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.
Human eyeThe human eye is a sensory organ, part of the sensory nervous system, that reacts to visible light and allows humans to use visual information for various purposes including seeing things, keeping balance, and maintaining circadian rhythm. The eye can be considered as a living optical device. It is approximately spherical in shape, with its outer layers, such as the outermost, white part of the eye (the sclera) and one of its inner layers (the pigmented choroid) keeping the eye essentially light tight except on the eye's optic axis.
Eye trackingEye tracking is the process of measuring either the point of gaze (where one is looking) or the motion of an eye relative to the head. An eye tracker is a device for measuring eye positions and eye movement. Eye trackers are used in research on the visual system, in psychology, in psycholinguistics, marketing, as an input device for human-computer interaction, and in product design. In addition, eye trackers are increasingly being used for assistive and rehabilitative applications such as controlling wheelchairs, robotic arms, and prostheses.
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.
Deep reinforcement learningDeep reinforcement learning (deep RL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. RL considers the problem of a computational agent learning to make decisions by trial and error. Deep RL incorporates deep learning into the solution, allowing agents to make decisions from unstructured input data without manual engineering of the state space. Deep RL algorithms are able to take in very large inputs (e.g.
Eye movementEye movement includes the voluntary or involuntary movement of the eyes. Eye movements are used by a number of organisms (e.g. primates, rodents, flies, birds, fish, cats, crabs, octopus) to fixate, inspect and track visual objects of interests. A special type of eye movement, rapid eye movement, occurs during REM sleep. The eyes are the visual organs of the human body, and move using a system of six muscles. The retina, a specialised type of tissue containing photoreceptors, senses light.
EyeEyes are organs of the visual system. They provide living organisms with vision, the ability to receive and process visual detail, as well as enabling several photo response functions that are independent of vision. Eyes detect light and convert it into electro-chemical impulses in neurons (neurones).
Evolution of the eyeMany scientists have found the evolution of the eye attractive to study because the eye distinctively exemplifies an analogous organ found in many animal forms. Simple light detection is found in bacteria, single-celled organisms, plants and animals. Complex, image-forming eyes have evolved independently several times. Diverse eyes are known from the Burgess shale of the Middle Cambrian, and from the slightly older Emu Bay Shale.
Reinforcement learningReinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning. Reinforcement learning differs from supervised learning in not needing labelled input/output pairs to be presented, and in not needing sub-optimal actions to be explicitly corrected.
Eye movement in readingEye movement in reading involves the visual processing of written text. This was described by the French ophthalmologist Louis Émile Javal in the late 19th century. He reported that eyes do not move continuously along a line of text, but make short, rapid movements (saccades) intermingled with short stops (fixations). Javal's observations were characterised by a reliance on naked-eye observation of eye movement in the absence of technology.
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.
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.
Accommodation (vertebrate eye)Accommodation is the process by which the vertebrate eye changes optical power to maintain a clear image or focus on an object as its distance varies. In this, distances vary for individuals from the far point—the maximum distance from the eye for which a clear image of an object can be seen, to the near point—the minimum distance for a clear image. Accommodation usually acts like a reflex, including part of the accommodation-vergence reflex, but it can also be consciously controlled.
Lens (vertebrate anatomy)The lens, or crystalline lens, is a transparent biconvex structure in most land vertebrate eyes. Along with the cornea, aqueous and vitreous humours it refracts light, focusing it onto the retina. In many land animals the shape of the lens can be altered, effectively changing the focal length of the eye, enabling them to focus on objects at various distances. This adjustment of the lens is known as accommodation (see also below).
Animal communicationAnimal communication is the transfer of information from one or a group of animals (sender or senders) to one or more other animals (receiver or receivers) that affects the current or future behavior of the receivers. Information may be sent intentionally, as in a courtship display, or unintentionally, as in the transfer of scent from predator to prey with kairomones. Information may be transferred to an "audience" of several receivers. Animal communication is a rapidly growing area of study in disciplines including animal behavior, sociology, neurology and animal cognition.
CommunicationCommunication is usually defined as the transmission of information. The term can also refer to the message itself, or the field of inquiry studying these transmissions, also known as communication studies. The precise definition of communication is disputed. Controversial issues are whether unintentional or failed transmissions are included and whether communication does not just transmit meaning but also create it. Models of communication aim to provide a simplified overview of its main components and their interaction.
Eye examinationAn eye examination is a series of tests performed to assess vision and ability to focus on and discern objects. It also includes other tests and examinations pertaining to the eyes. Eye examinations are primarily performed by an optometrist, ophthalmologist, or an orthoptist. Health care professionals often recommend that all people should have periodic and thorough eye examinations as part of routine primary care, especially since many eye diseases are asymptomatic.
Q-learningQ-learning is a model-free reinforcement learning algorithm to learn the value of an action in a particular state. It does not require a model of the environment (hence "model-free"), and it can handle problems with stochastic transitions and rewards without requiring adaptations. For any finite Markov decision process (FMDP), Q-learning finds an optimal policy in the sense of maximizing the expected value of the total reward over any and all successive steps, starting from the current state.
Human–robot interactionHuman–robot interaction (HRI) is the study of interactions between humans and robots. Human–robot interaction is a multidisciplinary field with contributions from human–computer interaction, artificial intelligence, robotics, natural language processing, design, and psychology. A subfield known as physical human–robot interaction (pHRI) has tended to focus on device design to enable people to safely interact with robotic systems. Human–robot interaction has been a topic of both science fiction and academic speculation even before any robots existed.
Eye contactEye contact occurs when two people or animals look at each other's eyes at the same time. In people, eye contact is a form of nonverbal communication and can have a large influence on social behavior. Coined in the early to mid-1960s, the term came from the West to often define the act as a meaningful and important sign of confidence and respect. The customs, meaning, and significance of eye contact can vary greatly between societies, neurotypes, and religions. The study of eye contact is sometimes known as oculesics.
