An apparatus and a method use a convolutional neural network (CNN) including a plurality of convolution layers in the field of artificial intelligence (AI) systems and applications thereof. A computing apparatus using a CNN including a plurality of convolution layers includes a memory storing one or more instructions; and one or more processors configured to execute the one or more instructions stored in the memory to obtain input data; identify a filter for performing a convolution operation with respect to the input data, on one of the plurality of convolution layers; identify a plurality of sub-filters corresponding to different filtering regions within the filter; provide a plurality of feature maps based on the plurality of sub-filters; and obtain output data, based on the plurality of feature maps.

Dual machine translators are trained by generating a translated medical image by operation of an illustrative model on an original medical record, generating information based on whether the translated medical image is natural in a modality of medical imaging, producing a back-translated medical record by operation of an interpretive model on the translated medical image, calculating a reward by comparing the back-translated medical record to the original medical record, updating parameters of the illustrative model in response to the information and the reward, and updating parameters of the interpretive model in response to the reward.

Dual machine translators are trained by generating a translated medical image by operation of an illustrative model on an original medical record, generating information based on whether the translated medical image is natural in a modality of medical imaging, producing a back-translated medical record by operation of an interpretive model on the translated medical image, calculating a reward by comparing the back-translated medical record to the original medical record, updating parameters of the illustrative model in response to the information and the reward, and updating parameters of the interpretive model in response to the reward.

Recommender systems often rely on models which are trained to maximize accuracy in predicting user preferences. When the systems are deployed, these models determine the availability of content and information to different users. The gap between these objectives gives rise to a potential for unintended consequences, contributing to phenomena such as filter bubbles and polarization. An analysis of information availability through the lens of user recourse includes a computationally efficient audit for top-N matrix factorization recommender models and may be used for adapting recommender modules to meet targets for model performance parameters within defined contexts.

A bi-directional spatial-temporal transformer neural network (BDSTT) is trained to predict original coordinates of a skeletal joint in a specific frame through relative relationships of the skeletal joint to other joints and to the state of the skeletal joint in other frames. Obtain a plurality of frames comprising coordinates of the skeletal joint and coordinates of other joints. Produce a spatially masked frame by masking the original coordinates of the skeletal joint. Provide the specific frame, the spatially masked frame, and at least one more frame to a coordinate prediction head of the BDSTT. Obtain, from the coordinate prediction head, a prediction of coordinates for the skeletal joint. Adjust parameters of the BDSTT until a mean-squared error, between the prediction of coordinates for the skeletal joint and the original coordinates of the skeletal joint, converges.

A non-transitory computer-readable recording medium stores therein a learning data selection program that causes a computer to execute a process including: extracting a first input data group relating to first input data in correspondence with designation of the first input data included in an input data group input to a machine learning model, the machine learning model classifying or determining transformed data that is transformed from input data; acquiring a first transformed data group of the machine learning model and a first output data group of the machine learning model, respectively, the first transformed data group being input to the machine learning model and corresponding to the first input data group, the first output data group corresponding to the first transformed data group; and selecting learning target data of an estimation model from the first input data group.

A data processing method includes: a data preparing step of preparing actual data of a three-dimensional chromatogram including a chromatogram and a spectrum acquired by chromatography analysis for a sample containing a plurality of components, and spectral data for the plurality of components in the sample whose peaks overlap each other on the chromatogram of the actual data; a similarity calculating step of calculating, for each wavelength region, a similarity between wavelength regions corresponding to each other in the spectral data for the plurality of components prepared in the data preparing step while comprehensively changing the wavelength regions; a target range setting step of setting a target range by searching for a wavelength region having a similarity lower than an overall similarity between the spectral data for the plurality of components based on a calculation result in the similarity calculating step; and a peak separating step of creating chromatogram data for the plurality of components by performing, using the spectral data for the plurality of components, matrix decomposition of the actual data in the target range set in the target range setting step.

A data processing method includes: a data preparing step of preparing actual data of a three-dimensional chromatogram including a chromatogram and a spectrum acquired by chromatography analysis for a sample containing a plurality of components, and spectral data for the plurality of components in the sample whose peaks overlap each other on the chromatogram of the actual data; a similarity calculating step of calculating, for each wavelength region, a similarity between wavelength regions corresponding to each other in the spectral data for the plurality of components prepared in the data preparing step while comprehensively changing the wavelength regions; a target range setting step of setting a target range by searching for a wavelength region having a similarity lower than an overall similarity between the spectral data for the plurality of components based on a calculation result in the similarity calculating step; and a peak separating step of creating chromatogram data for the plurality of components by performing, using the spectral data for the plurality of components, matrix decomposition of the actual data in the target range set in the target range setting step.

Low-dimensional feature values with which semantic factors of content are ascertained are generated from relevance between sets of two types of content. Based on a relation indicator indicating a pair of groups indicating which groups are related to first types of content groups among second types of content groups, an initial feature value extracting unit 11 extracts initial feature values of the first type of content and the second type of content. A content pair selecting unit 12 selects a content pair by selecting one first type of content and one second type of content from each pair of groups indicated by the relation indicator. A feature value conversion function generating unit 13 generates feature conversion functions 31 of converting the initial feature values into low-dimensional feature values based on the content pair selected from each pair of groups.

A computing system can include an embedding model and a clustering model. The computing system input each of the plurality of inputs into the embedding model and receiving respective embeddings for the plurality of inputs as outputs of the embedding model. The computing system can input the respective embeddings for the plurality of inputs into the clustering model and receiving respective cluster assignments for the plurality of inputs as outputs of the clustering model. The computing system can evaluate a clustering loss function that evaluates a first average, across the plurality of inputs, of a respective first entropy of each respective probability distribution; and a second entropy of a second average of the probability distributions for the plurality of inputs. The computing system can modify parameter(s) of one or both of the clustering model and the embedding model based on the clustering loss function.