Thursday, July 23, 2026
- Document Question Answering Modelsv5Document question answering models (DocQA, sometimes called DocVQA for document visual question answering) are machine learning systems that take a document image or PDF together with a natural language…
- Dynamic modelv7A dynamic model in machine learning is a model that is retrained frequently or continuously as new data arrives, so that its parameters track changes in the underlying data distribution over time.
- Derived labelv4A derived label is a label that has been generated programmatically or inferred from other observable signals, rather than collected from direct human annotation of the variable a model is trying to predict.
- Dropout Regularizationv6Dropout regularization is a regularization technique for neural networks that prevents overfitting by randomly setting a fraction of neuron activations to zero on each training step, forcing the network to…
- Divisive Clusteringv4Divisive clustering, also called top-down clustering, is a hierarchical clustering method that begins with all data points in a single cluster and recursively splits that cluster into smaller subclusters.
- ERQAv3ERQA (Embodied Reasoning Question Answering) is a multimodal benchmark released by Google DeepMind in March 2025 to evaluate the embodied reasoning capabilities of vision-language models (VLMs) on robotics…
- Eager Executionv5Eager execution is an imperative, define-by-run mode of running machine learning framework operations in which each operation is evaluated immediately as it is called and returns a concrete value
- Devicev4In machine learning, a device is the hardware target on which tensor operations are executed: a CPU, an NVIDIA GPU through CUDA, an Apple GPU through Metal Performance Shaders, a Google TPU through XLA, or an…
- Downsamplingv4Downsampling is the process of reducing the number of samples, the spatial resolution, or the number of data instances in a signal, image, or dataset in order to lower computational cost and memory use while…
- EQ-Bench 3v3EQ-Bench 3 is an artificial intelligence benchmark that measures the emotional intelligence of large language models through challenging multi-turn role-plays and transcript-analysis tasks
- Dynabenchv3Dynabench is an open-source artificial intelligence benchmarking platform that runs in a web browser and supports human-and-model-in-the-loop dataset creation
- DeepSeek-OCRv5DeepSeek-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…
- Decision Forestv6A 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 Boundaryv8A decision boundary (also called a decision surface) is the hypersurface in feature space that separates the regions a classifier assigns to different classes.
- Deep Q-Network (DQN)v6Deep Q-Network (DQN) is a reinforcement learning algorithm that uses a deep neural network to approximate the optimal action-value function (Q-function)
- Dense Layerv8A 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.
- Demographic Parityv8Demographic 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…
- Decoderv7A 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…
- Dataset API (tf.data)v4The 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.
- Deep Neural Networkv10A deep neural network (DNN) is an artificial neural network with multiple hidden layers of artificial neurons stacked between its input and output layers
- Dense Featurev7A 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…
- Deep Modelv7A 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…
- Decision Thresholdv7A 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.
- Denoisingv5Denoising is the process of removing unwanted noise from data to recover a cleaner underlying signal
- Depthv4In machine learning, depth is the number of sequential processing stages a model applies between its input and its output.
- Data Visualizationv5Data visualization is the graphical representation of information and data through charts, plots, maps, and dashboards.
- 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.
- Cursor Rulesv5Cursor Rules are persistent natural-language instructions that steer the AI agent inside Cursor, the AI-powered code editor built by Anysphere.
- Data Augmentationv10Data 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 Parallelismv10Data 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…
- CuDNNv8NVIDIA 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…
- Cybersecurity ChatGPT Pluginsv3Cybersecurity 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.
- DataFramev6A 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)v4Data-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…
- DQNv7The 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 (Agent)v5DALL-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.
- Data Analysisv5Data analysis is the process of inspecting, cleaning, transforming, and modeling data to discover useful information, draw conclusions, and support decision-making.
- Custom GPTs By ChatGPTv5Custom GPTs by ChatGPT are the small set of Custom GPTs that OpenAI itself publishes under the verified @ChatGPT builder profile inside the GPT Store.
- Data Analysis ChatGPT Pluginsv4Data 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…
- CustomGPT Instructions for Knowledge (Uploaded Files)v4"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…
- Data Visualization ChatGPT Pluginsv4Data 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…
- DALL·E Custom GPTsv4DALL·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 .
- Dark Factoryv4A 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.
- AI in cryptocurrencyv4AI in cryptocurrency refers to the use of artificial intelligence techniques, including machine learning, large language models, and AI agents, within cryptocurrency and blockchain systems.
- Creative Writing v3v3Creative 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…
- Convex Setv7A convex set is a set of points in which the line segment connecting any two points of the set lies entirely within the set .
- Conversational Modelsv6Conversational models are computational systems designed to carry on a dialogue with human users in natural language
- Convolutional Operationv4The 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.
- Cross-Validationv5Cross-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.
- Convolutional Layerv6A 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 Filterv6A 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.
- Convolutionv9Convolution 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 Functionv9A 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.
- Counterfactual Fairnessv8Counterfactual 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…
- Criticv8A 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…
- Cross-Entropyv7Cross-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
- Convex Optimizationv7Convex 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.
- Crash Blossomv8A 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.
- Cryptocurrency ChatGPT Pluginsv5Cryptocurrency 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…
- Coverage Biasv5Coverage bias is a type of selection bias that occurs when the method used to collect data systematically excludes part of the target population
- Costv6In machine learning, cost is the scalar number that summarizes how badly a model is performing on a chunk of data.
- Convergencev6Convergence 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…
- Cloud TPUv7Cloud 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…
- Confusion Matrixv7A 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…
- Claude Skillsv7Claude 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…
- Computer-use agentv7A 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…
- Companiesv4Companies in the field of artificial intelligence span foundation model developers, cloud platforms, semiconductor manufacturers, vector database vendors, developer tooling startups, image and video generation…
- Continuous Featurev7A 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.
- Co-Trainingv5Co-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.
- Clusteringv7Clustering 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
- AI in collectiblesv3Artificial 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…
- Co-Adaptationv5Co-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
- Convenience Samplingv6Convenience 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…
- Confident Learning (CL)v6Confident Learning (CL) is a data-centric machine learning framework for characterizing, finding, and learning with label errors in datasets.
- 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…
- Collectibles ChatGPT Pluginsv4Collectibles 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…
- Conditionv4In 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 .
- Clippingv6Clipping is a family of techniques in machine learning that constrain numerical values to lie within a specified range or below a specified magnitude.
- Candidate Generationv7Candidate generation is the first stage in a multi-stage recommendation system or information retrieval pipeline.
- Cars ChatGPT Pluginsv4Cars 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…
- Calibration Layerv7A 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…
- Classification Thresholdv7A 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.
- Class-Imbalanced Datasetv6A 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…
- Causal Language Modelv6A 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…
- Classv4In machine learning, a class is one of the discrete categories that a classification model can assign to an input.
- Candidate Samplingv6Candidate 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.
- COLLIEv3COLLIE (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
- Claude Code Playwrightv6Claude 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
- Carsv4AI 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.
- Categorical Datav7Categorical 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…
- Checkpointv8In 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…
- Centroidv6A 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.
- Centroid-based clusteringv6Centroid-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…
- Bidirectionalv7Bidirectional describes a sequence model in which the representation at every position depends on the entire input sequence, both the tokens before it and the tokens after it
- Boostingv7Boosting is an ensemble learning method in machine learning that trains a sequence of weak learners, each one correcting the errors of its predecessors, and combines them into a single strong learner with high…
- BrowseCompv5BrowseComp (short for Browsing Competition) is a benchmark for measuring how well AI agents can navigate the open internet to retrieve hard-to-find facts.
- Binary conditionv4A binary condition is a test at a node of a decision tree that has exactly two possible outcomes, typically yes or no (equivalently true or false), routing an example down one of two branches.
- Bias (Math) or Bias Termv6The bias term is a learnable additive constant b added to the weighted sum of a neuron's inputs before an activation function is applied, computed as $$z = w \cdot x + b$$.
- Business ChatGPT Pluginsv4Business ChatGPT plugins were the subset of third party extensions, listed in the official plugin store, that connected ChatGPT to enterprise software, customer relationship management systems, sales…
- Bidirectional language modelv7A bidirectional language model is a language model that, when computing a representation for a token, conditions on both the tokens that come before it (the left context) and the tokens that come after it (the…
