Abstract: The present invention is related to polymer-based formulation for release of drugs and bioactives at gastrointestinal tract specific sites including stomach, intestine and colon.

Abstract: The present invention is related to polymer based formulation for release of drugs and bioactives at gastrointestinal tract specific sites including stomach, intestine and colon.

Abstract: Provided are a method and apparatus for classifying a sentence into a class by using a deep neural network. The method includes respectively training first and second sentences by using first and second neural networks, obtaining a contrastive loss based on first and second feature vectors generated as output data of the training, and information about whether classes to which the first and second sentences belong are the same, and repeating the training in such a manner that the contrastive loss has a maximum value.

Abstract: An electronic apparatus for compressing a language model is provided, the electronic apparatus including a storage configured to store a language model which includes an embedding matrix and a softmax matrix generated by a recurrent neural network (RNN) training based on basic data including a plurality of sentences, and a processor configured to convert the embedding matrix into a product of a first projection matrix and a shared matrix, the product of the first projection matrix and the shared matrix having a same size as a size of the embedding matrix, and to convert a transposed matrix of the softmax matrix into a product of a second projection matrix and the shared matrix, the product of the second projection matrix and the shared matrix having a same size as a size of the transposed matrix of the softmax matrix, and to update elements of the first projection matrix, the second projection matrix and the shared matrix by performing the RNN training with respect to the first projection matrix, the second p

Abstract: The present invention is related to polymer based formulation for release of drugs and bioactives at gastrointestinal tract specific sites including stomach, intestine and colon.

Abstract: Provided are a method and apparatus for classifying a sentence into a class by using a deep neural network. The method includes respectively training first and second sentences by using first and second neural networks, obtaining a contrastive loss based on first and second feature vectors generated as output data of the training, and information about whether classes to which the first and second sentences belong are the same, and repeating the training in such a manner that the contrastive loss has a maximum value.

Abstract: An electronic apparatus for compressing a language model is provided, the electronic apparatus including a storage configured to store a language model which includes an embedding matrix and a softmax matrix generated by a recurrent neural network (RNN) training based on basic data including a plurality of sentences, and a processor configured to convert the embedding matrix into a product of a first projection matrix and a shared matrix, the product of the first projection matrix and the shared matrix having a same size as a size of the embedding matrix, and to convert a transposed matrix of the softmax matrix into a product of a second projection matrix and the shared matrix, the product of the second projection matrix and the shared matrix having a same size as a size of the transposed matrix of the softmax matrix, and to update elements of the first projection matrix, the second projection matrix and the shared matrix by performing the RNN training with respect to the first projection matrix, the second p

Abstract: Provided is a method to enable an image slideshow based on gaze of a user. The method displays an image to a user for viewing, wherein, invisible to the user, each image is divided into a grid of tiles. While the user is viewing the image, the method detects the gaze of the user to identify regions of the image that are of interest to the user. The identified regions of interest are mapped to the grid of tiles on the image, to recognize tiles of interest to the user. The tiles of interest for the image are calculated and another image is presented to the user for viewing when the number of tiles of interest exceeds a threshold value previously computed for the user.