5 results about "Object function" patented technology

The invention discloses an emotion recognition method and system based on a deep learning model and a long-short memory network, The method comprises the following steps: data preprocessing and data set partitioning of EEG signals are performed to construct a network model, wherein the network model comprises a picture reconstruction model composed of a variational encoder and an emotion recognition model composed of a long-short memory network; the network model comprises an image reconstruction model composed of a variational encoder and a short-long memory network; The objective function isconstructed according to the network model. The network model is trained by training set, and the objective function is optimized by Adam optimizer in neural network, and the trained network model isobtained. Using the cross-test set to cross-test the trained network model, determining the super-parameters of the network model, and obtaining the final network model; and using the final network model to visualize the seed data and perform emotion recognition. The invention relies on the data artificial intelligence method to learn the collected EEG signal space and time complex structure, reduce the subjective factors in the prediction, and improve the prediction accuracy.

The invention discloses an image classification method based on heterogeneous tensor decomposition. The method comprises the following steps: constructing an original tensor according to an ORL data set; decomposing the original tensor into a factor matrix and a sample feature representation matrix corresponding to each order of the tensor; adding column-by-column orthogonal constraints on the factor matrix; low-rank constraint is applied to the sample feature representation matrix, and the lowest-rank representation is obtained by identifying the global low-rank structure of the sample; through l2, 1 norm constraint loss function and a regularization item, a target of robust feature selection discrimination is realized; obtaining a complete objective function; carrying out optimization iteration on the objective function by using an alternating direction multiplier to obtain an optimal solution, and further obtaining a classifier; and inputting the test set pictures in the ORL into the trained classifier to complete image classification. The method solves the problems that in a traditional vector or matrix method, structural information is likely to be lost, and dependence among elements and heterogeneity in the tensor decomposition process are damaged.

The invention belongs to the technical field of players and provides a method and device for muting a WMP assembly and a player. The method comprises the steps that a creating instance object function of a WMP is called so as to create an object; whether the object created through the creating instance object function is a first object or not is judged; if yes, a first muting function or a second muting function of the first object is called and muting is set according to the called first muting function or the second muting function. According to the method and device for muting the WMP assembly and the player, the problem of failure of muting of the WMP assembly under a webkit kernel can be effectively solved.