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 principal component analysis (PCA), which is commonly used in machine learning for dimensionality reduction.
For questions about implementation of Machine Learning and Artificial Intelligence algorithms in the C++ programming language.
For questions about algorithms/methods used in AI/ML which is inspired by human behavior/brain.
For questions related to reward shaping, which is a technique where supplemental rewards are provided to make a problem easier to learn. In general, there is usually an obvious natural reward for any …
For questions related to the family of models known as R-CNN (such as the original R-CNN model, fast R-CNN, faster R-CNN and mask R-CNN).
For questions about the proofs/intuitions/methods of combinatorial mathematics used in an AI algorithm.
For questions relating to AI's programming computers. NOT FOR THE PROGRAMMING OF THE AI'S THEMSELVES.
Use for pathfinding, pathing, plotting, etc.
Use for questions involving fitness functions.
Use for question involving discount factor (γ) in reinforcement learning.
For questions related to the synthesis of speech, not to be confused with synthesizing text or formal language expressions or expressions in context free grammars. Speech in this context is either a s…
For questions related to the Atari games, which are often used in reinforcement learning (RL) as standard problems to test new RL algorithms or methods.
For questions related to the random forest (or random decision forests), which is an ensemble machine learning technique (that is, an ML technique that uses or combines different models).
For questions related to AI benchmarks--results that validate a specific technique or approach. Also for question regarding the history of AI achievements, and predictions as to future achievements.
For questions related to conditional probability e.g. in the context of Bayesian inference or networks.
For questions related to the Markov property or Markov assumption (that is, the assumption that the "future is independent of the past, given the present"), which underlies e.g. most reinforcement lea…
For questions related to the concept of a "deterministic policy" (as defined in reinforcement learning).
For questions related to the simulated annealing algorithm (SA), which is a probabilistic algorithm that attempts to find the global optimum of a function. SA can e.g. be used to solve the travelling …
For questions related to the reinforcement learning technique called "eligibility traces", which combines temporal-difference and Monte Carlo methods.
For questions related to the softmax function, which a function that takes as input a vector of K real numbers, and normalizes it into a probability distribution consisting of K probabilities proporti…
For questions related to the concept of algorithmic bias, which is the bias that algorithms exhibit, such as privileging one arbitrary group of users over others. Algorithmic bias can emerge due to ma…
For questions related to the Vapnik–Chervonenkis theory (also known as VC theory), which a form of computational learning theory, so it attempts to explain the learning process from a statistical poin…
For questions related to the gated recurrent unit (GRU), a modification and simplification of the LSTM unit, which is a more sophisticated unit (with respect to the standard one) of a recurrent neural…
For questions related to Artificial Intelligence as a profession. Type of roles (programmer, researcher, etc.) and associated fields of knowledge and skill sets.
For question about artificial systems that exhibit the behavioral characteristics of natural living systems.
Use for questions about self awareness in general, not restricted to engineered artifacts (AI's). Can be synonymous with "Artificial Consciousness" but has a broader scope. "Self Awareness" should b…
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 Boltzmann machines (aka stochastic Hopfield network with hidden units), which are stochastic recurrent neural networks, more precisely, they are Markov random fields.
For questions related to TD($\lambda$) family of algorithms.
For questions related to restricted Boltzmann machines, which is a generative stochastic artificial neural network that can learn a probability distribution over its set of inputs.
For questions related to convolutional layers, which are layers that perform the convolution (or cross-correlation) operation.