feature-engineering-ts machine learning
Feature Engineering for Time Series Introduction & Motivation Feature Engineering for Time Series addresses a central problem in timeseries forecasting…
1,257 technical terms and definitions
Feature Engineering for Time Series Introduction & Motivation Feature Engineering for Time Series addresses a central problem in timeseries forecasting…
code ai
Feature Envy is a code smell where a method in Class A is more interested in the data and capabilities of Class B than in its own class — repeatedly accessing fields, getters…
transfer learning
Feature Extraction is the process of using a pre-trained neural network as a fixed feature extractor — passing input data through the frozen network to obtain learned…
feature extraction time series, feature extraction time, extraction time series, feature extraction, extraction time, time series
Feature Extraction Time Series Introduction & Motivation Feature Extraction Time Series addresses a central problem in timeseries process control…
Feature Extraction via Transfer Learning Introduction & Motivation Feature Extraction via Transfer Learning addresses a central problem in transfer learning and {target}…
toggle, experiment
Feature Flags for ML Systems What are Feature Flags? Toggles that enable/disable features at runtime without deploying new code, essential for ML experimentation and gradual…
software engineering
Feature flags (also called feature toggles) are a software engineering technique that allows you to enable or disable functionality at runtime without deploying new code. In AI…
feature flag management, feature flag, flag management
Feature Flag Management Introduction & Motivation Feature Flag Management addresses a central problem in verification process control and flag-evaluation-latency-microseconds…
feature flag progressive delivery, feature flag progressive, flag progressive delivery, feature flag, flag progressive, progressive delivery
Feature Flag Progressive Delivery Introduction & Motivation Feature Flag Progressive Delivery addresses a central problem in cloud process control…
feature flag toggling, feature flag, flag toggling
Feature Flag Toggling Introduction & Motivation Feature Flag Toggling addresses a central problem in programming process control and flag-state-management-evaluation prediction…
Permutation Feature Importance Methods Introduction & Motivation Permutation Feature Importance Methods addresses a central problem in explainability interpretation and model…
feature importance, permutation shap lime, lime passed shap, feature importance permutation shap & lime, feature importance permutation, importance permutation shap, importance permutation
Feature Importance: Permutation, SHAP & LIME Introduction & Motivation Feature importance: understand model decisions. Permutation importance: shuffle features; measure…
feature importance ranking, feature importance, importance ranking
Feature Importance Ranking Introduction & Motivation Feature Importance Ranking addresses a central problem in ml-analysis process control and importance-estimation-accuracy…
Feature Importance via Permutation Introduction & Motivation Feature Importance via Permutation addresses a central problem in interpretability and explanation of xai predictions…
Feature Importance via Permutation (Extended Study) Introduction & Motivation Feature Importance via Permutation (Extended Study) addresses a central problem in interpretability…
Feature Importance via Permutation (Extended Study) Introduction & Motivation Feature Importance via Permutation (Extended Study) addresses a central problem in interpretability…
Feature Interaction Explanation Introduction & Motivation Feature Interaction Explanation addresses a central problem in explainability interpretation and model understanding: how…
theory
Feature Learning Regime is the operating mode where neural networks actively learn useful internal representations during training — as opposed to the lazy regime where features…
activation map, convolutional feature map, channels, filters, receptive field, Grad-CAM, network dissection
A feature map is the two-dimensional grid of values produced when one filter of a convolutional layer is slid across its input, recording at each position how strongly the pattern…
model compression
Feature Matching Distillation (FitNets) is a knowledge distillation approach where the student is trained to match the teacher's intermediate feature representations — not just…
Feature Matching in GANs Introduction & Motivation Feature Matching in GANs addresses a central problem in generative generation and generator-gradient-improvement synthesis: how…
computer vision
Feature Pyramid extraction from Vision Transformers addresses the fundamental architectural mismatch between the single-scale, columnar output of a standard ViT (which maintains…
fpn, multi scale feature, fpn detection, feature pyramid
Feature Pyramid Network (FPN) is the multi-scale feature extraction architecture that builds a top-down pathway with lateral connections to create feature maps at multiple…
Feature Pyramid Network Design Introduction & Motivation Feature Pyramid Network Design addresses a central problem in vision processing and multi-scale-feature-quality…
simulation
Feature-scale simulation models the evolution of individual device features (trenches, vias, lines, contact holes) during fabrication processes — capturing the detailed geometry…
feature normalization, standardization, min-max scaling, z-score scaling, robust scaler, StandardScaler, data leakage in preprocessing
Feature scaling is the preprocessing step of rewriting numeric input features so that they live on comparable numeric ranges, typically by shifting and rescaling each column…
Feature Scaling Method Selection Introduction & Motivation Feature Scaling Method Selection addresses a central problem in {subject} assurance and {target} management: how…
importance, reduce
Feature Selection is the process of identifying and keeping only the most informative variables for a machine learning model while discarding noisy, redundant, or irrelevant…
feature selection, dimensionality reduction filtering, l1 mi passed pca rfe, feature selection & dimensionality reduction filtering & wrapper methods, reduction filtering
Feature Selection & Dimensionality Reduction: Filtering & Wrapper Methods Introduction & Motivation Feature selection removes irrelevant features, improving interpretability…
feature selection, filter wrapper embedded, l1 passed rfe, feature selection filter wrapper & embedded methods, feature selection filter, selection filter wrapper, wrapper embedded methods
Feature Selection: Filter, Wrapper & Embedded Methods Introduction & Motivation Feature Selection: select relevant features; reduce dimensions. Filter, wrapper, embedded methods.…
Feature Squeezing Defense Introduction & Motivation Feature Squeezing Defense addresses a central problem in robustness of advrobust models under adversarial conditions: how…
Feature Squeezing Defense (Extended Study) Introduction & Motivation Feature Squeezing Defense (Extended Study) addresses a central problem in robustness of advrobust models under…
Feature Squeezing Defense (Extended Study) Introduction & Motivation Feature Squeezing Defense (Extended Study) addresses a central problem in robustness of advrobust models under…
feast, ml features, training serving skew, feature engineering, offline online
Feature stores provide centralized infrastructure for managing ML features — storing, versioning, and serving feature data consistently between training and inference, solving…
mlops
Feature stores centralize the storage, management, and serving of ML features for training and inference consistency. Core problem: Features computed differently in training vs…
feature store management, feature store, store management
Feature Store Management Introduction & Motivation Feature Store Management addresses a central problem in ml-ops process control and feature-retrieval-latency-milliseconds…
feature store management, feature store, store management
Feature Store Management Introduction & Motivation Feature Store Management addresses a central problem in systems process control and feature-latency-online-retrieval prediction…
explainable ai
Feature Visualization is a technique that generates synthetic input images that maximally activate specific neurons, channels, or layers in a neural network — revealing what…
interpretability
Feature Visualization is techniques that generate or select inputs to reveal patterns learned by internal model units - It helps interpret what neurons or channels respond…
explainable ai
Feature visualization in language models is the interpretability method that constructs inputs or activations to reveal what internal model features respond to - it helps…
Feature Visualization via Activation Maximization Introduction & Motivation Feature Visualization via Activation Maximization addresses a central problem in interpretability…
Feature Visualization via Activation Maximization (Extended Study) Introduction & Motivation Feature Visualization via Activation Maximization (Extended Study) addresses a central…
Feature Visualization via Activation Maximization (Extended Study) Introduction & Motivation Feature Visualization via Activation Maximization (Extended Study) addresses a central…
what is a feature machine learning, feature vector
Features are the individual measurable input variables a model actually sees — a house-price model's features might be square footage, bedroom count, and zip code; an image…
FedBN Federated Learning with Local Batch Normalization Introduction & Motivation FedBN Federated Learning with Local Batch Normalization addresses a central problem in federated…
learning, privacy, preserving, distributed
Federated Learning and Privacy-Preserving ML is a distributed machine learning paradigm where model training occurs across decentralized data sources without centralizing raw data…
Federated Active Learning with Budget-Constrained Queries Introduction & Motivation Federated Active Learning with Budget-Constrained Queries addresses a central problem…
Federated Active Learning Introduction & Motivation Federated Active Learning addresses a central problem in {subject} learning and efficient {target} annotation: how to Achieve…
Federated BALD Active Learning with Disagreement Gating Introduction & Motivation Federated BALD Active Learning with Disagreement Gating addresses a central problem in federated…
FedAdversarial Robustness via Distributed PGD Attacks Introduction & Motivation FedAdversarial Robustness via Distributed PGD Attacks addresses a central problem in federated…