Deep learningDeep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.
Artificial neural networkArtificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.
Visual systemThe visual system comprises the sensory organ (the eye) and parts of the central nervous system (the retina containing photoreceptor cells, the optic nerve, the optic tract and the visual cortex) which gives organisms the sense of sight (the ability to detect and process visible light) as well as enabling the formation of several non-image photo response functions. It detects and interprets information from the optical spectrum perceptible to that species to "build a representation" of the surrounding environment.
Visual perceptionVisual perception is the ability to interpret the surrounding environment through photopic vision (daytime vision), color vision, scotopic vision (night vision), and mesopic vision (twilight vision), using light in the visible spectrum reflected by objects in the environment. This is different from visual acuity, which refers to how clearly a person sees (for example "20/20 vision"). A person can have problems with visual perceptual processing even if they have 20/20 vision.
DigitizationDigitization is the process of converting information into a digital (i.e. computer-readable) format. The result is the representation of an object, , sound, document, or signal (usually an analog signal) obtained by generating a series of numbers that describe a discrete set of points or samples. The result is called digital representation or, more specifically, a , for the object, and digital form, for the signal.
Visual cortexThe visual cortex of the brain is the area of the cerebral cortex that processes visual information. It is located in the occipital lobe. Sensory input originating from the eyes travels through the lateral geniculate nucleus in the thalamus and then reaches the visual cortex. The area of the visual cortex that receives the sensory input from the lateral geniculate nucleus is the primary visual cortex, also known as visual area 1 (V1), Brodmann area 17, or the striate cortex.
Cultural heritageCultural heritage is the heritage of tangible and intangible heritage assets of a group or society that is inherited from past generations. Not all heritages of past generations are "heritage"; rather, heritage is a product of selection by society. Cultural heritage includes tangible culture (such as buildings, monuments, landscapes, archive materials, books, works of art, and artifacts), intangible culture (such as folklore, traditions, language, and knowledge), and natural heritage (including culturally significant landscapes, and biodiversity).
Machine learningMachine learning (ML) is an umbrella term for solving problems for which development of algorithms by human programmers would be cost-prohibitive, and instead the problems are solved by helping machines 'discover' their 'own' algorithms, without needing to be explicitly told what to do by any human-developed algorithms. Recently, generative artificial neural networks have been able to surpass results of many previous approaches.
Oil paintingOil painting is the process of painting with pigments with a medium of drying oil as the binder. It has been the most common technique for artistic painting on wood panel or canvas for several centuries, spreading from Europe to the rest of the world. The advantages of oil for painting images include "greater flexibility, richer and denser colour, the use of layers, and a wider range from light to dark". But the process is slower, especially when one layer of paint needs to be allowed to dry before another is applied.
PaintingPainting is the practice of applying paint, pigment, color or other medium to a solid surface (called the "matrix" or "support"). The medium is commonly applied to the base with a brush, but other implements, such as knives, sponges, and airbrushes, can be used. In art, the term "painting" describes both the act and the result of the action (the final work is called "a painting").
Feature learningIn machine learning, feature learning or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process.
PatternA pattern is a regularity in the world, in human-made design, or in abstract ideas. As such, the elements of a pattern repeat in a predictable manner. A geometric pattern is a kind of pattern formed of geometric shapes and typically repeated like a wallpaper design. Any of the senses may directly observe patterns. Conversely, abstract patterns in science, mathematics, or language may be observable only by analysis. Direct observation in practice means seeing visual patterns, which are widespread in nature and in art.
Visual fieldThe visual field is "that portion of space in which objects are visible at the same moment during steady fixation of the gaze in one direction"; in ophthalmology and neurology the emphasis is on the structure inside the visual field and it is then considered “the field of functional capacity obtained and recorded by means of perimetry”. However, the visual field can also be understood as a predominantly perceptual concept and its definition then becomes that of the "spatial array of visual sensations available to observation in introspectionist psychological experiments" (for example in van Doorn et al.
Oil paintOil paint is a type of slow-drying paint that consists of particles of pigment suspended in a drying oil, commonly linseed oil. The viscosity of the paint may be modified by the addition of a solvent such as turpentine or white spirit, and varnish may be added to increase the glossiness of the dried oil paint film. The addition of oil or alkyd medium can also be used to modify the viscosity and drying time of oil paint. Oil paints were first used in Asia as early as the 7th century AD and can be seen in examples of Buddhist paintings in Afghanistan.
Unsupervised learningUnsupervised learning, is paradigm in machine learning where, in contrast to supervised learning and semi-supervised learning, algorithms learn patterns exclusively from unlabeled data. Neural network tasks are often categorized as discriminative (recognition) or generative (imagination). Often but not always, discriminative tasks use supervised methods and generative tasks use unsupervised (see Venn diagram); however, the separation is very hazy. For example, object recognition favors supervised learning but unsupervised learning can also cluster objects into groups.
Meta-learning (computer science)Meta learning is a subfield of machine learning where automatic learning algorithms are applied to metadata about machine learning experiments. As of 2017, the term had not found a standard interpretation, however the main goal is to use such metadata to understand how automatic learning can become flexible in solving learning problems, hence to improve the performance of existing learning algorithms or to learn (induce) the learning algorithm itself, hence the alternative term learning to learn.
Text-to-image modelA text-to-image model is a machine learning model which takes an input natural language description and produces an image matching that description. Such models began to be developed in the mid-2010s, as a result of advances in deep neural networks. In 2022, the output of state of the art text-to-image models, such as OpenAI's DALL-E 2, Google Brain's , StabilityAI's Stable Diffusion, and Midjourney began to approach the quality of real photographs and human-drawn art.
IconographyIconography, as a branch of art history, studies the identification, description and interpretation of the content of images: the subjects depicted, the particular compositions and details used to do so, and other elements that are distinct from artistic style. The word iconography comes from the Greek εἰκών ("image") and γράφειν ("to write" or to draw). A secondary meaning (based on a non-standard translation of the Greek and Russian equivalent terms) is the production or study of the religious images, called "icons", in the Byzantine and Orthodox Christian tradition.
Pattern recognitionPattern recognition is the automated recognition of patterns and regularities in data. While similar, pattern recognition (PR) is not to be confused with pattern machines (PM) which may possess (PR) capabilities but their primary function is to distinguish and create emergent pattern. PR has applications in statistical data analysis, signal processing, , information retrieval, bioinformatics, data compression, computer graphics and machine learning.
Conservation and restoration of cultural propertyThe conservation and restoration of cultural property focuses on protection and care of cultural property (tangible cultural heritage), including artworks, architecture, archaeology, and museum collections. Conservation activities include preventive conservation, examination, documentation, research, treatment, and education. This field is closely allied with conservation science, curators and registrars.
