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 the 1d convolution in convolutional neural networks.
For questions related to the asynchronous advantage actor-critic (A3C) algorithm.
For questions related to the academic aspects of AI, and the academic fields involving AI.
For questions about use of AI to promote accessibility, in particular in regard to humans with disabilities.
For questions related to the "action model learning", which is an area of machine learning concerned with creation and modification of software agent's knowledge about effects and preconditions of the…
For questions regarding action recognition. This should be used when asking about what could be implemented that complements or harms this.
For questions related to the selection of and theory behind specific activation functions used in artificial networks.
For questions related to active learning, which is a machine learning technique where the user is interactively queried to label certain unlabelled training examples.
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 about the ADADELTA optimization algorithm used to train neural networks. ADADELTA adaptively changes the learning rate during training. It was proposed in the paper "ADADELTA: An Adaptiv…
For questions about Adam, a gradient-based optimization algorithm widely used to train neural networks. It was proposed in the paper "Adam: A Method for Stochastic Optimization" (2014) by Diederik P. …
For questions related to admissible heuristics, which are heuristics that never overestimate the cost of reaching a goal.
For questions related to the advantage actor-critic algorithms (that is, actor-critic algorithms that use the "advantage" function).
For questions related to adversarial machine learning, which is a branch of machine learning focused on the study of adversarial examples, which are malicious inputs designed to fool machine learning …
For questions related to affective computing, which is the study and development of systems and devices that can recognize, interpret, process, and simulate human emotions (or affects). AC is an inter…
For questions about Artificial General Intelligence (AGI), a hypothetical machine characteristic permitting it to learn any arbitrary intellectual ability up to the limits of the available computing r…
Use for basic, fundamental questions about AI theory or practice. (i.e. design, application, implementation, mathematics of AI, philosophy of AI, etc.)
A hypothetical artificial superintelligence is kept in a virtual prison with limited means of affecting the external world. Can the AI hack its way out or trick its human keepers into releasing it?
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 related to AI-complete (or AI-hard) problems, which, informally, are the problems, in AI, that require a human-level or general intelligence to be solved.
For questions related to the design of AI agents, algorithms or models.
For general questions about the field of AI. Academic, industry, etc.
Use for questions related to claims or presentations related to AI capabilities that may be hoaxes.
For questions about AI milestone, both those achieved and those predicted.
For questions regarding various parameters/methods of implementation/improvement/analyzing the safety of an Artificially Intelligent algorithm. A typical real world example is autonomous vehicles.
For questions related to the apocalyptic or dystopian scenarios of automata supplanting humanity.
For questions related to AI winters, which are periods of reduced funding and interest in artificial intelligence research, due to unmet expectations after a period of hype. There have been at least t…
a theoretical mathematical formalism for artificial general intelligence.
For questions related to the convolutional neural network denoted as AlexNet, designed by Alex Krizhevsky (hence the name AlexNet), and published with Ilya Sutskever and Krizhevsky's doctoral advisor …
For questions about algorithm's that exhibit characteristics of intelligence, or are critical components in systems that exhibit intelligence, and problem-solving and goal-based algorithms in general.