AutoencoderAn autoencoder is a type of artificial neural network used to learn efficient codings of unlabeled data (unsupervised learning). An autoencoder learns two functions: an encoding function that transforms the input data, and a decoding function that recreates the input data from the encoded representation. The autoencoder learns an efficient representation (encoding) for a set of data, typically for dimensionality reduction. Variants exist, aiming to force the learned representations to assume useful properties.
Built environmentThe term built environment refers to human-made conditions and is often used in architecture, landscape architecture, urban planning, public health, sociology, and anthropology, among others. These curated spaces provide the setting for human activity and were created to fulfill human desires and needs. The term can refer to a plethora of components including the traditionally associated buildings, cities, public infrastructure, transportation, open space, as well as more conceptual components like farmlands, dammed rivers, wildlife management, and even domesticated animals.
