The technology described herein is directed to a media indexer framework including a character recognition engine that automatically detects and groups instances (or occurrences) of characters in a multi-frame animated media file. More specifically, the character recognition engine automatically detects and groups the instances (or occurrences) of the characters in the multi-frame animated media file such that each group contains images associated with a single character. The character groups are then labeled and used to train an image classification model. Once trained, the image classification model can be applied to subsequent multi-frame animated media files to automatically classifying the animated characters included therein.

This specification describes a computer-implemented method for testing the performance of a video game server. The method comprises initializing a recurrent neural network. The recurrent neural network is trained based on requests sent from one or more client devices to the video game server. The initializing comprises inputting a start token into the recurrent neural network. An output distribution for a first-time step is generated, as an output of the recurrent neural network. The output distribution comprises a probability of generating each of a set of one or more requests to the video game server, in addition to a probability of generating a stop token. A first request from the set of one or more requests is selected based on the output distribution. The method comprises for one or more further time steps, until a stop token has been selected from output of the recurrent neural network: inputting, into the recurrent neural network, a request selected in the previous time step; generating, as an output of the recurrent neural network, an output distribution for the time step; and selecting, based on the output distribution, a request. A generated sequence of requests is stored. The generated sequence of requests comprises one or more of the requests selected at each respect time step. The generated sequence of requests is inputted into a test generator. A performance test for testing the performance of the video game server is generated by the test generator.

Automatic document classification using machine learning may involve receiving inputs that assign documents to classifiers, which define document classification rules for a classification model. The computing device may train the classification model using a machine learning technique that assigns each document of a second set of documents to destinations based on the document classification rules. The computing device may also receive a template design for each destination that specifies metadata to extract for a document type corresponding to documents assigned to the destination. The computing device may subsequently classifying a particular document using the classification model, which may involve assigning the particular document to a given destination of the plurality of destinations based on the document classification rules, and exporting metadata from the particular document using the template design associated with the given destination.

A method for testing a technical system. The method includes: tests are carried out with the aid of a simulation of the system, the tests are evaluated with respect to a fulfillment measure of a quantitative requirement on the system and an error measure of the simulation, on the basis of the fulfillment measure and error measure, a classification of the tests as either reliable or unreliable is carried out, and a test database is improved on the basis of the classification.

A network authentication system can be configured for sampling a plurality of signal samples from a device on a network, providing the plurality of signal samples to a first machine-learned model that is configured to determine a device fingerprint based at least in part on the plurality of signal samples, and providing the device fingerprint to a second machine-learned model that is configured to classify the device based at least in part on the device fingerprint.

An information processing apparatus comprising: a holding unit configured to hold a plurality of learning models for estimating geometric information based on an input image captured by an image capturing apparatus; a selection unit configured to calculate, for each of the learning models, an evaluation value that indicates suitability of the learning model to a scene of the input image, and select a learning model from the plurality of learning models based on the evaluation values; and an estimation unit configured to estimate first geometric information using the input image and the selected learning model.

Unsupervised or supervised machine learning (“ML”) techniques discussed herein can be used to classify browsers as one or more types of browser or within one or more browser groups. For example, a computer system configured to improve security of server computers interacting with client computers through an intermediary computer, and comprising: a memory comprising processor logic; one or more processors coupled to the memory, wherein the one or more processors execute the processor logic, which causes the one or more processors to: receive a first plurality of requests from a first plurality of browsers; generate a first plurality of request-feature vectors from the first plurality of requests; generate a plurality of browser groups based on the first plurality of request-feature vectors; receive a first new request from a first client computer; generate a first new request-feature vector based on the first new request; determine that the first new request-feature vector belongs to a first browser group among the plurality of browser groups; determine that the first browser group is associated with a first rule, and in response, respond to the first new request according to the first rule.

An image processing device includes an image processing unit that performs image processing on an observed image in which a cell is imaged and an image processing method selector that is configured to determine an observed image processing method for analyzing the imaged cell on the basis of information of a processed image obtained through image processing of the image processing unit.

A learning section (13) learns a classification criterion of a classifier at each time point using labeled learning data collected until a past prescribed time point and unlabeled learning data collected on and after the prescribed time point and learns a time-series change of the classification criterion. A classifier creation section (14) predicts a classification criterion of the classifier at an arbitrary time point including a future time point and certainty expressing the reliability of the classification criterion using the learned classification criterion and the time-series change. Thus, the classifier that outputs a label expressing an attribute of input data is created.

An occupant monitoring device includes processing circuitry to detect an eye of an occupant on a vehicle and to determine an eye opening degree of the eye using an image captured by an image capturing device having an automatic exposure adjusting function for adjusting an exposure time; to determine that the eye is closed when the eye opening degree of the eye is less than a predetermined eye opening degree threshold value; to deactivate the automatic exposure adjusting function when the automatic exposure adjusting function is active and the eye is determined to be closed; to detect brightness in a vicinity of the eye using an image which is captured by the image capturing device after the automatic exposure adjusting function is deactivated; and when the eye is determined to be closed, to determine that the occupant is in a drowsy state when the brightness in the vicinity of the eye is less than a predetermined brightness threshold value, and to determine that the occupant is in an awake state when the brightness is equal to or greater than the predetermined brightness threshold value.