Logic levelIn digital circuits, a logic level is one of a finite number of states that a digital signal can inhabit. Logic levels are usually represented by the voltage difference between the signal and ground, although other standards exist. The range of voltage levels that represent each state depends on the logic family being used. A logic-level shifter can be used to allow compatibility between different circuits. In binary logic the two levels are logical high and logical low, which generally correspond to binary numbers 1 and 0 respectively or truth values true and false respectively.
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.
Prospective short-circuit currentThe prospective short-circuit current (PSCC), available fault current, or short-circuit making current is the highest electric current which can exist in a particular electrical system under short-circuit conditions. It is determined by the voltage and impedance of the supply system. It is of the order of a few thousand amperes for a standard domestic mains electrical installation, but may be as low as a few milliamperes in a separated extra-low voltage (SELV) system or as high as hundreds of thousands of amps in large industrial power systems.
Synthèse logiqueEn électronique, la synthèse logique (RTL synthesis) est la traduction d'une forme abstraite de description du comportement d'un circuit (voir Register Transfer Level) en sa réalisation concrète sous forme de portes logiques. Le point de départ peut être un langage de description de matériel comme VHDL ou Verilog, un schéma logique du circuit. D'autres sources sont venues s'additionner depuis les années 2010, comme l'utilisation de la programmation en OpenCL. Le point d'arrivée peut être un code objet pour un CPLD ou FPGA ou la création d'un ASIC.
Neuromorphic engineeringNeuromorphic computing is an approach to computing that is inspired by the structure and function of the human brain. A neuromorphic computer/chip is any device that uses physical artificial neurons to do computations. In recent times, the term neuromorphic has been used to describe analog, digital, mixed-mode analog/digital VLSI, and software systems that implement models of neural systems (for perception, motor control, or multisensory integration).
Canonical normal formIn Boolean algebra, any Boolean function can be expressed in the canonical disjunctive normal form (CDNF) or minterm canonical form, and its dual, the canonical conjunctive normal form (CCNF) or maxterm canonical form. Other canonical forms include the complete sum of prime implicants or Blake canonical form (and its dual), and the algebraic normal form (also called Zhegalkin or Reed–Muller). Minterms are called products because they are the logical AND of a set of variables, and maxterms are called sums because they are the logical OR of a set of variables.
Residual-current deviceA residual-current device (RCD), residual-current circuit breaker (RCCB) or ground fault circuit interrupter (GFCI) is an electrical safety device that quickly breaks an electrical circuit with leakage current to ground. It is to protect equipment and to reduce the risk of serious harm from an ongoing electric shock. Injury may still occur in some cases, for example if a human receives a brief shock before the electrical circuit is isolated, falls after receiving a shock, or if the person touches both conductors at the same time.
Réseau de neurones à impulsionsLes réseaux de neurones à impulsions (SNNs : Spiking Neural Networks, en anglais) sont un raffinement des réseaux de neurones artificiels (ANNs : Artificial Neural Networks, en anglais) où l’échange entre neurones repose sur l’intégration des impulsions et la redescente de l’activation, à l’instar des neurones naturels. L’encodage est donc temporel et binaire. Le caractère binaire pose une difficulté de continuité au sens mathématique (cela empêche notamment l’utilisation des techniques de rétropropagation des coefficients - telle que la descente de gradient - utilisées classiquement dans les méthodes d'apprentissage).
Triple modular redundancyIn computing, triple modular redundancy, sometimes called triple-mode redundancy, (TMR) is a fault-tolerant form of N-modular redundancy, in which three systems perform a process and that result is processed by a majority-voting system to produce a single output. If any one of the three systems fails, the other two systems can correct and mask the fault. The TMR concept can be applied to many forms of redundancy, such as software redundancy in the form of N-version programming, and is commonly found in fault-tolerant computer systems.
