and inference latency…
neural network pruning, weight pruning structured, magnitude pruning lottery ticket, compression deep learning
Model Compression Techniques are the family of methods that reduce neural network size, memory footprint, and computational cost while preserving accuracy — including pruning…
model compression techniques, model compression, compression techniques
Model Compression Techniques Introduction & Motivation Model Compression Techniques addresses a central problem in ml-training process control and compression-ratio-achieved…
model optimization
Model Conversion is transforming model formats between frameworks and runtimes for deployment compatibility - It is often required to move from training stacks to production…
Model Debugging via Explanations Introduction & Motivation Model Debugging via Explanations addresses a central problem in explainability interpretation and model understanding…
inference optimization techniques, runtime optimization neural networks, deployment efficiency, production inference optimization
Model Deployment Optimization is the comprehensive process of preparing trained neural networks for production inference — encompassing graph optimization, operator fusion, memory…
model deployment, deployment optimization, api aws cd ci gcp, model deployment & optimization
Model Deployment & Optimization Introduction & Motivation Deployment: bring models to production. Containerization, serving infrastructure. Applications: scalable inference…
model deployment, deployment serving, api ml nlp onnx passed rest, model deployment & serving
Model Deployment & Serving Introduction & Motivation Model Deployment: put trained models into production. Serving infrastructure; real-time inference. Applications: web services…
doe
Model Discrimination Design is a DOE strategy specifically designed to distinguish between competing statistical models — selecting experiments that maximize the expected…
knowledge distillation efficiency, knowledge distillation, distillation efficiency
Knowledge Distillation Efficiency Introduction & Motivation Knowledge Distillation Efficiency addresses a central problem in ml-training process control and student-teacher-gap…
knowledge distillation, teacher student, soft labels, logit distillation, feature distillation
Model distillation trains a smaller student to reproduce useful behavior or internal representations of a larger teacher. It converts expensive model capability into…
Model Distillation into Interpretable Surrogates Introduction & Motivation Model Distillation into Interpretable Surrogates addresses a central problem in interpretability…
Model Distillation into Interpretable Surrogates (Extended Study) Introduction & Motivation Model Distillation into Interpretable Surrogates (Extended Study) addresses a central…
Model Distillation into Interpretable Surrogates (Extended Study) Introduction & Motivation Model Distillation into Interpretable Surrogates (Extended Study) addresses a central…
teacher student training, dark knowledge transfer, logit distillation, feature distillation
Knowledge Distillation is the model compression technique where a smaller student network is trained to replicate the behavior of a larger teacher network — learning not just…
teacher student network, knowledge transfer distillation, soft label distillation, distillation training
Knowledge Distillation is the model compression technique where a smaller "student" network is trained to mimic the behavior of a larger, more capable "teacher" network…
Rule Distillation from Complex Models Introduction & Motivation Rule Distillation from Complex Models addresses a central problem in explainability interpretation and model…
model training
Model editing directly updates specific weights to fix factual errors or modify behaviors without full retraining. Motivation: Models contain factual errors, knowledge becomes…
model editing knowledge editing large language models, model editing, knowledge editing large, ceo llm memit mend mlp peft, model editing & knowledge editing in large language models
Model Editing & Knowledge Editing in Large Language Models 1. Introduction & Motivation Large language models memorize an enormous number of facts during pretraining, but that…
model ensemble inference and resource sharing overhead, model ensemble inference, ensemble inference resource, inference resource sharing, resource sharing overhead, model ensemble
Model Ensemble Inference and Resource Sharing Overhead Introduction & Motivation Model Ensemble Inference and Resource Sharing Overhead addresses a central problem in inference…
reinforcement learning advanced
Model ensemble RL is reinforcement-learning approaches that use multiple models or policies to improve robustness and uncertainty handling - Ensembles aggregate predictions…
llm evaluation, ai evaluation, mmlu, humaneval, gsm8k, benchmarking, model judge, human evaluation, goodhart law
Model evaluation is the disciplined measurement of an AI model’s capabilities, limitations, risks, efficiency, and fitness for a stated deployment. A score becomes useful only…
capability elicitation, few shot prompting evaluation, benchmark contamination
LLM Capability Elicitation and Evaluation is the systematic process of measuring what a language model can and cannot do — including prompt engineering for evaluation, avoiding…
llm evaluation framework, evaluation harness, benchmark contamination, llm benchmark design
LLM Evaluation and Benchmarking is the systematic methodology for measuring language model capabilities across diverse tasks — encompassing academic benchmarks (MMLU, HumanEval…
Aggregating Multiple Explanations Introduction & Motivation Aggregating Multiple Explanations addresses a central problem in explainability interpretation and model understanding…
interoperability, framework portability
ONNX for Model Interoperability What is ONNX? ONNX (Open Neural Network Exchange) is an open format for representing machine learning models, enabling interoperability between…
stealing, query
Model Extraction (Model Stealing) is the adversarial attack where an adversary reconstructs a functional copy of a proprietary machine learning model by systematically querying…
interpretability
Model Extraction is an attack that approximates a target model by repeatedly querying its prediction API - It can replicate decision behavior and expose intellectual property…
ai safety
Model extraction attack (also called model stealing) is a security attack where an adversary aims to recreate a proprietary ML model by systematically querying it and using…
model extraction, extraction knowledge, api ip kl, model extraction & knowledge theft, model extraction knowledge, extraction knowledge theft, knowledge theft
Model Extraction & Knowledge Theft Introduction & Motivation Model extraction: steal model knowledge via queries. Recover models via API access. Applications: security…
model extraction stealing, model extraction, extraction stealing
Model Extraction Stealing Introduction & Motivation Model Extraction Stealing addresses a central problem in systems process control and extraction-attack-query-based prediction…
unique, identify
Model Fingerprinting is the technique of identifying or verifying a machine learning model's identity based on its behavioral characteristics — using carefully crafted probe…
mfu, optimization
Model FLOPs utilization is the efficiency metric that estimates how much useful model computation is achieved relative to hardware capability - it separates productive model math…
Model-Free vs Model-Based Learning Introduction & Motivation Model-Free vs Model-Based Learning addresses a central problem in reinforcement policy learning…
model governance audit trail prediction fab ml systems, model governance, audit trail prediction, ml, model governance audit, governance audit trail, trail prediction fab
Model Governance and Audit Trail Prediction for Fab ML Systems Introduction & Motivation Model Governance and Audit Trail Prediction for Fab ML Systems addresses a central problem…
model inference energy efficiency prediction, model inference energy, inference energy efficiency, energy efficiency prediction, model inference, inference energy
Model Inference Energy Efficiency Prediction with Machine Learning Introduction & Motivation Model Inference Energy Efficiency Prediction with Machine Learning addresses a central…
portable model format, framework exchange
ONNX (Open Neural Network Exchange) is an open-source format for representing machine learning models, enabling interoperability between different frameworks and deployment…
gradient attribution saliency, shap lime explanation, attention visualization model, feature importance neural
Neural Network Interpretability and Explainability is the research and engineering discipline that develops methods to understand why neural networks make specific predictions…
shap shapley values, grad cam saliency, attention visualization, feature attribution method
Model Interpretability and Explainability encompasses the techniques for understanding why neural networks make specific predictions — from gradient-based saliency maps showing…
interpretability
Model Inversion is an attack that reconstructs sensitive input features from model outputs or gradients - It exposes privacy risk by inferring private attributes from accessible…
ai safety
Model inversion attacks reconstruct training data from model parameters or prediction outputs. Attack types: Class representative: Reconstruct average input for a class - what…
privacy
Model Inversion Attacks are privacy attacks that reconstruct private training data (or representative features) from a trained model — exploiting the model's predictions…
privacy
Model inversion defense encompasses techniques to prevent attackers from reconstructing training data by querying or analyzing a trained machine learning model. Model inversion…