Solid oxide electrolyzer cellA solid oxide electrolyzer cell (SOEC) is a solid oxide fuel cell that runs in regenerative mode to achieve the electrolysis of water (and/or carbon dioxide) by using a solid oxide, or ceramic, electrolyte to produce hydrogen gas (and/or carbon monoxide) and oxygen. The production of pure hydrogen is compelling because it is a clean fuel that can be stored, making it a potential alternative to batteries, methane, and other energy sources (see hydrogen economy).
Photoelectrolysis of waterPhotoelectrolysis of water, also known as photoelectrochemical water splitting, occurs in a photoelectrochemical cell when light is used as the energy source for the electrolysis of water, producing dihydrogen which can be used as a fuel. This process is one route to a "hydrogen economy", in which hydrogen fuel is produced efficiently and inexpensively from natural sources without using fossil fuels. In contrast, steam reforming usually or always uses a fossil fuel to obtain hydrogen.
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.
Biological neuron modelBiological neuron models, also known as a spiking neuron models, are mathematical descriptions of the properties of certain cells in the nervous system that generate sharp electrical potentials across their cell membrane, roughly one millisecond in duration, called action potentials or spikes (Fig. 2). Since spikes are transmitted along the axon and synapses from the sending neuron to many other neurons, spiking neurons are considered to be a major information processing unit of the nervous system.
High dynamic rangeHigh dynamic range (HDR) is a dynamic range higher than usual, synonyms are wide dynamic range, extended dynamic range, expanded dynamic range. The term is often used in discussing the dynamic range of various signals such as s, videos, audio or radio. It may apply to the means of recording, processing, and reproducing such signals including analog and digitized signals. The term is also the name of some of the technologies or techniques allowing to achieve high dynamic range images, videos, or audio.
BackpropagationAs a machine-learning algorithm, backpropagation performs a backward pass to adjust the model's parameters, aiming to minimize the mean squared error (MSE). In a single-layered network, backpropagation uses the following steps: Traverse through the network from the input to the output by computing the hidden layers' output and the output layer. (the feedforward step) In the output layer, calculate the derivative of the cost function with respect to the input and the hidden layers.
