Offline
In machine learning, offline describes operations that happen ahead of time on a fixed dataset rather than continuously on live data.
Machine Learning
Explore learning methods, model architectures, datasets, and practical applications.
Explore articles
Browse subtopics (63)
Articles that also belong to these categories. Counts cover all of Machine Learning.
All articles (858)Deep Learning (187)Natural Language Processing (92)Statistics (90)Training & Optimization (70)Data & Datasets (65)Neural Networks (58)Reinforcement Learning (58)Model Evaluation (55)Artificial Intelligence (54)Large Language Models (49)Mathematics (48)Computer Vision (41)AI Ethics (35)AI Infrastructure (29)AI Safety (26)Open Source AI (25)Data Science (24)AI Benchmarks (22)Developer Tools (20)Algorithms (18)AI Hardware (17)AI Tools & Products (17)Google (16)Generative AI (14)Information Retrieval (14)Model Architecture (13)People (13)AI Agents (12)Interpretability (12)Robotics (12)AI Companies (11)Transformer Models (11)AI Inference (10)MLOps (10)AI Models (8)Computer Science (8)AI Code Generation (7)AI Research (7)Multimodal AI (7)Speech & Audio AI (7)Chinese AI (6)AI Policy & Regulation (5)Meta AI (5)Programming Languages (5)AI History (4)AI for Science (4)Prompt Engineering (4)AI Alignment (3)AI Events (3)Reasoning Models (3)Embodied AI (2)Software Development (2)2025 in artificial intelligence (1)Anthropic (1)Diffusion Models (1)Drug Discovery (1)Education AI (1)Enterprise AI (1)Healthcare AI (1)Image Generation (1)NVIDIA (1)Small Language Models (1)World Models (1)
Showing 541-600 of 858 articles
On-device AI
On-device AI is the practice of running machine learning models on the phone, laptop, watch, or embedded board a person is actually using, instead of sending the input to a remote data center.
One-Hot Encoding
One-hot encoding is a data preprocessing technique that converts a categorical variable with $$k$$ distinct categories into $$k$$ binary columns, where each category is represented by a vector that contains…
One-Shot Learning
One-shot learning is a machine learning approach in which a model learns to recognize or classify new categories from only a single labeled example per class.
One-vs.-all
One-vs.-all (OvA), also known as one-vs.-rest (OvR) or one-against-all, is a strategy for turning a multi-class classification problem into several binary classification problems by training one binary…
Online learning
Online learning is a machine learning paradigm in which a model receives data sequentially, one example or one mini-batch at a time, and updates its parameters immediately after each observation rather than…
Open-source AI
Open-source AI refers to artificial intelligence systems whose recipients have broad rights to use, study, modify, and share the system, together with access to the materials needed to exercise those rights.
OpenThoughts
OpenThoughts is an open-source initiative and a series of datasets of verified reasoning traces created to train open reasoning models.
Optimizer
An optimizer in machine learning is an algorithm that iteratively adjusts a model's learnable parameters to minimize (or maximize) an objective function, commonly called a loss function
Out-Group Homogeneity Bias
Out-group homogeneity bias, also called the out-group homogeneity effect, is the cognitive bias in which people perceive members of an out-group as more similar to one another than members of their own…
Out-of-bag evaluation (OOB evaluation)
Out-of-bag (OOB) evaluation, sometimes called out-of-bag estimation or OOB error, is a model validation technique used with bagging-based ensemble methods such as random forests and bagged decision trees.
Outlier Detection
Outlier detection is the process of identifying data points, observations, or patterns that deviate so markedly from the rest of a dataset that they are likely to have been generated by a different process.
Outliers
An outlier is a data point that differs so markedly from the rest of a dataset that it appears not to belong to the same population.
Output Layer
The output layer is the final layer of a neural network: it takes the features computed by the hidden layers and converts them into the model's prediction, with its size and activation function fixed by the…
Overfitting
Overfitting is a failure of generalization: a fitted model or a model-selection procedure performs better on the observations used to develop it than on new observations from the population of interest.
Oversampling
Oversampling is a data preprocessing technique in machine learning that fixes class imbalance by increasing the number of minority class examples in the training set, either by duplicating existing samples…
PASCAL VOC
PASCAL VOC (Pattern Analysis, Statistical Modelling and Computational Learning Visual Object Classes) is a long-running benchmark dataset and annual challenge for object recognition, object detection…
PR AUC
PR AUC (Precision-Recall Area Under the Curve), also referred to as AUPRC or AUC-PR, is a classification evaluation metric that quantifies the area beneath a precision-recall curve.
PROWL-1
PROWL-1 is a training framework from the AI lab Odyssey in which a reinforcement learning agent is paid to break a world model.
Pandas
Pandas is an open-source data analysis and manipulation library for the Python programming language, providing high-performance, flexible data structures designed for working with structured (tabular…
Parameter
In machine learning and statistics, a parameter is an internal variable of a model whose value is learned from data during the training process.
Partial derivative
A partial derivative measures how a multivariable function changes when one of its inputs is varied while every other input is held fixed.
Participation Bias
Participation bias is a systematic error that arises when the individuals who choose to take part in a study, survey, or data collection effort differ in meaningful ways from those who do not, so the resulting…
Particle Filter
A particle filter is a simulation-based method for estimating the changing, unobserved state of a system from a sequence of noisy observations.
Pass@k
Pass@k is the standard metric for evaluating code generation models: it measures the probability that at least one of k generated candidate solutions passes all of a problem's unit tests.
Pattern Recognition
Pattern recognition is the automatic discovery of regularities in data through the use of computer algorithms
Perceptron
A perceptron is the earliest trainable artificial neural network: a single-layer linear model that classifies inputs into two categories by computing a weighted sum and applying a step threshold.
Performance
Performance in machine learning is an overloaded word. It refers to two related but distinct ideas. The first is the quality of a model's predictions: how accurate or useful its outputs are for a given task.
Permutation variable importances
Permutation variable importance is a model-agnostic technique that measures how much a fitted machine learning model relies on a given feature by randomly shuffling that feature's values and recording how much…
Perplexity
Perplexity has two distinct meanings in artificial intelligence. In information theory and natural language processing, perplexity (PPL) is an intrinsic score for a probabilistic model: on a specified sequence
Pipeline
A pipeline in machine learning is a sequence of data processing steps chained together into an automated, end-to-end workflow, where each step takes the previous step's output as its input.
Pipelining
Pipelining is a term used in two distinct senses within machine learning and artificial intelligence.
Policy
In reinforcement learning (RL), a policy is the function that maps an agent's observed state to the action it takes, defining the agent's complete strategy of behavior.
Policy gradient methods
Policy gradient methods are a family of reinforcement learning algorithms that directly parameterise the agent's policy and optimise it by stochastic gradient ascent on the expected return.
Pose estimation
Pose estimation is the computer vision task of detecting and localizing the keypoints (also called landmarks or joints) of a human body, hand, face, animal, or rigid object in images and video, then connecting…
Positive class
In binary classification, the positive class is the class a model is testing for: the outcome it exists to detect, such as "spam," "fraud," or "tumor." The other label, covering everything else
Post-training
Post-training is the stage of large language model (LLM) development that comes after pre-training and turns a raw, general-purpose base model into an aligned, instruction-following AI assistant.
Pre-Trained Model
A pre-trained model is a machine learning model that has already been trained on a large, general-purpose dataset and can then be reused, either as a fixed feature extractor or by fine-tuning
Pre-training
Pre-training is a stage of machine learning in which a model learns parameters from a source dataset or source objective before those parameters are reused or adapted for a target use.
Precision
Precision is a classification metric defined as the fraction of positive predictions that are correct: Precision = TP / (TP + FP), where TP is the number of true positives and FP is the number of false…
Precision-Recall Curve
A precision-recall curve (PR curve) is a graph that plots precision on the y-axis against recall on the x-axis at every possible classification threshold for a binary classification model.
Prediction
Prediction in machine learning is the output a trained model produces when it is applied to new, previously unseen input.
Prediction Bias
Prediction bias is the difference between the average of a machine learning model's predictions and the average of the ground-truth labels in a dataset.
Predictive Parity
Predictive parity is a group fairness metric in machine learning that holds when a classifier's positive predictive value (PPV), also called precision
Predictive rate parity
Predictive rate parity (PRP), also called predictive parity, predictive value parity, or the sufficiency criterion, is a group fairness metric in machine learning that requires a classifier's positive…
Prefix caching (automatic prefix caching)
Prefix caching is an inference optimization for large language model serving that stores and reuses the key-value (KV) cache computed for a shared prompt prefix, so that the prefill for that prefix is computed…
Preprocessing
Preprocessing is the stage of a machine learning workflow that transforms raw data into a clean, consistent, numerical format that learning algorithms can use.
Principal Component Analysis (PCA)
Principal component analysis (PCA) is an unsupervised learning technique for dimensionality reduction that identifies the orthogonal directions of maximum variance in high-dimensional data and projects…
Prior belief
A prior belief, also called the prior distribution or simply the prior, is the probability distribution that expresses what is known or assumed about an unknown parameter before any data is observed.
Probabilistic Graphical Model
A probabilistic graphical model (PGM) is a mathematical representation in which a graph expresses the factorization and conditional-independence structure of a probability distribution.
Probabilistic Regression Model
A probabilistic regression model (also called distributional regression) is a regression model that outputs a full probability distribution over possible target values rather than a single point estimate.
Process reward model (PRM)
A process reward model (PRM), also called a process-supervised reward model or step-level verifier, is a learned scoring model that evaluates the correctness or quality of each intermediate step in a large…
Program Synthesis
Program synthesis is the task of automatically constructing a program that satisfies a specification expressed at a higher level than the code itself: a logical formula, a set of input-output examples, a…
Prompt Caching
Prompt caching is an large language model (LLM) inference optimization that stores the computed key-value (KV) state of a repeated prompt prefix so it can be reused across API calls, cutting both cost and…
Prompt Engineering
Prompt engineering is the systematic design and testing of the inputs supplied to a generative model so that the model is more likely to produce a useful result.
Prompt lookup decoding
Prompt lookup decoding (PLD), also called n-gram speculative decoding, is an inference acceleration method for large language models that speeds up text generation without changing the model or its outputs.
Protein folding
Protein folding is the physical process by which a polypeptide chain, a linear sequence of amino acids, acquires its functional three-dimensional structure, and the long-standing scientific challenge of…
Protein language model
A protein language model (pLM) is a neural network trained on raw amino acid sequences using the same self-supervised objectives that power text models, with individual amino acids serving as tokens instead of…
Proximal Policy Optimization (PPO)
Proximal Policy Optimization (PPO) is an on-policy policy gradient reinforcement learning algorithm that stabilizes training by clipping the policy update so the new policy stays close ("proximal") to the old…
Proxy labels
A proxy label (also called a surrogate label) is an observable, easy-to-collect stand-in for the true target a model should predict, used to train that model when the real target is too expensive, too slow, or…