A method for generating a predictive model for quantization parameters of a neural network is described. The method comprises accessing a first vector of data values corresponding to input values to a first layer implemented in a neural network, generating a feature vector of one or more features extracted from the data values of the first vector, accessing a second vector of data values corresponding to the input values of a second layer implemented in the neural network, subsequent to the first layer, generating a target vector of data values comprising one or more quantization parameters for the second layer, from the data values of the second vector, evaluating, on the basis of the feature vector and the target vector, a predictive model for predicting the one or more quantization parameters of the second layer and modifying the predictive model on the basis of the evaluation.

A computer-implemented method for evaluating an image classifier, in which a classifier output of the image classifier is provided for the actuation of an at least semi-autonomous robot. The evaluation method includes: ascertaining a first dataset including image data and annotations being assigned to the image data, the annotations including information about the scene imaged in the respective image and/or about image regions to be classified and/or about movement information of the robot; ascertaining regions of the scenes that are reachable by the robot based on the annotations; ascertaining relevance values for image regions to be classified by the image classifier; classifying the image data of the first image dataset with the aid of the image classifier; evaluating the image classifier based on image regions correctly classified by the image classifier and incorrectly classified image regions, as well as the calculated relevance values of the corresponding image regions.

A model compression device includes a compression unit and a determination unit. The compression unit is configured to create a compression model arrived at by compressing a first prediction model created by machine learning. The determination unit is configured to determine whether or not a second prediction model created by re-learning the compression model can be further compressed on the basis of an index related to the performance of the second prediction model.

A method may include generating views materializing tensors generated by a convolutional neural network operating on an image. Determining the outputs of the convolutional neural network operating on the image with a patch occluding various portions of the image. The outputs being determined by generating queries on the views that performs, based at least on the changes associated with occluding different portions of the image, partial re-computations of the views. A heatmap may be generated based on the outputs of the convolutional neural network. The heatmap may indicate the quantities to which the different portions of the image contribute to the output of the convolutional neural network operating on the image. Related systems and articles of manufacture, including computer program products, are also provided.

A learning data generation device includes processing circuitry to extract a cause expression and a result expression from an input text, and to generate a modified text by at least one of a method of interchanging the cause expression and the result expression and a method of specifying one of the cause expression and the result expression as a modification target sentence and replacing the modification target sentence with a replacement candidate sentence dissimilar to the modification target sentence.

A data labeling processing method and apparatus, an electronic device, and a medium are provided. A method includes: determining an item feature of an item to be labeled and a resource feature of a labeling end to be matched; determining a co-occurrence feature for the item to be labeled and the labeling end to be matched; obtaining a classification result based on the item feature, the resource feature, and the co-occurrence feature, wherein the classification result indicates whether the labeling end to be matched is matched with the item to be labeled; and sending the item to be labeled to the labeling end to be matched based on the classification result.

The need for an accurate, early, and precise estimation of expected delivery date (EDD) for the pregnant subject is vital. A system and method for predicting a day/date of delivery for a pregnant subject using one or more microbiome samples collected from the pregnant subject is provided. The disclosure relates to applying machine learning techniques on the microbiome characterization data corresponding to the biological sample(s) collected from the pregnant subject. The method further comprises using the predicted EDD to suitably plan and take required medical treatment or precautions or medical advice for the pregnant subject to prevent any pregnancy and/or delivery related complications and to manage the delivery appropriately. The disclosure also provides compositions of the microbiome data which can potentially influence the delivery date, or the method provides exemplary compositions of the microbiome data which plays vital role in estimating the EDD of the pregnant subject.

Systems and methods for enhancing trainable optical character recognition (OCR) performance are disclosed herein. An example method includes receiving, at an application executing on a user computing device communicatively coupled to a machine vision camera, an image captured by the machine vision camera, the image including an indicia encoding a payload and a character string. The example method also includes identifying the indicia and the character string; decoding the indicia to determine the payload; and applying an optical character recognition (OCR) algorithm to the image to interpret the character string and identify an unrecognized character within the character string. The example method also includes comparing the payload to the character string to validate the unrecognized character as corresponding to a known character included within the payload; and responsive to validating the unrecognized character, adding the unrecognized character to a font library referenced by the OCR algorithm.

A device, computer program and computer-implemented method for machine learning. The method comprises providing a task comprising an action space of a multi-armed bandit problem or a contextual bandit problem and a distribution over rewards that is conditioned on actions, providing a hyperprior, wherein the hyperprior is a distribution over the action space, determining, depending on the hyperprior, a hyperposterior for that a lower bound for an expected reward on future bandit tasks has as large a value as possible, when using priors sampled from the hyperposterior, and wherein the hyperposterior is a distribution over the action space.

A computer system (which may include one or more computers) that chooses or selects one or more criteria for when to terminate training of a neural network is described. During operation, the computer system may choose or select the one or more criteria for when to terminate the training of the neural network, where the one or more criteria are based at least in part on a measure corresponding to a local geometry of a loss landscape at or proximate to a current location in the loss landscape. Note that one of the one or more criteria may include: a trace of a Hessian matrix associated with a loss function dropping below a threshold, or a ratio between an operator norm of the Hessian matrix and a curvature of the loss function at the current location in the loss landscape reaching a second threshold.