A tag is a keyword or label that categorizes your question with other, similar questions. Using the right tags makes it easier for others to find and answer your question.
For questions about AI in relation to video games in particular. (Currently this tag is also used for combinatorial games, such as board and card games.)
For questions about AI problem solving in terms of approaches, theory, logic, and other aspects where the problem is well defined and the objective is to find a solution to the problem.
For questions about the use of various programming languages to be used in AI and ML programming.
For questions about current affairs about various types of contributions/theories proposed by different groups/communities identifying themselves as AI researchers/practitioners/enthusiasts.
For questions involving, but not exclusively about, hardware. (Please use the "hardware-evaluation" for questions exclusively about analysis of hardware components.)
For questions regarding the use of the mathematical theory of games (Von Neumann, Morgenstern, Nash etc) in AI. For questions about the use of AI in game design and gaming, use [gaming].
For questions that ask about or call for proofs for specific assertions, whether they be proofs of theorems or corollaries, proofs of concept through working implementation, counter proofs, or counter…
For questions related to reinforcement learning algorithms often referred to as "policy gradients" (or "policy gradient algorithms"), which attempt to directly optimise a parameterised policy (without…
For questions related to word embeddings, which are vector representations of words.
For questions related to the concept of "reward" (e.g. in reinforcement learning).
For question involving probability as related to AI methods. (This tag is for general usage. Feel free to utilize in conjunction with the "math" and more specific probability tags.)
For questions related to multi-agent systems (MAS), which are systems that involve multiple agents (each of them can have different skills) that cooperate with each other and interact with the environ…
Use for questions involving minimax and variants such as maximin. Applies both to algorithms and the minimax theorem.
used in the context of non-blind (i.e., informed) search and planning: the problem of finding a sequence of actions to find/generate a desired state from an initial stat…
For questions relating to self-driving vehicles, their AI related requirements, the prioritization of those requirements, AI designs for AVs, plotting courses, changing plans due to conditions, algori…
For questions about AI architecture specifically. (For general software architecture questions, use the "software-architecture" tag.
For questions related to the family of reinforcement learning algorithms denoted by "actor-critic", where there is an actor (a policy) and a critic (a value function).
For questions related to object detection (which includes e.g. human or face detection), whose goal is to locate a specific object in an image. Object detection is different from object recognition, w…
For questions related to neuroevolution (or neuro-evolution) techniques, such as NEAT, that are used to evolve (or train) artificial neural networks (that is, they are used evolve their parameters or …
For questions about ways of measuring intelligence of AI, either in relation to other AIs, in relation to humans, or in absolute terms on a certain scale.
For questions about the applications/clarifications/intuitions/proofs behind the use of statistical methods in AI/ML programs.
For questions about functioning, applications, structure and improvement of performance of hidden layers in a Neural Network.
Use for broad questions on the concepts used in AI and implementations. Breakdowns of subfields, methods, and sets of methods, with an emphasis on context and utility.
For questions involving topology in any form in relation to Artificial Intelligence.
For questions related to the concept of super-intelligence (also called ultra-intelligence or hyper-intelligence), which is a hypothetical intelligent agent that possesses intelligence far surpassing …
For questions related to DeepMind's AlphaZero, which is a computer program that can play Go, Chess, and Shogi. AlphaZero achieved, within 24 hours of training, a superhuman level of play in these thre…
For questions about all aspects of a biological or artificial neuron.
a variant of boolean logic, where the values are real numbers between 0 and 1 (inclusive), rather than only the integer numbers 0 and 1. Use this tag for questions that involve this re…
For questions related to regression (both linear and non-linear) in the context of machine learning and AI.
For questions about the Turing Test, a test designed to see whether a third-party person can identify, from a written transcript, who was the AI and who was the human is an human/AI conversation.
For questions about the over-fitting of data-sets in Machine Learning algorithms.