The presently disclosed subject matter includes a computerized method and system that provide the ability to train and execute a unique machine learning (ML) model specifically configured to enhance classifier (e.g., RegEx) output by identifying and removing false positive results from the classifiers output. Classifier output, comprising a collection of data-subsets (e.g., columns in a relational database) of one or more structured or semi-structured data sources (e.g., tables of a relational database), are transformed to be represented by a plurality of numerical vectors. The numerical vectors are used during a training phase (as well as the execution phase) for training a machine learning model to enhance the classifier output and reduce false positives.

A system for decision support includes a path unit for determining a determined path through a decision tree that leads to a determined recommendation node including a determined recommendation. The decision tree comprises condition nodes and recommendation nodes, wherein a condition node comprises a condition associated with a particular branch of the decision tree. A recommendation node comprises a recommendation associated with the one or more conditions of the one or more condition nodes on a path towards the recommendation node. The path unit is arranged for taking into account the conditions of the condition nodes along the path by applying the conditions to a set of parameters. The system comprises an explanation unit for generating an explanation of a reason for the determined recommendation based on at least one of the condition nodes on the path that leads to the recommendation node.

Systems and methods are described for linking records from different databases. A search may be performed for each record of a received record set for similar records based on having similar field values. Recommended records of the record set may be assigned with the identified similar records to sub-groups. Pairs of records may be formed for each record of the sub-group, and comparative and identifying features may be extracted from each field of the pairs of records. Then, a trained model may be applied to the differences to determine a similarity score. Cluster identifiers may be applied to records within each sub-group having similarity scores greater than a predetermined threshold. In response to a query for a requested record, all records having the same cluster identifier may be output on a graphical interface, allowing users to observe linked records for a person in the different databases.

Methods and system for privacy preserving information exchange in a network of electronic devices are disclosed. In one embodiment, a method is implemented in an electronic device to serve as a local party for information exchange between the local party and another electronic device to serve as an aggregator. The method includes storing a plurality of values in a 2D vector, where a first dimension of the 2D vector is based on the number of values, and where each position in the first dimension has one unique value. The method further includes transmitting the 2D vector to the aggregator with masking for the aggregator to prevent the aggregator from decoding the 2D vector, where aggregating the masked 2D vector with masked 2D vectors from other local parties allows decoding of the aggregated 2D vector.

A method of performing a reshape operation specified in a reshape layer of a neural network model is described. The reshape operation reshapes an input tensor with an input tensor shape to an output tensor with an output tensor shape. The tensor data that has to be reshaped is directly routed between tile memories of the hardware accelerator in an efficient manner. This advantageously optimizes usage of memory space and allows any number and type of neural network models to be run on the hardware accelerator.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for presenting a new machine learning model architecture. In some aspects, the methods include obtaining a training dataset with a plurality of training samples that includes feature variables and output variables. A first matrix is generated using the training dataset which is a sparse representation of the training dataset. Generating the first matrix can include generating a categorical representation of numeric features and an encoded representation of the categorical features. The methods further include generating a second, third and a fourth matrix. Each feature of the first matrix is then represented using a vector that includes a multiple adjustable parameters. The machine learning model can learn by adjusting values of the adjustable parameters using a combination of a loss function the fourth matrix, and the first matrix.

An information processing device includes an acquisition unit (551) that acquires information related to a communication environment, and a determination unit (552) that determines a mode to be used on the basis of the information related to the communication environment among a first mode of determining a communication parameter on the basis of a measurement result using a reference signal, a second mode of determining the communication parameter on the basis of a learning result of machine learning using known information related to communication, and a third mode of determining the communication parameter according to the first mode and/or the second mode.

A system and method for generating libraries of chemical compounds having desired and specific properties by formulating a reaction-based mechanism that may be powered by several algorithms including but not limited to genetic algorithm, expert iteration algorithms, planning methods, reinforcement learning and machine learning algorithms. The system and method may also provide the process steps by which these optimized products S′ may be synthesized from the reactants R1,R2 and further enables a rapid and efficient search of the synthetically accessible chemical space.

Systems and methods for automatically analyzing spectral power measurements to identify abnormalities. The systems and methods may receive measurements comprising RF power measured over a contiguous range of frequencies, where at least a first portion of the contiguous range is used to transmit signals and at least a second portion of the contiguous range is unused. Respective boundaries of the unused portions may be identified and infilled to provide modified measurements. The modified measurements may be automatically analyzed to identify the abnormalities.

Apparatuses, systems, and techniques to detect loops in neural network graphs. In at least one embodiment, one or more loops are detected within one or more graphs corresponding to one or more neural networks.