Apparatuses and methods in a communication system are disclosed. In a network element, an encoder module obtains as an input network data that is representative of the current condition of the communications network, the network data comprising a plurality of values indicative of the performance of network elements and performs (800) feature reduction providing at its output a set of activations. A clustering module performs (802) batch normalisation and an amplitude limitation to the output of the encoder module to obtain normalised activations. A clustering control module calculates a projection of the normalised activations and determines (804) a clustering loss. A decoder module calculates (806) a reconstruction loss. The network element backpropagates the reconstruction loss and the clustering loss through the modules.

When conducting imaging mass analysis for a region to be measured on a sample, an individual reference value calculating part obtains a maximum value in P.sub.i/I.sub.i of respective measuring points, and stores the value together with measured data as an individual reference value. When performing comparison analysis for a plurality of the data obtained from different samples, a common reference value determining part reads out corresponding a plurality of the individual reference values and determines a minimum value as a common reference value Fmin. A normalization calculation processing part normalizes the respective intensity values by multiplying the intensity values read out from an external memory device by a normalization coefficient long_Max(Fmin/P.sub.i) obtained from the common reference value Fmin, TIC values Pi at the respective measuring points, and a maximum allowable value long_Max of a variable storing the intensity values at the time of operation.

A highly versatile data processing is implemented on data collected in a manufacturing process. A data processing device includes: a calculation part configured to collect a plurality of data groups associated with a predetermined step of a process, and calculate effects in the predetermined step for each of the plurality of data groups; a dividing part configured to divide a feature space such that a distribution of each of the plurality of data groups associated with the predetermined step in the feature space is classified for each of the calculated effects; and an output part configured to output specific data that specifies respective regions of the divided feature space.

A system and method for identifying line Mura defects on a display. The system is configured to generate a filtered image by preprocessing an input image of a display using at least one filter. The system then identifies line Mura candidates by converting the filtered image to a binary image, counting line components along a slope in the binary image, and marking a potential candidate location when the line components along the slope exceed a line threshold. Image patches are then generated with the candidate locations at the center of each image patch. The image patches are then classified using a machine learning classifier.

In some implementations, a dataset evaluation system may receive a target dataset. The dataset evaluation system may-processing the target dataset to generate a normalized target dataset. The dataset evaluation system may process the normalized target dataset with an intruder dataset to identify whether any quasi-identifiers are present in the normalized target dataset. The dataset evaluation system may determine a Cartesian product of the normalized target dataset and the intruder dataset. The dataset evaluation system may compute, using a distance linkage disclosure technique, an inference risk score for the target dataset with the intruder dataset based on the Cartesian product and whether any quasi-identifiers are present in the normalized target dataset. The dataset evaluation system may output information associated with the inference risk score.

In some implementations, a dataset evaluation system may receive a target dataset. The dataset evaluation system may-processing the target dataset to generate a normalized target dataset. The dataset evaluation system may process the normalized target dataset with an intruder dataset to identify whether any quasi-identifiers are present in the normalized target dataset. The dataset evaluation system may determine a Cartesian product of the normalized target dataset and the intruder dataset. The dataset evaluation system may compute, using a distance linkage disclosure technique, an inference risk score for the target dataset with the intruder dataset based on the Cartesian product and whether any quasi-identifiers are present in the normalized target dataset. The dataset evaluation system may output information associated with the inference risk score.

Aspects of the invention include detecting an error alert from a target computer system. In response to detecting the error alert, performance data is then retrieved from the target computer system. A gated recurrent unit (GRU) neural network is used to generate a prediction of a root cause of the error alert based on the performance data. The weights of a reset gate of the GRU neural network are adjusted based on received feedback of the prediction.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing a neural network. In one aspect, the neural network includes a batch renormalization layer between a first neural network layer and a second neural network layer. The first neural network layer generates first layer outputs having multiple components. The batch renormalization layer is configured to, during training of the neural network on a current batch of training examples, obtain respective current moving normalization statistics for each of the multiple components and determine respective affine transform parameters for each of the multiple components from the current moving normalization statistics. The batch renormalization layer receives a respective first layer output for each training example in the current batch and applies the affine transform to each component of a normalized layer output to generate a renormalized layer output for the training example.

Provided is a method for developing a geographic agnostic machine learning model. The method may include selecting transaction data associated with payment transactions conducted by a first plurality of users, wherein the transaction data includes first transaction data associated with payment transactions conducted by a first plurality of users in a first geographic area and second transaction data associated with payment transactions conducted by a second plurality of users in a second geographic area, formatting the first transaction data associated with payment transactions conducted by the first plurality of users in the first geographic area and the second transaction data associated with payment transactions conducted by the second plurality of users in the second geographic area to provide training data, and generating the geographic agnostic machine learning model using the training data. A system and computer program product are also disclosed.

Disclosed are systems and methods for data mining a plurality of records to identify one or more patterns. A list of frequent items is generated using the records of a certain subpopulation in a dataset of the records. By scanning through the dataset, a prefix tree is generated based on the list of frequent items. Each node in the prefix tree includes an accumulator which maintains separate counts of records from the subpopulation matching the respective node and of records from the plurality of records matching the respective node. One or more population-normalized frequent patterns associated with the plurality of records are extracted based on a traversal of the prefix tree.