model flops utilization
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…
2,310 technical terms and definitions
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…
Hugging Face Hub, model registry, model cards, Mitchell 2019, from_pretrained, model versioning, TensorFlow Hub, PyTorch Hub
A model hub is an online registry where trained machine learning models are published, discovered, versioned and downloaded, in the way a package index such as PyPI serves code…
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
Interpretability asks why a model produced a specific output, and the field's central, uncomfortable tension is between an explanation that looks convincing and an explanation…
shap shapley values, grad cam saliency, attention visualization, feature attribution method
Interpretability asks why a model produced a specific output, and the field's central, uncomfortable tension is between an explanation that looks convincing and an explanation…
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…
model inversion membership, model inversion, inversion membership
Model Inversion Membership Introduction & Motivation Model Inversion Membership addresses a central problem in systems process control and membership-inference-attack prediction…
model training
Model merging combines weights from multiple fine-tuned models to create a single model with combined capabilities. Methods: Linear interpolation (weighted average of weights)…
model averaging, slerp merging, weight interpolation, model fusion
Model Merging is a technique that combines multiple fine-tuned LLMs into a single model by interpolating or adding their weight spaces — creating models with combined capabilities…
model soup, slerp merge, ties merge, dare merge
Model Merging is the technique of combining the weights of multiple independently fine-tuned models into a single model without additional training — creating models that inherit…
model soup, TIES merging, DARE merging, frankenmerge, weight interpolation
Model Merging is the technique of combining the weights of multiple fine-tuned models into a single model without additional training — by interpolating, averaging, or selectively…
weight averaging, model soups, task arithmetic, federated averaging
Model Merging and Weight Averaging — Combining Neural Networks Without Retraining Model merging combines the parameters of multiple trained neural networks into a single model…
model soup, model averaging, task arithmetic merging, slerp merging
Model Merging is the technique of combining the weights of multiple independently-trained or fine-tuned neural networks into a single model that inherits the capabilities of all…
model merging task arithmetic combining fine tuned models without retraining, model merging, task arithmetic combining, cpu dare glue gpu slerp ties, merging task
Model Merging & Task Arithmetic: Combining Fine-Tuned Models Without Retraining Introduction & Motivation Fine-tuning a large pretrained model on a new task or dataset…
ml model monitoring, production model monitoring, ml observability, model performance monitoring
Model monitoring definition and system boundary. Model monitoring is the continuous measurement of a deployed model, its inputs and outputs, the serving system, and eventual…
model monitoring and drift detection, model monitoring drift, monitoring drift detection, model monitoring, monitoring drift, drift detection
Model Monitoring and Drift Detection Introduction & Motivation Model Monitoring and Drift Detection addresses a central problem in ml-ops process control…
model monitoring drift detection, model monitoring drift, monitoring drift detection, model monitoring, monitoring drift, drift detection
Model Monitoring Drift Detection Introduction & Motivation Model Monitoring Drift Detection addresses a central problem in systems process control…
Output-Level Explanation Methods Introduction & Motivation Output-Level Explanation Methods addresses a central problem in explainability interpretation and model understanding…
model training
Model parallelism splits model layers across devices, enabling training models too large for single GPU memory. Motivation: Models like GPT-3 (175B) exceed single GPU memory. Must…
tensor parallelism, pipeline parallelism, sequence parallelism, expert parallelism, megatron
Model parallelism partitions model parameters, activations, or layer computation across accelerators. It enables models and contexts that cannot fit on one GPU and can raise…
model parallelism communication overhead and synchronization, model parallelism communication, parallelism communication overhead, communication overhead synchronization, model parallelism
Model Parallelism Communication Overhead and Synchronization Introduction & Motivation Model Parallelism Communication Overhead and Synchronization addresses a central problem…
model parallelism layer distribution and device placement, model parallelism layer, parallelism layer distribution, layer distribution device, distribution device placement
Model Parallelism Layer Distribution and Device Placement Introduction & Motivation Model Parallelism Layer Distribution and Device Placement addresses a central problem…
distributed training
Model parallelism strategies split large neural networks across multiple GPUs when a model doesn't fit in single GPU memory, enabling training and inference of models…
distributed model training, tensor parallelism model, pipeline parallelism training, 3d parallelism
Model Parallelism Strategies are the techniques for distributing a single neural network across multiple GPUs or nodes when the model is too large to fit on a single device…
mpc, control theory
Model Predictive Control (MPC) is an advanced control strategy that uses a mathematical model of the system to predict future behavior — and solves an optimization problem at each…
manufacturing operations
Model Predictive Control is an optimization-based control strategy that computes future control moves over a prediction horizon - It is a core method in modern semiconductor…
Model Predictive Control for RL Introduction & Motivation Model Predictive Control for RL addresses a central problem in sequential decision making via deeprl: how to Learn…
Model Predictive Control for RL (Extended Study) Introduction & Motivation Model Predictive Control for RL (Extended Study) addresses a central problem in sequential decision…
Model Predictive Control for RL (Extended Study) Introduction & Motivation Model Predictive Control for RL (Extended Study) addresses a central problem in sequential decision…
process control
MPC (Model Predictive Control) in semiconductor manufacturing is a multi-variable control strategy that uses a process model to predict future outputs and optimize control actions…
model predictive control mpc, model predictive control, predictive control mpc, model predictive, predictive control, control mpc
Model Predictive Control MPC Introduction & Motivation Model Predictive Control MPC addresses a central problem in robotics process control and predictive-model-future-trajectory…
model predictive control (mpc) prediction, model predictive control, predictive control (mpc), control (mpc) prediction, model predictive, predictive control, control (mpc)
Model Predictive Control (MPC) Prediction with Machine Learning Introduction & Motivation Model Predictive Control (MPC) Prediction with Machine Learning addresses a central…
Model Predictive Path Integral MPPI Control Introduction & Motivation Model Predictive Path Integral MPPI Control addresses a central problem in reinforcement policy learning…
structured pruning, channel pruning, filter pruning, network slimming
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
weight pruning neural network, lottery ticket hypothesis, magnitude pruning, sparse neural network
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
structured unstructured pruning, magnitude pruning lottery ticket, pruning neural network compression, iterative pruning fine tuning
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
model quantization accuracy loss prediction, model quantization accuracy, quantization accuracy loss, accuracy loss prediction, model quantization, quantization accuracy
Model Quantization Accuracy Loss Prediction with Machine Learning Introduction & Motivation Model Quantization Accuracy Loss Prediction with Machine Learning addresses a central…
quantization, post training quantization, ptq, qat, gptq, awq, smoothquant, int8, int4
Model quantization reduces the numerical precision used to store or compute neural-network weights and activations. Moving FP32 models to FP16, BF16, FP8, INT8, INT4, or mixed…
weight quantization llm, int8 int4 quantization, gptq awq quantization, quantization aware training
Model Quantization is the inference optimization technique that reduces the numerical precision of neural network weights and activations from 32-bit or 16-bit floating-point…
int8 int4 quantization, gptq awq quantization, weight quantization llm, post training quantization
Model Quantization is the compression technique that reduces neural network weight and activation precision from 32-bit or 16-bit floating point to lower bit-widths (INT8, INT4…
post training quantization, quantization aware training, quantization calibration range, weight activation quantization
Model Quantization is the neural network compression technique that converts floating-point weights and activations to lower-precision integer representations (INT8, INT4…
post training quantization ptq, quantization aware training qat, int8 int4 quantization, weight activation quantization
Model Quantization is the compression technique that reduces neural network weight and activation precision from 32-bit floating-point to lower-bitwidth representations (INT8…
ml model registry, model versioning, mlflow registry, wandb artifacts, sagemaker model registry, vertex ai registry
Model registry is an authoritative catalog of versioned model artifacts, metadata, lineage, approvals and deployment status. It turns an opaque checkpoint file into a governed…
mlops
A model registry is a central repository for storing, versioning, and managing trained machine learning models. Core features: Versioning: Track model versions with metadata.…