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.
Augmented realityAugmented reality (AR) is an interactive experience that combines the real world and computer-generated content. The content can span multiple sensory modalities, including visual, auditory, haptic, somatosensory and olfactory. AR can be defined as a system that incorporates three basic features: a combination of real and virtual worlds, real-time interaction, and accurate 3D registration of virtual and real objects. The overlaid sensory information can be constructive (i.e. additive to the natural environment), or destructive (i.
Computer visionComputer vision tasks include methods for , , and understanding digital images, and extraction of high-dimensional data from the real world in order to produce numerical or symbolic information, e.g. in the forms of decisions. Understanding in this context means the transformation of visual images (the input to the retina in the human analog) into descriptions of the world that make sense to thought processes and can elicit appropriate action.
PredationPredation is a biological interaction where one organism, the predator, kills and eats another organism, its prey. It is one of a family of common feeding behaviours that includes parasitism and micropredation (which usually do not kill the host) and parasitoidism (which always does, eventually). It is distinct from scavenging on dead prey, though many predators also scavenge; it overlaps with herbivory, as seed predators and destructive frugivores are predators. Predators may actively search for or pursue prey or wait for it, often concealed.
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 intelligenceArtificial intelligence (AI) is the intelligence of machines or software, as opposed to the intelligence of human beings or animals. AI applications include advanced web search engines (e.g., Google Search), recommendation systems (used by YouTube, Amazon, and Netflix), understanding human speech (such as Siri and Alexa), self-driving cars (e.g., Waymo), generative or creative tools (ChatGPT and AI art), and competing at the highest level in strategic games (such as chess and Go).
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.
Reinforcement learning from human feedbackIn machine learning, reinforcement learning from human feedback (RLHF) or reinforcement learning from human preferences is a technique that trains a "reward model" directly from human feedback and uses the model as a reward function to optimize an agent's policy using reinforcement learning (RL) through an optimization algorithm like Proximal Policy Optimization. The reward model is trained in advance to the policy being optimized to predict if a given output is good (high reward) or bad (low reward).
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.
Multi-agent reinforcement learningMulti-agent reinforcement learning (MARL) is a sub-field of reinforcement learning. It focuses on studying the behavior of multiple learning agents that coexist in a shared environment. Each agent is motivated by its own rewards, and does actions to advance its own interests; in some environments these interests are opposed to the interests of other agents, resulting in complex group dynamics. Multi-agent reinforcement learning is closely related to game theory and especially repeated games, as well as multi-agent systems.
HD DVDHD DVD (short for High Definition Digital Versatile Disc) is an obsolete high-density optical disc format for storing data and playback of high-definition video. Supported principally by Toshiba, HD DVD was envisioned to be the successor to the standard DVD format. HD DVD employed a blue laser with a shorter wavelength (with the exception of the 3× DVD and HD REC variants), and it stored about 3.2 times as much data per layer as its predecessor (maximum capacity: 15 GB per layer compared to 4.7 GB per layer on a DVD).
High-definition videoHigh-definition video (HD video) is video of higher resolution and quality than standard-definition. While there is no standardized meaning for high-definition, generally any video image with considerably more than 480 vertical scan lines (North America) or 576 vertical lines (Europe) is considered high-definition. 480 scan lines is generally the minimum even though the majority of systems greatly exceed that. Images of standard resolution captured at rates faster than normal (60 frames/second North America, 50 fps Europe), by a high-speed camera may be considered high-definition in some contexts.
Mixed realityMixed reality (MR) is a term used to describe the merging of a real-world environment and a computer-generated one. Physical and virtual objects may co-exist in mixed reality environments and interact in real time. Mixed reality that incorporates haptics has sometimes been referred to as Visuo-haptic mixed reality. In a physics context, the term "interreality system" refers to a virtual reality system coupled with its real-world counterpart.
RoboticsRobotics is an interdisciplinary branch of electronics and communication, computer science and engineering. Robotics involves the design, construction, operation, and use of robots. The goal of robotics is to design machines that can help and assist humans. Robotics integrates fields of mechanical engineering, electrical engineering, information engineering, mechatronics engineering, electronics, biomedical engineering, computer engineering, control systems engineering, software engineering, mathematics, etc.
Computer-mediated realityComputer-mediated reality refers to the ability to add to, subtract information from, or otherwise manipulate one's perception of reality through the use of a wearable computer or hand-held device such as a smartphone. Mediated reality is a proper superset of mixed reality, augmented reality, and virtual reality, as it also includes, for example, diminished reality. Typically, it is the user's visual perception of the environment that is mediated.
Bird of preyBirds of prey or predatory birds, also known as raptors, are hypercarnivorous bird species that actively hunt and feed on other vertebrates (mainly mammals, reptiles and other smaller birds). In addition to speed and strength, these predators have keen eyesight for detecting prey from a distance or during flight, strong feet with sharp talons for grasping or killing prey, and powerful, curved beaks for tearing off flesh. Although predatory birds primarily hunt live prey, many species (such as fish eagles, vultures and condors) also scavenge and eat carrion.
Extended realityExtended reality (XR) is a catch-all term to refer to augmented reality (AR), virtual reality (VR), and mixed reality (MR). The technology is intended to combine or mirror the physical world with a "digital twin world" able to interact with it. The fields of virtual reality and augmented reality are rapidly growing and being applied in a wide range of areas such as entertainment, marketing, real estate, training, maintenance and remote work.
Google DeepMindDeepMind Technologies Limited, doing business as Google DeepMind, is a British-American artificial intelligence research laboratory which serves as a subsidiary of Google. Founded in the UK in 2010, it was acquired by Google in 2014, becoming a wholly owned subsidiary of Google parent company Alphabet Inc. after Google's corporate restructuring in 2015. The company is based in London, with research centres in Canada, France, and the United States.
Soft roboticsSoft robotics is a subfield of robotics that concerns the design, control, and fabrication of robots composed of compliant materials, instead of rigid links. In contrast to rigid-bodied robots built from metals, ceramics and hard plastics, the compliance of soft robots can improve their safety when working in close contact with humans. The goal of soft robotics is the design and construction of robots with physically flexible bodies and electronics. Sometimes softness is limited to part of the machine.
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.
