4 results about "Composite function" patented technology

The invention provides a reverse design method of a composite function metasurface based on transfer learning, relates to the field of metamaterial design and optimization, and solves the problem of low efficiency of a traditional design method of a metasurface with a complex structure. Comprising the following steps: generating a data set containing various metasurface structure parameters and corresponding spectral responses; building a deep prediction neural network taking the unit structure parameters as input and the spectral response as output; the trained network is combined with a genetic particle swarm optimization algorithm, metasurface phase distribution, transmissivity and other requirements determined in advance are used as objective functions, and optimal parameters are searched through multiple iterations; and migrating universal features learned on the large-scale data set by the source domain network model through a parameter fine tuning method, applying the universal features to a new small data set target domain, repeating the previous process until all parameters are determined, and completing the design. According to the method, the complex metasurface design efficiency can be improved, the neural network performance is ensured, meanwhile, the requirement of the deep learning method for the data collective quantity is reduced, the robustness of the model is improved, and a low-cost practical scheme is provided for metasurface inverse design.

The application provides a DOM data geometric accuracy reduction method, device, equipment and storage medium. It relates to the technical field of geographic data processing. The method comprises the following steps: adding an amplitude factor, a period factor and an error control factor in a hyperbolic exponential composite function, constructing a geometric accuracy reduction function and establishing a geometric accuracy reduction model; selecting a range control point from DOM data, inputting the coordinates of the range control point into the geometric accuracy reduction model, calculating a mean error, and if the mean error does not meet a preset geometric reduction scale, adjusting the error control factor in the geometric reduction model and using the geometric accuracy reduction model with the adjusted error control factor until the mean error meets the preset geometric reduction scale, so that an updated geometric accuracy reduction model is obtained. The application can overcome the significant limitations of the traditional vector data geometric accuracy reduction method in terms of grid data structure adaptability, spatial correlation preservation and continuous data continuity.

The application provides a grammar error correction large model training method and device based on reinforcement learning, equipment and medium, relating to the technical field of data processing. The method comprises the following steps: obtaining an initial grammar correction corpus containing error sentences and corresponding correct sentence pairs, processing the initial grammar correction corpus to generate a reasoning correction training set, adjusting a first preset language model according to the reasoning correction training set to obtain an initial strategy model, performing reinforcement learning training on the initial strategy model based on a preset composite function by using a reinforcement learning algorithm, and finally obtaining a target grammar correction model. The target grammar correction model can fully utilize the reasoning ability, effectively improve the performance of the model in terms of precision and recall, better meet the actual needs of grammar correction, and generate correction results containing reasoning processes, which provides more transparent and interpretable basis for the correction process.

A learning method to be executed by a computer according to one embodiment includes of acquiring event history information representing a history of a predetermined event; and training, by using the acquired event history information, parameters of an intensity function in which a trigger function is set to be a function represented by a composite function of a first function and a predetermined second function; and a derivative of the first function, the first function being represented by a neural network that models a temporal change in influence of the event.