3,135 articles
Cosine annealing
Cosine annealing is a learning rate schedule for training neural networks that decays the rate along half a cosine curve, introduced by Loshchilov and Hutter in 2016.
Cosmos DB
Cosmos DB, formally Azure Cosmos DB, is Microsoft's fully managed, globally distributed NoSQL and vector database service, offering document, key-value, graph, and table data models with single-digit-millisecond latency.
Cost-sensitive learning
Cost-sensitive learning is a machine learning approach that incorporates unequal misclassification costs into model training or prediction, using weighting, resampling, or threshold moving to minimize expected cost.
CosyPose
CosyPose is a computer vision method introduced at ECCV 2020 that estimates the 6D pose of multiple known objects from RGB images taken from unknown camera viewpoints.
Couchbase Inc.
Couchbase Inc. is an American database software company in Santa Clara, California. Its distributed NoSQL database stores data as JSON documents, serving them from memory and syncing to mobile devices.
Counterexample-guided abstraction refinement
Counterexample-guided abstraction refinement (CEGAR) is a model checking technique that verifies large systems by checking a coarse abstract model and refining it with spurious counterexamples.
Counterfactual explanation
A counterfactual explanation is a machine learning explanation showing the smallest input changes that would have changed a model's prediction, such as what a rejected loan applicant needed.
Counterfactual simulation
Counterfactual simulation is a computational modeling approach that estimates outcomes under interventions that did not occur, built on causal models and the potential outcomes framework.
Counting sort
Counting sort is a non-comparison sorting algorithm that orders items with integer keys by counting how often each key occurs, running in Θ(n + k) time.
Covariance intersection
Covariance intersection is a data fusion algorithm that combines estimates whose error correlations are unknown into a single consistent estimate, applied in object tracking and SLAM.
Covariance matrix adaptation evolution strategy (CMA-ES)
Covariance matrix adaptation evolution strategy (CMA-ES) is a stochastic evolutionary algorithm for black-box minimization of continuous, non-convex functions, introduced by Nikolaus Hansen and Andreas Ostermeier in 2001.
Crayfish optimization algorithm
The crayfish optimization algorithm (COA) is a swarm-based metaheuristic that models crayfish sheltering, competition, and foraging behaviors, introduced by Heming Jia and colleagues in 2023.
Create, read, update and delete
Create, read, update and delete (CRUD) is the set of four basic operations on persistent data, named by James Martin in 1983 and standard across databases and APIs.
Credit scoring model
A credit scoring model is a statistical or machine learning method that estimates a borrower's probability of default, producing scores like the FICO score used in lending.
Criminal record
A criminal record, also called a rap sheet or criminal history, is an official compilation of a person's arrests, detentions, charges, and their outcomes, including acquittal or sentencing.
Cross-attention network
A cross-attention network is a neural architecture that fuses two sequences with attention, queries from one and keys and values from the other, unlike self-attention.
Cross-correlation
Cross-correlation, also called the cross-correlation function, is a signal-processing operation measuring the similarity of two signals at each lag; its peak marks the shift where they align best.
Cross-domain few-shot learning
Cross-domain few-shot learning (CD-FSL) is a machine learning setting where a model trained on one domain recognizes new classes in another from few labeled examples.
Cross-encoder
A cross-encoder is a neural network that jointly processes a query and a candidate document through one transformer encoder to output a relevance score, unlike bi-encoders.
Cross-entropy loss
Cross-entropy loss is the standard loss function for training classifiers in deep learning, typically with a softmax output, and is equivalent to maximum likelihood estimation.
Cross-entropy method
The cross-entropy method is a Monte Carlo technique, introduced by Reuven Rubinstein in 1997, for estimating rare-event probabilities and solving combinatorial and continuous optimization problems.
Cross-industry standard process for data mining
The cross-industry standard process for data mining, known as CRISP-DM, is a six-phase process model for data mining projects, developed with European Union funding and published in 2000.
Cross-lingual retrieval
Cross-lingual retrieval is an information retrieval method that ranks documents in one language against a query in another, serving cross-language search, question answering, bitext mining, and multilingual RAG.
Cross-lingual transfer
Cross-lingual transfer is a natural language processing method that applies labeled data, trained models, or representations from high-resource languages to lower-resource target languages, often without parallel data.
Cross-modal contrastive learning
Cross-modal contrastive learning trains paired encoders, such as image and text, to place matched pairs close in a shared embedding space, enabling retrieval and zero-shot classification.
Cross-modal hashing
Cross-modal hashing is a machine learning technique that encodes data from different modalities, such as images and text, into compact binary codes for fast retrieval.
Cross-modal knowledge distillation
Cross-modal knowledge distillation, also called cross-modal distillation, is a machine learning technique where a teacher model trained on one modality, such as images, trains a student model on another, such as audio or depth.
Crossover (genetic algorithm)
Crossover, also called recombination, is the genetic algorithm operator that exchanges genetic material between two or more parent solutions to produce offspring for the next generation.
Crow search algorithm
The crow search algorithm (CSA) is a population-based metaheuristic introduced by Alireza Askarzadeh in 2016 that imitates how crows hide and retrieve food to optimize engineering design problems.
Crowd counting
Crowd counting is a computer vision task that estimates the number of people in an image or video frame, often producing a density map showing how the crowd is distributed.