Machine learning

scientific study of algorithms and statistical models that computer systems use to perform tasks without explicit instructions

artificial intelligence model capable of generating content in response to a prompt

Claude is a series of large language models developed by Anthropic and first released in 2023. Since Claude 3, each generation has typically been released in three sizes, from least to most capable: Haiku, Sonnet, and Opus. An additional model named Claude Mythos was released to some companies in 2026 but not to the public.

set of data indexed in time order

creation or optimization of a prompt to be given to an artificial intelligence model

branch of machine learning

confident unjustified claim by an AI

statistical model validation technique

The identification of rare items, events or observations which raise suspicions by differing significantly from the expected or majority of the data

thumb|300px|Figure 1.  The green line represents an overfitted model and the black line represents a regularized model. While the green line best follows the training data, it is too dependent on that data and is likely to have a higher error rate on new unseen data, illustrated by black-outlined dots, compared to the black line. thumb|300x300px|Figure 2.  Noisy (roughly linear) data is fitted to a linear function and a polynomial function. Although the polynomial function is a perfect fit, the linear function can be expected to generalize better: If the two functions were used to ex

American company

form of business process automation technology

systematic and repeatable errors in a computer system that create unfair outcomes, such as privileging one arbitrary group of users over others

problem in library science, information science and computer science

table layout for visualizing performance; also called an error matrix

class of machine learning techniques in which a task is solved based on pseudo-labels which help initialize weights the weight, then the actual task is performed with supervised or unsupervised learning

research problem in machine learning (ML) that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem

model of text which uses a representation of text that is based on an unordered collection (a "bag") of words

model for randomly generating observable data in probability and statistics

process of taking a pre-trained model and further training it on a smaller, specific dataset to adapt or improve its performance for a particular task or domain

various phenomena that arise when analyzing and organizing data in high-dimensional spaces that do not occur in low-dimensional settings such as the three-dimensional physical space of everyday experience

machine learning technique

in machine learning, individual measurable property or characteristic of a phenomenon being observed

a set of techniques that learn a feature: a transformation of raw data input to a representation that can be effectively exploited in machine learning tasks

Quantum Machine Learning combines quantum computing and ML to enhance algorithms, leveraging unique quantum properties, like superposition and entanglement , for efficient problem-solving.

process that creates features for machine learning by transforming or combining existing features

thumb|MLOps is the set of practices at the intersection of Machine Learning, DevOps and Data Engineering MLOps or ML Ops is a paradigm that aims to deploy and maintain machine learning models in production reliably and efficiently. It bridges the gap between machine learning development and production operations, ensuring that models are robust, scalable, and aligned with business goals. The word is a compound of "machine learning" and the continuous delivery practice (CI/CD) of DevOps in the software field. Machine learning models are tested and developed in isolated experimental systems. Whe

machine learning technique that attempts to prevent models being fooled by supplying deceptive input

property of a set of predictive models whereby models with a lower bias in parameter estimation have a higher variance of the parameter estimates across samples, and vice versa

estimator

class of machine learning techniques combining a small amount of labeled data with a large amount of unlabeled data during training

manipulation of data before it is analyzed

the task of classifying the elements of a given set into two groups (predicting which group each one belongs to) on the basis of a classification rule

method for artificial intelligence

in machine learning, a parameter whose value is used to control the learning process

class of statistical modeling method applied in pattern recognition and machine learning and used for structured prediction

a rigorous method of deriving an ontology from a collection of objects and their properties

choosing a set of optimal hyperparameters for a learning algorithm

in computer science, a way to determine theoretical bounds in machine learning

tuning parameter (hyperparameter) in optimization

theoretical framework for machine learning

process of automating the end-to-end process of machine learning

creation of more data based on previously collected data to enhance the performance of a statistical model

language models designed for reasoning tasks

type of machine learning method

database designed to store vector embeddings and perform similarity search in high-dimensional spaces

learning programs from data

optimization technique for undifferentiable, black-box functions

machine learning strategy in which a learning algorithm interactively queries for new labels

geometric property of a pair of sets of points in Euclidean geometry

Used in machine learning

Astrostatistics is a discipline which spans astrophysics, statistical analysis and data mining. It is used to process the vast amount of data produced by automated scanning of the cosmos, to characterize complex datasets, and to link astronomical data to astrophysical theory. Many branches of statistics are involved in astronomical analysis including nonparametrics, multivariate regression and multivariate classification, time series analysis, and especially Bayesian inference. The field is closely related to astroinformatics.

in a machine-learning algorithm, the set of assumptions that the learner uses to predict outputs of given inputs that it has not encountered

type of coefficient

application of machine learning

Python library

reinforcement learning problem exemplifying the exploration–exploitation tradeoff

robot with processing architecture that will allow it to learn

trait of an algorithm, whose results are independent of given variables, e.g. gender, ethnicity, sexual orientation, disability

applications of machine learning to quantum physics