Machine Learning

Nonstationarity

Nonstationarity refers to the condition in which the statistical properties of a data-generating process change over time.

Statistics

Normalization

Normalization is the process of scaling numerical data to a standard range or distribution so that features and activations are comparable and downstream computation behaves predictably.

Data & Datasets

Novelty Detection

Novelty detection is a branch of machine learning concerned with identifying test data that differ in some meaningful way from the data available during training.

NumPy

NumPy (short for Numerical Python) is the foundational open-source library for numerical and scientific computing in Python, providing an n-dimensional array object called ndarray along with a large collection…

AI Tools & ProductsMathematics

Numerical Data

Numerical data (also called quantitative data) is information expressed as numbers on a continuous or discrete scale that supports arithmetic operations such as addition, subtraction, multiplication, and…

Data & Datasets

OCR Models

OCR Models are artificial intelligence (AI) systems that convert images of typed, handwritten, or printed text into machine-readable digital text through Optical Character Recognition (OCR).

Artificial IntelligenceComputer Vision

ONNX

ONNX (Open Neural Network Exchange) is an open standard file format for representing machine learning models so they can be moved between different frameworks, runtimes, and hardware platforms without being…

AI Tools & Products

ORPO

ORPO (Odds Ratio Preference Optimization) is a preference alignment algorithm for large language models that merges supervised fine-tuning and preference alignment into a single training stage, eliminating the…

Large Language ModelsTraining & Optimization

Object detection

Object detection is a computer vision task that finds instances of interest in an image and assigns each one a category.

Artificial IntelligenceComputer Vision

Objective

In machine learning, an objective (or objective function) is the scalar function that a learning algorithm optimizes during training: the single number whose gradients drive every parameter update.

Training & Optimization

Oblique condition

An oblique condition is a decision tree split test that involves more than one feature, comparing a linear combination of several numerical features to a threshold rather than testing a single feature on its…

Offline

In machine learning, offline describes operations that happen ahead of time on a fixed dataset rather than continuously on live data.

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.

AI HardwareAI Inference

One-Hot Encoding

One-hot encoding is a data preprocessing technique that converts a categorical variable with…

Data & Datasets

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.

Deep Learning

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…

Reinforcement Learning

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.

Artificial IntelligenceOpen Source AI

OpenThoughts

OpenThoughts is an open-source initiative and a series of datasets of verified reasoning traces created to train open reasoning models.

Data & Datasets

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

Deep LearningTraining & Optimization

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…

AI Ethics

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.

Model Evaluation

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.

Data & DatasetsStatistics

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.

Statistics

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…

Deep LearningNeural Networks

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.

Deep LearningModel Evaluation

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…

Data & Datasets

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…

AI BenchmarksComputer Vision

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.

Model Evaluation

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.

Reinforcement LearningTraining & Optimization

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…

AI Tools & ProductsData Science

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.

Neural Networks

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.

Mathematics

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…

Data & DatasetsStatistics

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.

AlgorithmsRobotics

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.

AI BenchmarksAI Code Generation

Pattern Recognition

Pattern recognition is the automatic discovery of regularities in data through the use of computer algorithms

Artificial IntelligenceComputer Science

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.

Neural Networks

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…

Interpretability

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

MathematicsNatural Language Processing

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.

MLOps

Pipelining

Pipelining is a term used in two distinct senses within machine learning and artificial intelligence.

MLOpsTraining & Optimization

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.

Reinforcement Learning

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.

Reinforcement LearningTraining & Optimization

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…

Computer VisionDeep Learning

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.

Artificial IntelligenceDeep Learning

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

Deep LearningNatural Language Processing

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.

Artificial IntelligenceComputer Vision

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…

Model Evaluation

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.

Model Evaluation

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.

Model Evaluation

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

AI Ethics

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…

AI Ethics

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…

AI Infrastructure

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.

Data & Datasets

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…

MathematicsStatistics

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.

Statistics