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.
Diffusion modelIn machine learning, diffusion models, also known as diffusion probabilistic models or score-based generative models, are a class of latent variable models. They are Markov chains trained using variational inference. The goal of diffusion models is to learn the latent structure of a dataset by modeling the way in which data points diffuse through the latent space. In computer vision, this means that a neural network is trained to denoise images blurred with Gaussian noise by learning to reverse the diffusion process.
Types of artificial neural networksThere are many types of artificial neural networks (ANN). Artificial neural networks are computational models inspired by biological neural networks, and are used to approximate functions that are generally unknown. Particularly, they are inspired by the behaviour of neurons and the electrical signals they convey between input (such as from the eyes or nerve endings in the hand), processing, and output from the brain (such as reacting to light, touch, or heat). The way neurons semantically communicate is an area of ongoing research.
Image resolutionImage resolution is the level of detail an holds. The term applies to digital images, film images, and other types of images. "Higher resolution" means more image detail. Image resolution can be measured in various ways. Resolution quantifies how close lines can be to each other and still be visibly resolved. Resolution units can be tied to physical sizes (e.g. lines per mm, lines per inch), to the overall size of a picture (lines per picture height, also known simply as lines, TV lines, or TVL), or to angular subtense.
Transformer (machine learning model)A transformer is a deep learning architecture that relies on the parallel multi-head attention mechanism. The modern transformer was proposed in the 2017 paper titled 'Attention Is All You Need' by Ashish Vaswani et al., Google Brain team. It is notable for requiring less training time than previous recurrent neural architectures, such as long short-term memory (LSTM), and its later variation has been prevalently adopted for training large language models on large (language) datasets, such as the Wikipedia corpus and Common Crawl, by virtue of the parallelized processing of input sequence.
Image editingImage editing encompasses the processes of altering s, whether they are digital photographs, traditional photo-chemical photographs, or illustrations. Traditional analog image editing is known as photo retouching, using tools such as an airbrush to modify photographs or editing illustrations with any traditional art medium. Graphic software programs, which can be broadly grouped into vector graphics editors, raster graphics editors, and 3D modelers, are the primary tools with which a user may manipulate, enhance, and transform images.
Convolutional neural networkConvolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.
PixelIn digital imaging, a pixel (abbreviated px), pel, or picture element is the smallest addressable element in a raster image, or the smallest addressable element in a dot matrix display device. In most digital display devices, pixels are the smallest element that can be manipulated through software. Each pixel is a sample of an original or synthetic image; more samples typically provide more accurate representations of the original. The intensity of each pixel is variable.
Classical architectureClassical architecture usually denotes architecture which is more or less consciously derived from the principles of Greek and Roman architecture of classical antiquity, or sometimes more specifically, from the works of the Roman architect Vitruvius. Different styles of classical architecture have arguably existed since the Carolingian Renaissance, and prominently since the Italian Renaissance. Although classical styles of architecture can vary greatly, they can in general all be said to draw on a common "vocabulary" of decorative and constructive elements.
Display resolutionThe display resolution or display modes of a digital television, computer monitor or display device is the number of distinct pixels in each dimension that can be displayed. It can be an ambiguous term especially as the displayed resolution is controlled by different factors in cathode ray tube (CRT) displays, flat-panel displays (including liquid-crystal displays) and projection displays using fixed picture-element (pixel) arrays. It is usually quoted as , with the units in pixels: for example, means the width is 1024 pixels and the height is 768 pixels.
Recurrent neural networkA recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.
Neoclassical architectureNeoclassical architecture, sometimes referred to as Classical Revival architecture, is an architectural style produced by the Neoclassical movement that began in the mid-18th century in Italy and France. It became one of the most prominent architectural styles in the Western world. The prevailing styles of architecture in most of Europe for the previous two centuries, Renaissance architecture and Baroque architecture, already represented partial revivals of the Classical architecture of ancient Rome and ancient Greek architecture, but the Neoclassical movement aimed to strip away the excesses of Late Baroque and return to a purer and more authentic classical style, adapted to modern purposes.
New Classical architectureNew Classical architecture, New Classicism or Contemporary Classical architecture is a contemporary movement in architecture that continues the practice of Classical architecture. It is sometimes considered the modern continuation of Neoclassical architecture, even though other styles might be cited as well, such as Gothic, Baroque, Renaissance or even non-Western styles – often referenced and recreated from a postmodern perspective as opposed to being strict revival styles.
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.
Classical orderAn order in architecture is a certain assemblage of parts subject to uniform established proportions, regulated by the office that each part has to perform. Coming down to the present from Ancient Greek and Ancient Roman civilization, the architectural orders are the styles of classical architecture, each distinguished by its proportions and characteristic profiles and details, and most readily recognizable by the type of column employed. The three orders of architecture—the Doric, Ionic, and Corinthian—originated in Greece.
Speech recognitionSpeech recognition is an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enable the recognition and translation of spoken language into text by computers. It is also known as automatic speech recognition (ASR), computer speech recognition or speech to text (STT). It incorporates knowledge and research in the computer science, linguistics and computer engineering fields. The reverse process is speech synthesis.
Large language modelA large language model (LLM) is a language model characterized by its large size. Their size is enabled by AI accelerators, which are able to process vast amounts of text data, mostly scraped from the Internet. The artificial neural networks which are built can contain from tens of millions and up to billions of weights and are (pre-)trained using self-supervised learning and semi-supervised learning. Transformer architecture contributed to faster training.
Classical antiquityClassical antiquity, also known as the classical era, classical period, classical age, or simply antiquity, is the period of cultural history between the 8th century BC and the 8th century AD centered on the Mediterranean Sea, comprising the interlocking civilizations of ancient Greece and ancient Rome known as the Greco-Roman world. It is the period in which both Greek and Roman societies flourished and wielded huge influence throughout much of Europe, North Africa, and West Asia.
Super-resolution microscopySuper-resolution microscopy is a series of techniques in optical microscopy that allow such images to have resolutions higher than those imposed by the diffraction limit, which is due to the diffraction of light. Super-resolution imaging techniques rely on the near-field (photon-tunneling microscopy as well as those that use the Pendry Superlens and near field scanning optical microscopy) or on the far-field.
Digital imageA digital image is an composed of picture elements, also known as pixels, each with finite, discrete quantities of numeric representation for its intensity or gray level that is an output from its two-dimensional functions fed as input by its spatial coordinates denoted with x, y on the x-axis and y-axis, respectively. Depending on whether the is fixed, it may be of vector or raster type. Raster image Raster images have a finite set of digital values, called picture elements or pixels.
