Wednesday, March 18, 2026
- Dense Layerv9A dense layer, also called a fully connected (FC) layer, linear layer, or affine layer, is a layer in an artificial neural network where every input neuron is connected to every output neuron.
- Dense Featurev8A dense feature is a feature in machine learning whose vector representation consists mostly or entirely of non-zero values, typically stored as a dense numeric array (a vector or tensor) of floating-point…
- Denoisingv6Denoising is the process of removing unwanted noise from data to recover a cleaner underlying signal
- Demographic Parityv9Demographic parity, also called statistical parity or acceptance rate parity, is a fairness criterion in machine learning that requires a model's predictions to be statistically independent of a protected…
- Deep Neural Networkv11A deep neural network (DNN) is an artificial neural network with multiple hidden layers of artificial neurons stacked between its input and output layers
- Deep Modelv8A 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 automatically learns hierarchical representations…
- Deep Research Benchv7Deep Research Bench (DRB) is a benchmark introduced by FutureSearch in May 2025 to evaluate how well large language model agents complete complex research tasks on the open web.
- Deep Q-Network (DQN)v7Deep Q-Network (DQN) is a reinforcement learning algorithm that uses a deep neural network to approximate the optimal action-value function (Q-function)
- DeepSeek-OCRv6DeepSeek-OCR is an open-source optical character recognition (OCR) and document-understanding system released by DeepSeek on 20 October 2025 that pioneers a contexts optical compression paradigm: it encodes…
- DeepSeekv15DeepSeek is a Chinese artificial intelligence company based in Hangzhou. It was founded in 2023 by Liang Wenfeng, who had previously co-founded the quantitative investment firm High-Flyer.
- DeepResearch Benchv6DeepResearch Bench is a benchmark for evaluating long-form reports produced by web research agents.
- Decoderv8A decoder is the component of a neural network that turns an internal, compressed, or abstract representation into a desired output, such as a translated sentence, a generated image, a reconstructed input, or…
- Decision Treev12A decision tree is a tree-structured model used in supervised learning. It predicts an outcome by routing an input from a root node through a sequence of tests to a terminal leaf.
- Decision Thresholdv8A decision threshold (also called a classification threshold or cutoff point) is a value used to convert the continuous probability output of a machine learning classifier into a discrete class label.
- Decision Forestv7A decision forest is a family of ensemble learning methods in machine learning that combine many decision trees to produce more accurate and stable predictions than any single tree.
- Decision Boundaryv9A decision boundary (also called a decision surface) is the hypersurface in feature space that separates the regions a classifier assigns to different classes.
- Datasetsv7In machine learning, a dataset is a structured collection of examples used to fit, tune, and evaluate models, where each example pairs input data (features) with an optional target (label or response).
- Dataset API (tf.data)v5The Dataset API (tf.data) is the high-performance input pipeline framework within TensorFlow for loading, transforming, and delivering data to machine learning models during training and evaluation.
- Data Set or Datasetv9A dataset (also written as "data set") is a structured collection of data points used to train, validate, and evaluate machine learning models.
- Data Parallelismv11Data parallelism is a distributed training technique in which the same neural network model is replicated across multiple processing units (typically GPUs), each device trains on a different shard of the input…
- Data Augmentationv11Data augmentation is a set of techniques that artificially expand the size and diversity of a training dataset by applying label-preserving transformations to existing examples, rather than collecting new…
- Data Visualization ChatGPT Pluginsv5Data visualization ChatGPT plugins were a category of third party tools, active from 2023 to 2024, that let ChatGPT draw charts, plot graphs, render flowcharts, and build other visual representations of data…
- Data Visualizationv6Data visualization is the graphical representation of information and data through charts, plots, maps, and dashboards.
- Data Analysis ChatGPT Pluginsv5Data analysis ChatGPT plugins were a category of third-party tools that extended ChatGPT with capabilities for analysts, data scientists, and finance professionals working with structured data in a chat…
- Data Analysisv6Data analysis is the process of inspecting, cleaning, transforming, and modeling data to discover useful information, draw conclusions, and support decision-making.
- DataFramev7A DataFrame is a two-dimensional, size-mutable, potentially heterogeneous tabular data structure with labeled axes (rows and columns), in which each column can hold a different data type and arithmetic…
- Data-centric AI (DCAI)v5Data-centric AI (DCAI) is the discipline of systematically engineering and improving the data used to train a machine learning model, rather than holding the data fixed and iterating mainly on model…
- Dark Factoryv6A dark factory, also called a lights-out factory, is a manufacturing or logistics facility that runs production with little or no human presence on the floor.
- DROP (Discrete Reasoning Over Paragraphs)v5DROP** (Discrete Reasoning Over Paragraphs) is a reading comprehension benchmark that requires artificial intelligence systems to perform discrete reasoning operations over textual content.
- DQNv8The Deep Q-Network (DQN) is a model-free, off-policy reinforcement learning algorithm that combines Q-learning with a deep neural network function approximator, learning to act directly from raw pixels.
- DALL·E Custom GPTsv5DALL·E Custom GPTs are Custom GPTs in the DALL·E category of the OpenAI GPT Store, the browse category the store launched with on January 10, 2024 for GPTs that exist primarily to generate or edit images.
- DALL-E (Agent)v6DALL-E (Agent) refers to the official DALL·E GPT published by OpenAI inside ChatGPT, a first-party agent variant of ChatGPT that exposes DALL·E 3 image generation through a dedicated conversational interface.
- DALL-Ev10DALL-E is a family of text-to-image systems developed by OpenAI that generates images from natural-language descriptions.
- Cybersecurity ChatGPT Pluginsv4Cybersecurity ChatGPT Plugins were a small, informal grouping of third-party extensions for ChatGPT that focused on security related tasks during the brief life of the ChatGPT plugins beta.
- Custom GPTs By ChatGPTv6Custom GPTs by ChatGPT are the small set of Custom GPTs that OpenAI itself publishes under the verified @ChatGPT builder profile inside the GPT Store.
- Custom GPTv9A custom GPT, branded by OpenAI as a "GPT", is a version of ChatGPT configured for a particular purpose.
- CustomGPT Instructions for Knowledge (Uploaded Files)v5"CustomGPT Instructions for Knowledge (Uploaded Files)" is the informal name for a short block of default instructions that OpenAI prepends to a Custom GPT's system prompt whenever the builder attaches files…
- Cursor Rulesv6Cursor Rules are persistent natural-language instructions that steer the AI agent inside Cursor, the AI-powered code editor built by Anysphere.
- CuDNNv9NVIDIA cuDNN (CUDA Deep Neural Network library) is a proprietary GPU-accelerated library of primitives for deep learning, first released by NVIDIA on September 7, 2014, that provides highly tuned…
- Cryptocurrency ChatGPT Pluginsv6Cryptocurrency ChatGPT Plugins were a category of third-party extensions for ChatGPT that connected the assistant to live crypto market data, on-chain blockchain data, decentralized finance (DeFi) analytics…
- AI in cryptocurrencyv5AI in cryptocurrency refers to the use of artificial intelligence techniques, including machine learning, large language models, and AI agents, within cryptocurrency and blockchain systems.
- Cross-Validationv6Cross-validation is a statistical resampling technique used in machine learning to estimate how accurately a predictive model will generalize to data it was not trained on.
- Cross-Entropyv8Cross-entropy is a measure from information theory of how many bits (or nats) are needed to encode data drawn from a true probability distribution P when using a code optimized for a different
- Criticv9A 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 are and converting that judgment into a…
- Creative Writing v3v4Creative Writing v3 is an artificial intelligence benchmark that evaluates creative writing in large language models (LLMs) using a hybrid framework combining isolated rubric scoring with pairwise Elo…
- Crash Blossomv9A crash blossom is a newspaper headline that is unintentionally ambiguous because its compressed wording allows more than one valid parse, producing an unintended (and often comical) alternative reading.
- Coverage Biasv6Coverage bias is a type of selection bias that occurs when the method used to collect data systematically excludes part of the target population
- Counterfactual Fairnessv9Counterfactual fairness is a formal definition of algorithmic fairness rooted in causal inference: a prediction is counterfactually fair toward an individual if it would remain unchanged in a counterfactual…
- Costv7In machine learning, cost is the scalar number that summarizes how badly a model is performing on a chunk of data.
- Convolutional Operationv5The convolutional operation is a mathematical procedure that combines two functions to produce a third function expressing how the shape of one is modified by the other.
- Convolutional Neural Networkv10A convolutional neural network (CNN, or ConvNet) is a neural network that uses convolution-like linear operators in at least some layers.
- Convolutional Layerv7A convolutional layer is the core building block of a convolutional neural network (CNN): it slides a small set of learnable filters (also called kernels) across the input, computing a convolution (technically…
- Convolutional Filterv7A 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 at each position to produce a feature map.
- Convolutionv10Convolution is a mathematical operation that combines two functions to produce a third function, expressing how the shape of one is modified by the other.
- Convex Setv8A convex set is a set of points in which the line segment connecting any two points of the set lies entirely within the set.
- Convex Optimizationv8Convex optimization is the branch of mathematical optimization that minimizes a convex function over a convex set, a problem class with one defining advantage: every local minimum is also a global minimum.
- Convex Functionv10A 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 the graph lies on or above the graph itself.
- Conversational Modelsv7Conversational models are computational systems designed to carry on a dialogue with human users in natural language
- Convergencev7Convergence in machine learning is the point at which an iterative optimization algorithm reaches a stable solution, meaning the loss function stops decreasing meaningfully and further parameter updates yield…
- Convenience Samplingv7Convenience sampling (also called grab sampling, accidental sampling, or opportunity sampling) is a non-probability sampling method in which data points or participants are selected because they are easy to…
- Continuous Featurev8A continuous feature is a numeric input variable in machine learning and statistics that can take any value within a range, including decimals and fractions, rather than a fixed set of categories or counts.
- Context windowv10A context window is the finite token sequence that a language model can process for one invocation.
- Confusion Matrixv8A confusion matrix is a table that summarizes the performance of a classification model by tabulating its predicted class labels against the actual class labels, with correct predictions on the diagonal and…
- Confirmation Biasv6Confirmation bias is the tendency to search for, interpret, favor, and recall information in ways that confirm one's preexisting beliefs, and in artificial intelligence it appears in three main forms: human…
- Confident Learning (CL)v7Confident Learning (CL) is a data-centric machine learning framework for characterizing, finding, and learning with label errors in datasets.
- Conditionv5In machine learning, a condition is any node in a decision tree that performs a test on one or more features and routes an example to one of its child nodes based on the result.
- Computer Visionv10Computer vision is the study of computational methods that extract, estimate, or generate useful representations from visual measurements.
- Computer-use agentv8A computer-use agent (CUA) is a category of AI agent in artificial intelligence that performs tasks by directly operating a general-purpose computer's graphical user interface (GUI) the way a human does, by…
- Companiesv6Companies in the field of artificial intelligence span foundation model developers, cloud platforms, semiconductor manufacturers, vector database vendors, developer tooling startups, image and video generation…
- Collectibles ChatGPT Pluginsv5Collectibles ChatGPT Plugins were third party tools published in the ChatGPT plugin store between March 23, 2023 and April 9, 2024 that helped users research, price, and discover collectible items such as…
- AI in collectiblesv4Artificial intelligence in collectibles refers to the use of machine learning and computer vision to grade, authenticate, price, and catalog collectible items such as trading cards, coins, sports memorabilia…
- Collaborative filteringv10Collaborative filtering (CF) is a family of techniques used in recommendation systems that predicts a user's preferences by collecting and analyzing preference signals from many other users.
- Co-Trainingv6Co-training is a semi-supervised learning algorithm that leverages both labeled and unlabeled data by training two classifiers on two distinct "views" of the data, allowing them to teach each other iteratively.
- Co-Adaptationv6Co-adaptation in neural networks refers to a phenomenon in which different hidden units develop highly correlated behavior, becoming excessively dependent on one another rather than learning independent
- Clusteringv8Clustering is an unsupervised learning technique that groups a set of data points into clusters so that points in the same cluster are more similar to each other than to points in other clusters
- Cloud TPUv8Cloud TPU is Google Cloud's offering of Tensor Processing Units (TPUs), the family of custom application-specific integrated circuits (ASICs) that Google builds to accelerate machine learning training and…
- Clippingv7Clipping is a family of techniques in machine learning that constrain numerical values to lie within a specified range or below a specified magnitude.
- Claude Sonnet 4.5v12Claude Sonnet 4.5 is a multimodal large language model (LLM) developed by Anthropic and released on September 29, 2025, which Anthropic described at launch as "the best coding model in the world." It is a…
- Claude Skillsv8Claude Skills (also marketed as Agent Skills) are a feature developed by Anthropic that lets users package repeatable workflows, instructions, reference materials, and optional executable scripts into…
- Claude Code Playwrightv7Claude Code Playwright refers to the practice and integration of using Claude Code, Anthropic's agentic coding tool available in the terminal, IDEs, and via API
- Claude Codev25Claude Code is an agentic software development product made by Anthropic. It uses models from the Claude family to inspect software projects, propose and apply changes, run development tools, and report…
- Claude --dangerously-skip-permissionsv9claude --dangerously-skip-permissions is a command-line flag for Claude Code, Anthropic's terminal-based coding agent.
- Claude (language model)v31Claude is a family of large language models (LLMs) developed by Anthropic, an American artificial intelligence safety and research company.
- Classification Thresholdv8A classification threshold (also called a decision threshold or cut-off point) is a numeric value used to convert the continuous probability output of a classification model into a discrete class label.
- Classification (machine learning)v10Classification is a supervised learning task in which a system uses labeled examples to assign one or more discrete labels to an input.
- Class-Imbalanced Datasetv7A class-imbalanced dataset is a dataset in which the distribution of examples across the target classes is significantly unequal, so that one class (the majority class) contains far more samples than one or…
- Classv5In machine learning, a class is one of the discrete categories that a classification model can assign to an input.
- Checkpointv9In machine learning, a checkpoint is a saved snapshot of a model's state captured at a specific point during the training process, used to resume training, recover from failures, or deploy and fine-tune the…
- Centroid-based clusteringv7Centroid-based clustering is a family of machine learning algorithms that group data by representing each cluster with a single prototype point, called a centroid, and assigning every point to whichever…
- Centroidv7A centroid is the geometric center of a set of points, computed as the arithmetic mean of their coordinates: each component of the centroid is the average of that coordinate across all the points.
- Causal Language Modelv7A causal language model (CLM), also called an autoregressive language model or a decoder-only language model, is a language model that predicts the next token in a sequence using only the tokens that precede…
- Categorical Datav8Categorical data, also called qualitative data, is data whose values are discrete labels or groups (such as colors, country names, or blood types) rather than measurable quantities, so they cannot be…
- Cars ChatGPT Pluginsv5Cars ChatGPT Plugins were a group of third-party ChatGPT plugins, active from May to mid-2023 within the broader plugin beta, that let the chatbot search live vehicle listings, car rentals, electric vehicle…
- Carsv5AI in cars covers the use of machine learning, computer vision, neural networks, and large language models in passenger vehicles, commercial trucks, and the systems that build and insure them.
- CapCut VideoGPTv9CapCut VideoGPT is a Custom GPT for ChatGPT, published in the GPT Store under the developer name capcut.com by the team behind CapCut, the video generation and editing app owned by ByteDance.
- Candidate Samplingv7Candidate sampling is a family of training-time optimization techniques used in machine learning to reduce the computational cost of models that must choose among a very large number of output classes.
- Candidate Generationv8Candidate generation is the first stage in a multi-stage recommendation system or information retrieval pipeline.
- Calibration Layerv8A calibration layer is a post-prediction adjustment appended to a trained machine learning model that rescales its raw output scores or predicted probabilities so they better reflect the true likelihood of…
- CUDAv14CUDA (Compute Unified Device Architecture) is NVIDIA's platform and programming model for general-purpose computation on its graphics processing units.
- COLLIEv4COLLIE (Systematic Construction of Constrained Text Generation Tasks) is a grammar-based benchmark framework for evaluating how well large language models can produce text that satisfies rich
