2,310 technical terms and definitions
mobilenet lightweight architecture and depthwise separable convolution, mobilenet lightweight architecture, lightweight architecture depthwise, architecture depthwise separable
MobileNet Lightweight Architecture and Depthwise Separable Convolution Introduction & Motivation MobileNet Lightweight Architecture and Depthwise Separable Convolution addresses…
computer vision
MobileNetV2 is the second generation of MobileNet that introduces inverted residual blocks with linear bottlenecks — expanding channels before depthwise convolution (inverted…
model optimization
MobileNetV2 is an improved MobileNet architecture using inverted residual blocks and linear bottlenecks - It increases efficiency and accuracy relative to earlier mobile…
computer vision
MobileNetV3 is the third generation MobileNet, co-designed by neural architecture search and human expertise — combining NAS-discovered architecture (MnasNet) with manual…
model optimization
MobileNetV3 is a hardware-aware mobile architecture combining efficient blocks, squeeze-excitation, and optimized activations - It targets better accuracy-latency tradeoffs on…
carrier mobility improvement, channel mobility optimization, scattering reduction, transport enhancement
Mobility Enhancement Techniques are the comprehensive set of methods to increase carrier mobility in the transistor channel — including strain engineering, interface optimization…
carrier mobility improvement, high mobility channel, mobility boosters cmos, transport enhancement
Mobility Enhancement Techniques are the comprehensive set of process and material innovations that increase carrier mobility in CMOS transistors beyond intrinsic silicon values…
simulation
Mobility Modeling is the TCAD simulation of charge carrier drift mobility (μ) as a function of doping concentration, electric field, temperature, interface quality, and crystal…
device physics
Mobility variation is the spread in carrier transport efficiency across devices caused by local differences in scattering, strain, and interface quality - it directly modulates…
audio & speech
MoChA is monotonic chunkwise attention that combines online monotonic alignment with local soft attention - It relaxes strict monotonicity by attending within small chunks after…
code ai
Mock Generation is the AI task of automatically creating mock objects, stub functions, and fake implementations that simulate complex external dependencies — databases, APIs, file…
moco, momentum contrast, self-supervised learning
MoCo (Momentum Contrast) enables contrastive learning with large negative sample pools using a momentum encoder. Problem solved: Contrastive learning needs many negatives, but…
Momentum Contrast Method Introduction & Motivation Momentum Contrast Method addresses a central problem in selfsupervised and momentum-encoder-update architecture: how…
MoCo v3 Self-Supervised Vision Transformers with Freeze Patch Introduction & Motivation MoCo v3 Self-Supervised Vision Transformers with Freeze Patch addresses a central problem…
mocvd compound semiconductor composition uniformity prediction, mocvd compound semiconductor, compound semiconductor composition, semiconductor composition uniformity
MOCVD Compound Semiconductor Composition Uniformity Prediction with Machine Learning Introduction & Motivation MOCVD Compound Semiconductor Composition Uniformity Prediction…
mocvd precursor utilization efficiency prediction, mocvd precursor utilization, precursor utilization efficiency, utilization efficiency prediction, mocvd precursor
MOCVD Precursor Utilization Efficiency Prediction with Machine Learning Introduction & Motivation MOCVD Precursor Utilization Efficiency Prediction with Machine Learning addresses…
mocvd reactor wafer carrier wobble prediction machine learning, mocvd reactor, wafer carrier wobble, cvd mocvd, mocvd reactor wafer carrier wobble prediction
MOCVD Reactor Wafer Carrier Wobble Prediction with Machine Learning Introduction & Motivation MOCVD Reactor Wafer Carrier Wobble Prediction with Machine Learning addresses…
serverless
Modal is the serverless cloud platform for Python that enables running GPU-accelerated AI workloads in the cloud by defining infrastructure requirements directly in Python code…
multimodal ai
Modality Dropout is an aggressive, highly effective regularization technique within deep learning architecture intentionally designed to induce severe, chaotic sensory deprivation…
multimodal ai
Modality Hallucination is a knowledge distillation technique where a model learns to internally generate (hallucinate) the features of a missing modality at inference time…
unimodal bimodal multimodal distribution, mode for categorical data, mean median mode relationship
The mode is the most frequently occurring value in a dataset — the only measure of central tendency that's meaningfully defined for nominal categorical data, where values are…
theory
Mode Connectivity is the observation that distinct minima of neural network loss functions are often connected by low-loss paths — meaning there exist smooth trajectories…
model merging
Mode Interpolation (Linear Mode Connectivity) is a model merging technique based on the observation that fine-tuned models from the same pre-trained checkpoint are connected by…
ai model, machine learning model
A model, in the machine learning sense, is a fixed set of learned numeric parameters — weights and biases arranged in a particular architecture — that maps an input to an output…
security
Model access control is the set of policies and technical mechanisms that govern who can use, modify, download, or inspect a machine learning model. As AI models become valuable…
Quantitative Metrics for Counterfactual Explanations Introduction & Motivation Quantitative Metrics for Counterfactual Explanations addresses a central problem in explainability…
Model-Agnostic Meta-Learning Introduction & Motivation Model-Agnostic Meta-Learning addresses a central problem in transfer learning and {target} adaptation: how to Apply…
Model-Agnostic Meta-Learning (MAML) Introduction & Motivation Model-Agnostic Meta-Learning (MAML) addresses a central problem in metalearning learning and rapid task adaptation…
model-agnostic meta-learning (maml) and fast adaptation, model-agnostic meta-learning (maml), meta-learning (maml) fast, (maml) fast adaptation, model-agnostic meta-learning
Model-Agnostic Meta-Learning (MAML) and Fast Adaptation Introduction & Motivation Model-Agnostic Meta-Learning (MAML) and Fast Adaptation addresses a central problem in MAML…
Model-Agnostic Meta-Learning (MAML) (Extended Study) Introduction & Motivation Model-Agnostic Meta-Learning (MAML) (Extended Study) addresses a central problem in metalearning…
Model-Agnostic Meta-Learning (MAML) (Extended Study) Introduction & Motivation Model-Agnostic Meta-Learning (MAML) (Extended Study) addresses a central problem in metalearning…
Model-Agnostic Meta-Learning (MAML) (Extended Study) Introduction & Motivation Model-Agnostic Meta-Learning (MAML) (Extended Study) addresses a central problem in metalearning…
neural architecture search methods, neural architecture search, architecture search methods, neural architecture, architecture search, search methods
Neural Architecture Search Methods Introduction & Motivation Neural Architecture Search Methods addresses a central problem in ml-architecture process control…
mlops
Model artifact management is the controlled handling of trained model files and related assets across development, validation, and deployment stages - it ensures model binaries…
model artifact management, model artifact, artifact management
Model Artifact Management Introduction & Motivation Model Artifact Management addresses a central problem in ml-ops process control and artifact-storage-efficiency prediction: how…
machine learning
Model Averaging is an ensemble technique that combines predictions from multiple trained models by computing their weighted or unweighted average, producing a consensus prediction…
metrology
Model-Based OCD is the computational engine behind optical scatterometry — using electromagnetic simulation (RCWA, FEM, or FDTD) to compute the expected optical response for…
Model-Based Planning and Learning Introduction & Motivation Model-Based Planning and Learning addresses a central problem in reinforcement policy learning…
reinforcement learning
Model-Based Reinforcement Learning (MBRL) is a reinforcement learning paradigm that explicitly learns a predictive model of environment dynamics and uses it to improve policy…
model based reinforcement learning, model reinforcement learning, model reinforcement, reinforcement learning, cem mbpo np rl, model-based reinforcement
Model-Based Reinforcement Learning Introduction & Motivation Model-based RL: learn environment model for planning. Combines learned dynamics with action optimization. Improves…
Model-Based Reinforcement Learning with World Models Introduction & Motivation Model-Based Reinforcement Learning with World Models addresses a central problem in sequential…
Model-Based Reinforcement Learning with World Models (Extended Study) Introduction & Motivation Model-Based Reinforcement Learning with World Models (Extended Study) addresses…
Model-Based Reinforcement Learning with World Models (Extended Study) Introduction & Motivation Model-Based Reinforcement Learning with World Models (Extended Study) addresses…
Model Behavior Pattern Explanation Introduction & Motivation Model Behavior Pattern Explanation addresses a central problem in explainability interpretation and model…
model caching strategy, model caching, caching strategy
Model Caching Strategy Introduction & Motivation Model Caching Strategy addresses a central problem in ml-inference process control and cache-hit-rate-percentage prediction: how…
model calibration confidence reliability, model calibration, calibration confidence, bs cifar ece ood, model calibration confidence, calibration confidence reliability, confidence reliability
Model Calibration and Confidence Reliability Introduction & Motivation Neural networks often provide overconfident predictions, requiring post-hoc calibration. Critical…
model calibration, confidence uncertainty estimation, cifar ece mc mce passed, model calibration confidence & uncertainty estimation, model calibration confidence, calibration confidence
Model Calibration: Confidence & Uncertainty Estimation Introduction & Motivation Model calibration: align predicted confidence with accuracy. Well-calibrated: P(correct…
model calibration for uncertainty, model calibration uncertainty, model calibration, calibration uncertainty
Model Calibration for Uncertainty Introduction & Motivation Model Calibration for Uncertainty addresses a central problem in ml-training process control…
model calibration, probability estimation confidence, ece passed svc svm, model calibration probability estimation & confidence adjustment, model calibration probability
Model Calibration: Probability Estimation & Confidence Adjustment Introduction & Motivation Calibration ensures predicted probabilities match true frequency. Uncalibrated models…
model calibration probability, model calibration, calibration probability
Model Calibration Probability Introduction & Motivation Model Calibration Probability addresses a central problem in systems process control…