Attention (machine learning)Machine learning-based attention is a mechanism mimicking cognitive attention. It calculates "soft" weights for each word, more precisely for its embedding, in the context window. It can do it either in parallel (such as in transformers) or sequentially (such as recursive neural networks). "Soft" weights can change during each runtime, in contrast to "hard" weights, which are (pre-)trained and fine-tuned and remain frozen afterwards. Multiple attention heads are used in transformer-based large language models.
Time delay neural networkTime delay neural network (TDNN) is a multilayer artificial neural network architecture whose purpose is to 1) classify patterns with shift-invariance, and 2) model context at each layer of the network. Shift-invariant classification means that the classifier does not require explicit segmentation prior to classification. For the classification of a temporal pattern (such as speech), the TDNN thus avoids having to determine the beginning and end points of sounds before classifying them.
Language modelA language model is a probabilistic model of a natural language that can generate probabilities of a series of words, based on text corpora in one or multiple languages it was trained on. Large language models, as their most advanced form, are a combination of feedforward neural networks and transformers. They have superseded recurrent neural network-based models, which had previously superseded the pure statistical models, such as word n-gram language model.
Physical neural networkA physical neural network is a type of artificial neural network in which an electrically adjustable material is used to emulate the function of a neural synapse or a higher-order (dendritic) neuron model. "Physical" neural network is used to emphasize the reliance on physical hardware used to emulate neurons as opposed to software-based approaches. More generally the term is applicable to other artificial neural networks in which a memristor or other electrically adjustable resistance material is used to emulate a neural synapse.
Visual acuityVisual acuity (VA) commonly refers to the clarity of vision, but technically rates a person's ability to recognize small details with precision. Visual acuity depends on optical and neural factors. Optical factors of the eye influence the sharpness of an image on its retina. Neural factors include the health and functioning of the retina, of the neural pathways to the brain, and of the interpretative faculty of the brain. The most commonly referred-to visual acuity is distance acuity or far acuity (e.g.
Linear regressionIn statistics, linear regression is a linear approach for modelling the relationship between a scalar response and one or more explanatory variables (also known as dependent and independent variables). The case of one explanatory variable is called simple linear regression; for more than one, the process is called multiple linear regression. This term is distinct from multivariate linear regression, where multiple correlated dependent variables are predicted, rather than a single scalar variable.
ImageNetThe ImageNet project is a large visual database designed for use in visual object recognition software research. More than 14 million images have been hand-annotated by the project to indicate what objects are pictured and in at least one million of the images, bounding boxes are also provided. ImageNet contains more than 20,000 categories, with a typical category, such as "balloon" or "strawberry", consisting of several hundred images.
Visual agnosiaVisual agnosia is an impairment in recognition of visually presented objects. It is not due to a deficit in vision (acuity, visual field, and scanning), language, memory, or intellect. While cortical blindness results from lesions to primary visual cortex, visual agnosia is often due to damage to more anterior cortex such as the posterior occipital and/or temporal lobe(s) in the brain.[2] There are two types of visual agnosia: apperceptive agnosia and associative agnosia. Recognition of visual objects occurs at two primary levels.
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.
Information societyAn information society is a society where the usage, creation, distribution, manipulation and integration of information is a significant activity. Its main drivers are information and communication technologies, which have resulted in rapid growth of a variety of forms of information. Proponents of this theory posit that these technologies are impacting most important forms of social organization, including education, economy, health, government, warfare, and levels of democracy.
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.
