Showing 121-180 of 810 articles
Contrastive Learning
See also: self-supervised learning, representation learning, metric learning, transfer learning, deep learning Contrastive learning is a family of machine...
Deep Learning
Contrastive decoding
Contrastive decoding (CD) is a decoding strategy for text generation from a large language model that selects tokens by contrasting two models of different...
AI Infrastructure
Convenience Sampling
Convenience sampling (also called grab sampling, accidental sampling, or opportunity sampling) is a non-probability sampling method in which data points or...
Data & DatasetsStatistics
Convergence
Convergence in machine learning is the point at which an iterative optimization algorithm reaches a stable solution, meaning the loss function stops decreasing...
MathematicsTraining & Optimization
Convex Function
A convex function is a real-valued function whose graph curves upward into a bowl or cup shape, so that the line segment (chord) connecting any two points on...
MathematicsTraining & Optimization
Convex Optimization
Convex optimization is the branch of mathematical optimization that minimizes a convex function over a convex set, a problem class with one defining advantage:...
MathematicsTraining & Optimization
Convex Set
A convex set is a set of points in which the line segment connecting any two points of the set lies entirely within the set [1][3]. Formally, a set in a real...
MathematicsTraining & Optimization
Convolution
See also: Machine learning terms, Convolutional layer, Convolutional filter Convolution is a mathematical operation that combines two functions to produce a...
Deep LearningMathematics
Convolutional Filter
A convolutional filter (also called a kernel or feature detector) is a small matrix of learnable weights that slides across an input and computes a dot product...
Computer VisionDeep Learning
Convolutional Layer
See also: Machine learning terms A convolutional layer is the core building block of a convolutional neural network (CNN): it slides a small set of learnable...
Computer VisionDeep Learning
Convolutional Neural Network
A convolutional neural network (CNN or ConvNet) is a type of neural network that processes grid-like data such as images by sliding small learnable filters...
Computer VisionDeep Learning
Convolutional Operation
The convolutional operation is a mathematical procedure that combines two functions to produce a third function expressing how the shape of one is modified by...
Computer VisionNeural Networks
Corrective RAG (CRAG)
Corrective Retrieval Augmented Generation (CRAG) is a method for improving the robustness of retrieval-augmented generation (RAG) when the underlying retrieval...
AI Agents
Cosine similarity
Cosine similarity is a measure of similarity between two non-zero vectors that calculates the cosine of the angle between them, defined as the dot product of...
Natural Language Processing
Cost-sensitive learning
Cost-sensitive learning is a family of machine learning methods that minimise the expected misclassification cost rather than the misclassification rate, by...
Counterfactual Fairness
Counterfactual fairness is a formal definition of algorithmic fairness rooted in causal inference: a prediction is counterfactually fair toward an individual...
AI EthicsStatistics
Coverage Bias
Coverage bias is a type of selection bias that occurs when the method used to collect data systematically excludes part of the target population, so the sample...
AI EthicsData & Datasets
Crash Blossom
A crash blossom is a newspaper headline that is unintentionally ambiguous because its compressed wording allows more than one valid parse, producing an...
Natural Language Processing
Critic
A critic in reinforcement learning (RL) is the component of an actor-critic system that estimates a value function, scoring how good the actor's chosen actions...
Deep LearningReinforcement Learning
Cross-Entropy
See also: Machine learning terms, Loss function, Entropy Cross-entropy is a measure from information theory of how many bits (or nats) are needed to encode...
Deep LearningMathematics
Cross-Entropy Loss
Cross-entropy loss is the standard loss function for classification and language modeling, defined as the negative log-probability a model assigns to the...
Deep Learning
Cross-Validation
Cross-validation is a statistical resampling technique used in machine learning to estimate how accurately a predictive model will generalize to data it was...
Model Evaluation
Curriculum learning
Curriculum learning is a training strategy for machine learning models in which training examples are presented in a meaningful, easy-to-hard order rather than...
Deep LearningTraining & Optimization
Curse of Dimensionality
See also: Machine learning, Feature engineering, Dimensionality reduction The curse of dimensionality is the set of problems that arise when data has a large...
MathematicsStatistics
DAPO (Decoupled Clip and Dynamic Sampling Policy Optimization)
DAPO, short for Decoupled Clip and Dynamic sAmpling Policy Optimization, is an open-source reinforcement learning algorithm and training system for large...
Reinforcement Learning
DARE (Drop And REscale)
DARE (Drop And REscale) is a training-free preprocessing technique for model merging that sparsifies the parameter changes introduced by fine-tuning before...
Reinforcement Learning
DBSCAN
DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a density-based clustering algorithm that groups together points packed closely in...
Artificial IntelligenceData Science
DDPM
Denoising Diffusion Probabilistic Models (DDPM) are a class of generative model introduced by Jonathan Ho, Ajay Jain, and Pieter Abbeel of UC Berkeley in their...
Deep LearningGenerative AI
DINO (computer vision)
DINO (self-DIstillation with NO labels) is a family of self-supervised learning methods for computer vision from Meta AI that trains Vision Transformers (ViTs)...
Computer VisionDeep Learning
DROP (Discrete Reasoning Over Paragraphs)
Discrete Reasoning Over Paragraphs Abbreviation A reading comprehension benchmark requiring discrete reasoning and mathematical operations over paragraphs ...
AI BenchmarksNatural Language Processing
DSPy
DSPy (short for Declarative Self-improving Python) is an open-source framework, developed at Stanford NLP, for programming rather than prompting large language...
Developer ToolsLarge Language Models
Dask
Dask is an open-source Python library for parallel and distributed computing that scales the familiar APIs of libraries such as NumPy, pandas, and scikit-learn...
AI InfrastructureData Science
Data Analysis
Data analysis is the process of inspecting, cleaning, transforming, and modeling data to discover useful information, draw conclusions, and support...
Data ScienceStatistics
Data Augmentation
Data augmentation is a set of techniques that artificially expand the size and diversity of a training dataset by applying label-preserving transformations to...
Data & DatasetsDeep Learning
Data Parallelism
Data parallelism is a distributed training technique in which the same neural network model is replicated across multiple processing units (typically GPUs),...
AI InfrastructureDeep Learning
Data Provenance Initiative
The Data Provenance Initiative (DPI) is a volunteer-led, multi-institution research collective that audits and documents the licenses, sources, creators, and...
Data & Datasets
Data Science
Data science is an interdisciplinary field that uses statistics, programming, and domain expertise to extract knowledge and insights from structured and...
Computer ScienceEducation AI
Data Set or Dataset
A dataset (also written as "data set") is a structured collection of data points used to train, validate, and evaluate machine learning models. In artificial...
Data & Datasets
Data labeling
Data labeling (also called data annotation) is the process of attaching meaningful tags, labels, or metadata to raw data so that machine learning algorithms...
Artificial IntelligenceData Science
Data poisoning
Data poisoning is a class of adversarial attack in which a malicious actor deliberately corrupts the training data used to build machine learning models, with...
AI Safety
Data preprocessing
Data preprocessing is the set of operations applied to raw data to clean and transform it into a form a machine learning model can use, covering deduplication,...
Data & Datasets
DataFrame
A DataFrame is a two-dimensional, size-mutable, potentially heterogeneous tabular data structure with labeled axes (rows and columns), in which each column can...
AI Tools & ProductsData Science
Dataset API (tf.data)
The Dataset API (tf.data) is the high-performance input pipeline framework within TensorFlow for loading, transforming, and delivering data to machine learning...
Deep LearningDeveloper Tools
Datasets
In machine learning, a dataset is a structured collection of examples used to fit, tune, and evaluate models, where each example pairs input data (features)...
Decision Boundary
A decision boundary (also called a decision surface) is the hypersurface in feature space that separates the regions a classifier assigns to different classes....
Decision Forest
See also: Random Forest, Decision Tree, Ensemble Learning A decision forest is a family of ensemble learning methods in machine learning that combine many...
Decision Threshold
A decision threshold (also called a classification threshold or cutoff point) is a value used to convert the continuous probability output of a machine...
Model Evaluation
Decision Tree
A decision tree is a tree-structured predictive model in machine learning that makes a prediction by asking a sequence of yes-or-no questions about an input's...
Decoder
See also: Encoder, Transformer, Machine learning terms A decoder is the component of a neural network that turns an internal, compressed, or abstract...
Deep LearningNeural Networks
Decoding strategies
Decoding strategies are the algorithms that select output tokens from a language model's next-token probability distribution during text generation. At each...
Large Language ModelsNatural Language Processing
Deep Learning
Deep learning is a subset of machine learning that uses artificial neural networks with multiple layers to automatically learn representations of data at...
Artificial IntelligenceDeep Learning
Deep Model
A deep model, also called a deep learning model or deep neural network, is an artificial neural network built from many stacked layers of processing units that...
Deep Learning
Deep Neural Network
A deep neural network (DNN) is an artificial neural network with multiple hidden layers of artificial neurons stacked between its input and output layers,...
Deep LearningNeural Networks
Deep Q-Network (DQN)
Deep Q-Network (DQN) is a reinforcement learning algorithm that uses a deep neural network to approximate the optimal action-value function (Q-function),...
Deep LearningReinforcement Learning
DeepLIFT
DeepLIFT (Deep Learning Important FeaTures) is a feature attribution method for deep neural networks introduced by Avanti Shrikumar, Peyton Greenside, and...
Deep LearningInterpretability
DeepSpeed
DeepSpeed is an open-source deep learning optimization library developed by Microsoft that makes distributed training and inference of large models efficient,...
AI InfrastructureDeep Learning
Deepak Pathak
Deepak Pathak is an Indian American roboticist and machine learning researcher who is the co-founder and chief executive officer of Skild AI, a startup...
PeopleRobotics
Demographic Parity
Demographic parity, also called statistical parity or acceptance rate parity, is a fairness criterion in machine learning that requires a model's predictions...
AI Ethics
Denoising
Denoising is the process of removing unwanted noise from data to recover a cleaner underlying signal, and in modern AI it doubles as a training principle: a...
Deep Learning
Dense Feature
A dense feature is a feature in machine learning whose vector representation consists mostly or entirely of non-zero values, typically stored as a dense...
Data & Datasets