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 related to attention based AI approaches, including gating at the network cell level, selection of models within a model container, virtual pan and zoom within an image field, selection …
For questions related to the reinforcement learning algorithm called proximal policy optimization (PPO), which was introduced in the paper "Proximal Policy Optimization Algorithms" (2017) by John Schu…
For questions related to the concept of data pre-processing, which includes, for example, cleaning, instance selection, normalization, transformation, feature extraction or selection.
For questions related to the concept of environment in reinforcement learning and other AI sub-fields.
For questions related to transfer learning, a machine learning method that focuses on storing knowledge gained while solving one problem in order to apply this knowledge to a different but related pro…
Use for objective evaluations and assessments of computing devices and components, including CPUs, GPUs, etc., based on architecture and performance statistics. Opinions may be suitable for comm…
For questions about the brain of a living organism, e.g. what qualifies as a brain? What is the purpose of a brain? How does the brain function?
Use for questions about collective behavior of decentralized, self-organized algorithmic systems, artificial or natural.
For questions related to computational learning theory (or, in short, learning theory), which is a research subfield of artificial intelligence devoted to studying the design and mathematical analysis…
For questions related to the planing of paths through a tree or network of vertices connected by edges, whereby there is some set of objectives that the plan is constructed to meet. Such objectives co…
For questions about the security measures against malicious algorithms, and security measures provided by AI algorithms in detecting, mitigating and preventing breaches and malicious activity.
For questions related to the convolution operation or convolutional layer (in the case of convolutional neural networks).
For questions related to machine translation (MT), which is the task of translating text using a computer, machine or software.
For questions related to the temporal-difference reinforcement learning (RL) algorithms, which is a class of model-free (that is, they do not use the transition and reward function of the MDP) RL algo…
specialized hardware for the manipulation of images and calculation of local image properties.
For questions related to features in the context of machine learning and, in general, AI.
For questions related to the transformer, which is a deep machine learning model introduced in 2017 in the paper "Attention Is All You Need", used primarily in the field of natural language processing…
Use for question about the emergent "mythology of AI", from Talos in Greek mythology, to Skynet and the technological singularity.
For questions related to Google in the context of AI (e.g. related to Google Translate). Google is an American multinational technology company specializing in internet-related services and products.
For questions about the application of AI/ML algorithms in the field of OCR.
For questions about processing signals of any physical quantity, with the help of Machine Learning or Artificially Intelligent algorithms.
For questions about the legal aspects and ramifications due to the creation/use of AI in various fields and applications (also laws in place to regulate the proper use of AI technology).
For questions related to the hyper-parameters of AI models and algorithms, which are parameters that are set before the learning process begins. For example, the number of hidden layers in a feed-forw…
For questions related to variational auto-encoders (VAEs). The first VAE was proposed in "Auto-Encoding Variational Bayes" (2013) by Diederik P. Kingma and Max Welling. There are several other VAEs, f…
For questions related to recommender systems in the context of machine learning and data mining.
For questions related to the REINFORCE algorithm (or update rule), which is a policy gradient algorithm, that is, an algorithm which estimates the policy directly (that is, without first estimating an…
For questions related to the concept of feature extraction, which is a set of techniques used to derive or create features from the existing set of features. Feature extraction is different from featu…
For questions related to BERT (which stands for Bidirectional Encoder Representations from Transformers), a language representation model introduced in the paper "BERT: Pre-training of Deep Bidirectio…
For questions related to AlphaGo Zero, which is a version of DeepMind's Go software, AlphaGo, that does not use data from human games and it is stronger than AlphaGo. There is a generalized version of…