8 results about "Hidden layer" patented technology

The invention discloses an automatic classification method for electrocardiogram signals. The method is achieved according to the following steps of firstly, obtaining electrocardiogram signals of a human body, conducting filtering on the electrocardiogram signals, and detecting R waves of the electrocardiogram signals where filtering is conducted; secondly, establishing a data set after the R waves are detected, wherein the data set is composed of multiple sets of cardiac beat data, and each set of cardiac beat data has a label; thirdly, establishing a sparse automatic coding deep learning network; fourthly, training the sparse automatic coding deep learning network step by step; fifthly, inputting the to-be-measured cardiac beat data into the sparse automatic coding deep learning network according to the network weight, obtained in the fourth step, of the first hidden layer, the network weight, obtained in the fourth step, of the second hidden layer and the network weight, obtained in the fourth step, of the softmax classifier so as to obtain cardiac data which are output in a classified mode. The sparse automatic coding deep learning network is applied to the classification of the cardiac beat data, and by means of the autonomous leaning capacity and the deep characteristic excavation characteristic of the sparse automatic coding deep learning network, deeper characteristics of signals are extracted, and the cardiac beat data are classified.

The invention relates to an interest point check-in prediction method fusing deep learning with a factorization machine and belongs to the field of location check-in prediction. The method comprises the following steps: S1, acquiring check-in data of a user; S2, performing embedding processing on input discrete data; S3, performing sparse elimination processing on the discrete data, and learning implicit second order relations among the data; S4, learning addition of continuous characteristics into a full connection hidden layer, and selecting an appropriate excitation function; S5, inputtinga result obtained by processing discrete characteristics and a result obtained by processing the continuous characteristics and adding the results as an input of a hidden layer h1; S6, enabling an output l1 of the hidden layer h1 to pass a first-order linear and characteristic interaction structure and adding as an input of a hidden layer h2; and S7, receiving an input by a hidden layer h3 from outputs l1 and l2 of the hidden layers h1 and h2, adding a shortcut structure at the same time for guaranteeing gradient stability during parameter learning, determining the best model structure, and finally outputting a prediction result. The method provided by the invention fully excavates and learns check-in rules and predicts interest point check-in problems by analyzing check-in information ofthe user.

The embodiment of the invention provides a translation model training method and device and a translation method and device. The model training method comprises the following steps: respectively inputting a source language statement and a noisy source language statement in a parallel bilingual sentence pair into a translation model to obtain a first prediction target language statement and a second prediction target language statement, first prediction probability distribution and second prediction probability distribution of the translation model and/or first feature vectors and second feature vectors output by the hidden layers are obtained respectively; based on the first prediction target language statement and the target language statement in the parallel bilingual sentence pair, the second prediction target language statement and the target language statement corresponding to the noise-added source language statement, the first feature vector and the second feature vector and/or the first prediction probability distribution and the second prediction probability distribution; determining the current training loss of the translation model, and adjusting the parameters of the translation model. According to the embodiment of the invention, the robustness of the translation model can be improved, the training method is simple, and model training is stable.

The invention relates to a soft measurement method for the temperature in a multi-component organic waste high-temperature gasifier, which comprises the following steps of: selecting a plurality of process variables measured during normal operation of the gasifier, performing data preprocessing, selecting a BP neural network with three layers, training the BP neural network by adopting a level-marquardt algorithm, and calculating the temperature in the gasifier according to the trained BP neural network. And selecting the neural network with the minimum result error in the neural networks with different hidden layer node numbers as a target neural network, and realizing soft measurement of the temperature in the multi-component organic waste high-temperature gasifier by using the obtained neural network. The method effectively overcomes the defects of uncertain and unstable properties of traditional temperature physical measurement and raw material components entering the furnace and the like, can accurately predict the temperature in the multi-component organic waste high-temperature gasifier, and has important application value for temperature regulation and stable operation in the waste treatment process.

The invention discloses a machine self-learning intelligent plate changing method for an edge roller. The method comprises the following steps: inputting multiple groups of samples into a machine learning neural network; the machine learning neural network performs forward calculation according to the input sample data so as to perform model training; adjusting the weight from the input layer to the hidden layer and the weight from the hidden layer to the output layer; updating the number of times of model training, judging whether the number of times of target training is reached or not, if not, returning to the above steps to continue training, and if yes, ending training, storing trained data and obtaining a trained model; in actual production, the width and thickness of glass required by production are input into the trained model to obtain the parking space, pressing and swing angle of the glass edge roller needing to be adjusted, and the glass edge roller is adjusted to obtain glass required by production; the method has the advantages that the board changing efficiency is improved, the model is continuously optimized according to historical data, the board changing result does not depend on previously stored data, and the board changing data error is small.

The invention discloses an automatic operation order issuing method and device based on artificial intelligence, a terminal and a medium. The method comprises the steps of obtaining a dispatching operation order order of a power dispatching system; building an identity authentication model based on a BP neural network, and authenticating the identity of the dispatcher through the identity authentication model; enabling the dispatcher passing the authentication to receive the dispatching operation command ticket and a pre-issuing order of the dispatching operation command ticket; judging whether the dispatching operation command ticket meets all automatic command issuing conditions or not; if yes, issuing a scheduling instruction to the authenticated dispatcher according to the pre-issued instruction; and if not, not issuing the scheduling instruction. The identity authentication model is established based on the neural network, and the accuracy of identity authentication is improved by setting the number of nodes of the input layer, the output layer and the hidden layer. Meanwhile, order issuing conditions are set through the safety isolation device DMIS system, automatic issuing of dispatching operation order instructions is achieved, and the method has the advantages of being short in consumed time, high in accuracy and high in safety.