Abstract: The method comprises, for a given route between a starting point and a destination, and for an arrival at the destination at a given desired time: a preliminary step of determining and recording a plurality of vehicle mission profiles, at least a first instant during the journey, a step of determining an instantaneous position of the vehicle at this first instant and a desired time remaining to reach the destination, a step of identifying, among the mission profiles, the mission profile(s) whose curves are closest to the desired time remaining at the instantaneous position of the vehicle, and a step of determining new driving parameters to follow a new mission profile, the new mission profile being determined on the basis of the determined mission profiles.

Abstract: Methods, apparatus, and processor-readable storage media for automated issue detection and remediation across multiple user systems using healing-as-a-service techniques are provided herein. An example computer-implemented method includes obtaining system configuration data from at least a portion of multiple user systems within a network; obtaining an alert pertaining to an issue attributed to a first of the user systems; training a machine learning model related to user system issue detection using at least a portion of the system configuration data and data related to the alert; determining user system configuration adjustments related to remedying at least a portion of the issue, by processing the data related to the alert using the trained machine learning model; automatically performing the user system configuration adjustments in connection with the first user system; and sharing, using at least one healing-as-a-service component, the trained machine learning model with the user systems in the network.

Abstract: A mutation detection apparatus includes a memory configured to store software for implementing a neural network and a processor configured to detect a mutation by executing the software, wherein the processor is configured to generate first genome data extracted from a target tissue and second genome data extracted from a normal tissue, extract image data by preprocessing the first genome data and the second genome data, and detect a mutation of the target tissue on the basis of the image data through the neural network trained to correct a sequencing platform-specific false positive.

Abstract: Techniques for machine and deep learning process modeling of performance and behavioral data are described, including receiving objective performance data, including an induction document, and raw performance data, validating the raw performance data, determining whether incumbent data is sufficient to build a model, building a model to generate an output performance dataset, evaluating a behavioral dataset generated using behavioral attributes determined from a survey, identifying a candidate file using the model, the model being identified as a model candidate, and evaluating the model candidate against one or more other model candidates using one or more exit criteria to determine whether the model candidate, relative to the one or more other model candidates, is used to identify a release candidate.

Abstract: A method of improving quality of crowdsourced affective data based on agreement relationship between a plurality of annotators include receiving, by a processor, a collection of stimuli previously given affective labels by the plurality of annotators, executing, by a processor, an algorithm operative to perform the steps including constructing an agreement multigraph as a probabilistic model including a pair-wise status of agreement between the affective labels given by different ones of the plurality of annotators, learning the probabilistic model computationally using the crowdsourced affective data, identifying a reliability of each of the plurality of annotators based on the learned model, and adjusting the crowdsourced affective data by calculating the affective labels of each stimuli based on the identified reliability of each of the plurality of annotators, thereby improving the quality of the crowdsourced affective data.

Abstract: Methods and software that allow one or more users to utilize targeted-advertising functionality in the context of a product program. For example, such logistical functionality may enable users to benefit from the use of one or more functionalities enabled by targeted advertising, such as fully or partially ad-sponsored software, relevant training or assistance recommendations, and user-customized advertising, among others. Various corresponding and related methods and software are described.

Abstract: A method for electronic logging of carrier data is described. The logged electronic carrier data is utilized to predict a likelihood of occurrence of a potential impending compliance rule violation. A plurality of travel conditions capable of changing a transit period, such as weather, traffic, and construction are monitored, aggregated, and used to determine a predicted likelihood of changing the transit period. The likelihood of occurrence of a compliance rule violation is determined, based on the aggregated values, the predicted likelihood of changing the transit period, and a group of compliance rules. An indicator of the likelihood of occurrence of a compliance rule violation may be generated, and presented to any number of electronic devices. Remedial actions to avoid or mitigate the compliance rule violation may be suggested.

Abstract: To provide search capabilities in a process control system, a contextual knowledge repository is generated that organizes process plant-related data according to semantic relations between the process plant-related data and the process plant entities. When a user submits a process plant search query related to process plant entities within a process plant, search results are obtained by identifying a data set from the contextual knowledge repository which is responsive to the process plant search query. The search results are then presented on a user interface device based on the identified data set. To allow for searches to be performed by user interface devices external to the process plant, a data diode is disposed between a field-facing component and an edge-facing component of the process plant so that data flows from the field-facing component to the edge-facing component without flowing from the edge-facing component to the field-facing component.

Abstract: The present disclosure relates to a method for determining the working life of a traction battery of a boat, including the steps of determining a system configuration and/or operating conditions of the boat, providing a traction battery model, which states an ageing condition of the traction battery as time progresses depending on the system configuration and/or operating conditions determining at least one condition that confirms the end-of-life condition of the traction battery has been reached and calculating the time-period until the end-of-life condition is reached on the basis of the traction battery model.

Abstract: A quantum-mechanics station (?-station) and a cloud-based server cooperate to provide quantum mechanics as a service (?aaS) including real-time, exclusive, interactive sessions. The ?-station serves as a system for implementing “recipes” for producing, manipulating, and/or using quantum-state carriers, e.g., rubidium 87 atoms. The cloud-based server acts as an interface between the station (or stations) and authorized users of account holders. To this end, the server hosts an account manager and a session manager. The account manager manages accounts and associated account-based and user-specific permissions that define what actions any given authorized user for an account may perform with respect to a ?-station. The session manager controls (e.g., in real-time) interactions between a user and a ?-station, some interactions allowing a user to select a recipe based on wavefunction characterizations returned earlier in the same session.

Abstract: The present disclosure describes systems, non-transitory computer-readable media, and methods for utilizing hash partitions to determine local densities and distances among users (or among other represented data points) for clustering sparse data into segments. For instance, the disclosed systems can generate hash signatures for users in a sparse dataset and can map users to hash partitions based on the hash signatures. The disclosed systems can further determine local densities and separation distances for particular users (or other represented data points) within the hash partitions. Upon determining local densities and separation distances for datapoints from the dataset, the disclosed systems can select a segment (or cluster of data points) grouped according to a hierarchy of a clustering algorithm, such as a density-peaks-clustering algorithm.

Abstract: Apparatuses, systems, and techniques to optimize kernel selection for performing a computation. In at least one embodiment, a neural network is trained and utilized to generate a list of kernels so that an (e.g., optimal) kernel may be identified. The neural network receives characteristics of the input matrices and determines relevancy scores for a list of possible kernels. Based on an ordered listing of kernels by relevant score, a kernel is selected from the list and utilized to perform the computation and provide the result.

Abstract: A database system comprised of a decoupled compute layer and storage layer is implemented to store, build, and maintain a canonical dataset, a temporary buffer, and projection datasets. The canonical dataset is a set of batch updated data. The data is appended in chunks to the canonical dataset such that the canonical dataset becomes a historical dataset over time. The buffer is a write ahead log that contains the most recent chunks of data and provides atomicity and durability for the database system. The projection datasets are indexes of the canonical dataset and/or the buffer that may have single or multiple column sort-orders and/or particular data formats. The writes to the canonical dataset, projection datasets, and buffer may be asynchronous and therefore the database system is advantageously less resource constrained.

Abstract: A cognitive assignment engine (CAE) system attempts to infer semantic meaning from textual content of an incoming message in order to use the inferred meaning to assign the message to an appropriate responder. If the message contains insufficient textual content, the system identifies ontological structures comprised by the message's graphical content and classifies each structure as a function of the structure's location within the graphical content or of an intrinsic characteristic of the structure. The system then generates a message identifier by performing a computation on these classifications and uses the identifier to retrieve a previously stored graphical template that comprises ontological structures similar to those of the incoming message. The system associates the incoming message with a semantic meaning previously associated with the template, enabling the system to classify the message and to assign the message to the correct responder.

Abstract: During a query compilation process, a query is received that is directed to a set of source tables, each source table from the set of source tables being organized into at least one micro-partition and the query including at least one pruning operation. During the query compilation process, a modification of the query is performed for adjusting the at least one pruning operation, the modification being based on a set of statistics collected for previous pruning operations on at least a portion of the set of source tables and a set of heuristics, the set of statistics indicating at least an amount of execution time for each previous query associated with each of the previous pruning operations. The query is compiled including the modification of the query. The compiled query is provided to an execution node of a database system for execution.

Abstract: Methods and systems for generating a universal computer model for assessing a risk in an electronic transaction based on one or more risk assessment models are presented. The one or more risk assessment models may be incompatible with each other. Different portions of a risk assessment models may be extracted from the risk assessment models. A node structure is generated for each risk assessment model based on the portions extracted from a corresponding risk assessment model. The node structures generated based on the risk assessment models are merged to produce a merged node structure. The universal computer model is generated based on the merged node structure.

Abstract: In one embodiment, a method includes receiving a user input comprising a natural-language utterance by an assistant xbot from a client system associated with a user, determining a semantic representation of the user input based on a structural ontology defining a labeling syntax for parsing the natural-language utterance to semantic units comprising actions, objects, and attributes, wherein the semantic representation embeds at least one object within at least one action and declares at least one attribute of the embedded object to be acted upon, sending a request based on the semantic representation to an agent for executing a task corresponding to the user input, receiving results of the executed task mapped to a structure determined by the structural ontology from the agent, and sending from the assistant xbot to the client system instructions for presenting a response based on the results of the executed task.

Abstract: A system and method for optimizing the latent space in generative machine learning models, and applications of the optimizations for use in the de novo generation of molecules for both ligand-based and pocket-based generation. The ligand-based optimizations comprise a tunable reward system based on a multi-property model and further define new measurable metrics: molecular novelty and uniqueness. The pocket-based optimizations comprise an initial multi-property optimization followed up by either a seed-based optimization or a relaxed-based optimization.

Abstract: An information processing device includes: a plurality of identifiers that discriminates whether abnormal data that is information indicating an abnormal value is included in treatment data and detects the abnormal data; and a hardware processor that: customizes evaluation data used when evaluating discrimination accuracy of the plurality of identifiers; calculates the discrimination accuracy of each of the plurality of identifiers using the evaluation data customized by the hardware processor; and selects one identifier out of the plurality of identifiers as an identifier used for discrimination based on a calculation result by the hardware processor.

Abstract: This application relates to apparatus and methods for identifying fraudulent transactions. A computing device receives return data identifying the return of at least one item. The computing device obtains modified strategy data identifying at least one rule of a modified strategy. The rule may be based on the application of at least one discrete stochastic gradient descent algorithm to an initial strategy. The computing device applies the modified strategy to the received return data identifying the return of the at least one item, and determines whether the return of the at least one item is fraudulent based on the application of the modified strategy. The computing device generates fraud data identifying whether the return of the at least one item is fraudulent based on the determination, and may transmit the fraud data to another computing device to indicate whether the return is fraudulent.

Abstract: The invention relates to a method and apparatus for monitoring the condition of subsystems within a renewable generation plant or microgrid which are using Supervisory Control and Data Acquisition (SCADA) systems for allowing plant operators to monitor and interact with a plant via human machine interfaces.

Abstract: Described herein are systems and methods for predicting whether an entity associated with a profile in one network is the same entity that is associated with a profile in a second network, which networks may represent networks from different network services or may represent networks from the same network service. In embodiments, network graph features, including nodes and connections, may be used to predict a probability that the profiles in the two networks should be matched. In embodiments, additional or different factors may be included in the predicted probability, such as homophily, match probabilities of seed nodes, match probabilities of attribute-matched nodes, attribute-attribute co-occurrence probabilities, and the like.

Abstract: Techniques are disclosed for improved autonomous agents that can provide a recommendation in a non-intrusive, conversational manner. In an aspect, a method determines a first sentiment score for a first utterance and a second sentiment score for a second utterance, each sentiment score indicating an emotion indicated by the respective utterance. The method further identifies that a difference between the first sentiment score and the second sentiment score is greater than a threshold. The method further extracts a noun phrase from the second utterance. The method identifies a text fragment that includes an entity that corresponds to the noun phrase. The method identifies that the text fragment addresses a claim of the second utterance. The method forms a third utterance that includes the a recommendation related to the second utterance and adds the third utterance to the sequence of utterances after the second utterance.

Abstract: An apparatus includes at least one memory configured to store a virtualization associated with a programming and test platform and a munition. The virtualization includes a virtual machine containing first software or firmware instructions associated with the programming and test platform and second software or firmware instructions that control behavior of the programming and test platform relative to the munition. The virtualization also includes a virtual representation of the munition. The virtualization further includes one or more virtual communication channels configured to communicatively couple the virtual machine and the virtual representation of the munition. The apparatus also includes at least one processor configured to execute the virtualization and simulate the programming and test platform and the munition on the apparatus.

Abstract: This disclosure provides a method, apparatus and computer program product to create a full homomorphic encryption (FHE)-friendly machine learning model. The approach herein leverages a knowledge distillation framework wherein the FHE-friendly (student) ML model closely mimics the predictions of a more complex (teacher) model, wherein the teacher model is one that, relative to the student model, is more complex and that is pre-trained on large datasets. In the approach herein, the distillation framework uses the more complex teacher model to facilitate training of the FHE-friendly model, but using synthetically-generated training data in lieu of the original datasets used to train the teacher.

Abstract: Embodiments of the present disclosure provide a method for solving a problem, a computing system and a program product. A method for solving a problem includes determining information related to a to-be-solved problem; acquiring, based on the information, knowledge elements that can be used for the to-be-solved problem from a knowledge repository, the knowledge repository storing: solved problems, at least one executable task related to the solved problems, at least one processing flow for implementing the at least one executable task, and a corresponding function module included in the at least one processing flow; and determining, based at least on the acquired knowledge elements, a solution to the to-be-solved problem. By such arrangements, automatic problem solving can be achieved in a faster, simpler way with a lower cost through division of the repository and the knowledge elements.

Abstract: The present invention is systems and methods of self-administering protocols on a blockchain platform. A system and method of self-administered protocols on a blockchain platform, comprising: self-administering one or more of the following actions: consensus, governance, self-forking, view change or finality of transactions on the blockchain platform; operating without a hierarchical structure to make decisions; validating the decision to avoid rogue decisions or attacks; setting of a time period to lapse to finalize the decision; allowing the set time period to lapse; finalizing the decision by saving the state on the blockchain platform. Self-administering also includes the capability of the blockchain platform to prune the state of the smart contracts and the global state of the blockchain platform.

Abstract: Systems and methods are described that employ machine learning models to optimize database management. Machine learning models may be utilized to decide whether a new database record needs to be created (e.g., to avoid duplicates) and to decide what record to create. For example, candidate database records potentially matching a received database record may be identified in a local database, and a respective probability of each candidate database record matching the received record is output by a match machine learning model. A list of statistical scores is generated based on the respective probabilities and is input to an in-database machine learning model to calculate the probability that the received database record already exists in the local database.

Abstract: There is disclosed a method and system for identifying relevant training data points for a prediction by a machine learning algorithm (MLA). The method comprises determining indicators of influence for training data points used to train the MLA. A normalizing function is applied to the indicators of influence to determine normalized indicators of influence. Training data points having the highest and lowest normalized indicators of influence are output for display.

Abstract: A system includes a data collection engine, a plurality of items including radio-frequency identification chips, a plurality of third party data and insight sources, a plurality of interfaces, client devices, a server and method thereof for preventing suicide. The server includes trained machine learning models, business logic and attributes of a plurality of patient events. The data collection engine sends attributes of new patient events to the server. The server can predict an adverse event risk of the new patient events based upon the attributes of the new patient events utilizing the trained machine learning models.

Abstract: A device that is configured to assign users to an issue cluster based on issue types for the users. The device is further configured to identify available agents and to assign each available agent to one or more knowledge area clusters based on knowledge scores. A knowledge score indicates an expertise level for an agent in a knowledge area. The device is further configured to identify an issue cluster that is associated with an issue type and to identify a user from the issue cluster. The device is further configured to identify a knowledge area cluster that is associated with the issue type and to identify an agent from the knowledge area cluster. The device is further configured to establish a network connection between a user device associated with the user and a user device associated with the agent.

Abstract: The present invention is directed to a brand value growthand retention system for brand drugs commercialized by brand drug advertisers through a brand drug's lifecycle during patent exclusivity and after loss of exclusivity. The brand value growth and retention system iteratively analyzes combined computational models of consumer, healthcare provider retailer and payor segment data to produce brand drug promotional campaigns that are predictive with modifying parameters that transform the promotional campaigns over time. As a result, the brand drug promotional campaign generates an increased number of brand drug purchases while predicting the pointwhere incremental promotional campaign investments produce a diminishing number of incremental brand drug purchases.

Abstract: Pre-computed query results stored at a database server are re-computed by a computation machine. The pre-computed query results are composed of a plurality of shares. Each share includes a certain number of pre-computed query results. The computation resources of the computation machine needed to re-compute a pre-computed query result of a first share depend on whether or not other pre-computed query results of the first share are re-computed during a given time interval forming a current re-computation cycle. The computation machine receives a request to re-compute pre-computed query results of at least a first share, determines a number of pre-computed query results in the first share to be re-computed in the current re-computation cycle based on a Reinforcement Learning algorithm, and re-computes the determined number of pre-computed query results in the first share.

Abstract: A hybrid computing system for solving a computational problem includes a digital processor, a quantum processor having qubits and coupling devices that together define a working graph of the quantum processor, and at least one nontransitory processor-readable medium communicatively coupleable to the digital processor which stores at least one of processor-executable instructions or data. The digital processor receives a computational problem, and programs the quantum processor with a first set of bias fields and a first set of coupling strengths. The quantum processor generates samples as potential solutions to an approximation of the problem. The digital processor updates the approximation by determining a second set of bias fields based at least in part on the first set of bias fields and a first set of mean fields that are based at least in part on the first set of samples and coupling strengths of one or more virtual coupling devices.

Abstract: A device for calculating a therapeutic remedy result, the device including a display; a sensor; and a computing device in communication with the display and the sensor, wherein the computing device is configured to record a user vibrancy datum; identify a therapeutic remedy instruction set as a function of the user vibrancy datum, wherein the therapeutic remedy instruction set comprises a therapeutic remedy; and calculate a therapeutic remedy result that associates the user vibrancy datum and the therapeutic remedy with a therapy response curve.

Abstract: In one embodiment, a method includes receiving a user input comprising a natural-language utterance by an assistant xbot from a client system associated with a user, determining a semantic representation of the user input based on a structural ontology defining a labeling syntax for parsing the natural-language utterance to semantic units comprising actions, objects, and attributes, wherein the semantic representation embeds at least one object within at least one action and declares at least one attribute of the embedded object to be acted upon, sending a request based on the semantic representation to an agent for executing a task corresponding to the user input, receiving results of the executed task mapped to a structure determined by the structural ontology from the agent, and sending from the assistant xbot to the client system instructions for presenting a response based on the results of the executed task.

Abstract: A system and related method for completing online transactions via mobile device includes a client-side e-commerce platform executing on the mobile device that identifies candidate items for purchase based on images related to an item desired by the user. The client-side platform determines attributes of the item based on an image captured by an onboard camera or otherwise stored on, or downloaded to, the mobile device. Purchase information for items offered by participating vendors, or third-party vendors, is retrieved by the platform via APIs of the vendor network or automated middleware respectively. The user may select items for purchase and complete the transaction via single click, and the middleware forwards payment details to the third-party vendors and retrieves purchase information and transaction records from the third-party vendors. The client-side platform generates a single transaction and invoice whether the selected items are purchased from in-network or third-party vendors.

Abstract: Systems and methods for both technical and non-technical users to create content for interactive synthetic characters are provided. In some embodiments, a conversation editor may be configured to create a traversable script for an interactive synthetic character by receiving a set of conversation rules from a user. These rules can be used to match certain words or phrases that a user speaks or types, or to monitor for a physical movement of the user or synthetic character. Each conversation rule can include responses to be performed by the interactive synthetic character. The responses can include, for example, producing audible or textual speech for the synthetic character, performing one or more animations, playing one or more sound effects, retrieving data from one or more data sources, and the like. A traversable script can be generated from the set of conversation rules that when executed by the synthetic character allows for the dynamic interactions.

Abstract: A site monitoring system may analyze information from sites to determine when a device, a sensor, a controller, or other structure associated with optically switchable devices has a problem. The system may, if appropriate, act on the problem. In certain embodiments, the system learns customer/user preferences and adapts its control logic to meet the customer's goals.

Abstract: A method for uterine activity monitoring may include: acquiring a plurality of signals from a plurality of sensors during uterine activity; processing the plurality of signals to extract a plurality of uterine electrical activity characteristics; analyzing the plurality of uterine electrical activity characteristics; and classifying the uterine activity as one of: a preterm labor contraction, a labor contraction, a Braxton-Hicks contraction, and a state of no contraction. A method of assessing over time a pre-term birth risk of a pregnant female may include: calculating a baseline pre-term birth risk score based on a user input; acquiring, over time, a signal from a sensor; analyzing the signal to extract a parameter of interest, such that the parameter of interest comprises a physiological parameter; and calculating an instant pre-term birth risk score based, at least in part, on the parameter of interest and the user input.

Abstract: A system and method to distribute pesticides, fertilizers, water, and other materials on a farm with accuracy and precision is disclosed in order to combat the problems imposed on the environment due to over-fertilization and over use of pesticides. This system and method is a social networking control system in which multiple farms have independent grids of sensors capable of detecting the presence of pesticides, fertilizers, water, and other materials in the air, in the top-soil, and in the groundwater. These grids of sensors detect the location and concentration of these materials and reports them back to a social control system for analysis. The control system regulates the deposition of further chemicals through computer control of the chemical dispersal systems.

Abstract: An image analysis method for multicenter study includes, by a multicenter study support system, recruiting and selecting a plurality of agency systems to perform multicenter study, and then distributing an analysis guide and an analysis program corresponding to a purpose and condition of the multicenter study to each of the agency systems, by each of the agency systems, collecting analysis data acquired through the analysis guide and the analysis program and then uploading the analysis data to the multicenter study support system, and by the multicenter study support system, collecting and processing the uploaded analysis data, and then sharing the data processing result with each of the agency systems.

Abstract: A system for generating an adversarial example in respect of a neural network, the adversarial example generated to improve a margin defined as a distance from a data example to a neural network decision boundary. The system includes a data receiver configured to receive one or more data sets including at least one data set representing a benign training example (x); an adversarial generator engine configured to: generate, using the neural network, a first adversarial example (Adv1) having a perturbation length epsilon1 against x; conduct a search in a direction (Adv1-x) using the neural network; and to generate, using the neural network, a second adversarial example (Adv2) having a perturbation length epsilon2 based at least on an output of a search in the direction (Adv1-x).

Abstract: Systems and methods of design, delivery, and analysis of customer feedback surveys include receiving interaction content. Interaction content is analyzed to identify at least one issue arising in the interaction content. A survey of a plurality of questions is automatedly created based upon the identified at least one issue. A delivery channel for the survey is determined. The survey is delivered through the determined delivery channel. A survey response with survey results data is received.

Abstract: A processing system includes a receiving circuit 1 for receiving an input signal from an externally connected sensor, an expected signal generating circuit 4 for automatically generating a teaching signal for use in the learning circuit 5, a learning circuit 5 for calculating a weight value, a bias value, and the like of the neural network model to form an expected signal from the teaching signal generated by the expected signal generating circuit 4 and the signal from the receiving circuit 1, an inference circuit 2 for performing signal processing based on a learned model of the neural network model generated by the learning circuit 5, and a validity verification circuit 3? for performing similarity calculation between an output signal of the inference circuit 2 and an expected signal for comparison.

Abstract: Techniques are described herein that are capable of performing intent-based scheduling via a digital personal assistant. For instance, an intent of user(s) to perform an action (a.k.a. activity) may be used to schedule time (e.g., on a calendar of at least one of the user(s)) in which the action is to be performed. Examples of performing an action include but are not limited to having a meeting, working on a project, participating in a social event, exercising, and reading.

Abstract: An inspection apparatus includes a group data creation unit configured to create group data obtained by dividing a plurality of samples into a plurality of groups, a statistical state calculation unit configured to perform a statistical process for the samples divided into each of the groups to calculate data indicating a statistical state of a predetermined data item between the groups, and a user interface unit configured to display the statistical state in a display format enabling recognition of the statistical state between the groups on the basis of the data indicating the statistical state of the predetermined data item between the groups calculated by the statistical state calculation unit.

Abstract: Fast, efficient, and robust compression-based methods for detecting boundaries in arbitrary datasets, including sequences (1D datasets), are desired. The methods, each employing three simple algorithms, approximate the information distance between two adjacent sliding windows within a dataset. One of the algorithms calculates an initial ordered list of subsequences; while a second algorithm updates the ordered list of subsequences by dropping a first entry and appending a last entry rather than calculating completely new ordered lists with each iteration. Large values in the distance metric are indicative of boundary locations. A smoothed z-score or a wavelet-based algorithm may then be used to locate peaks in the distance metric, thereby identifying boundary locations. An adaptive version of the method employs a collection of window sizes and corresponding weighting functions, making it more amenable to real datasets with unknown, complex, and changing structures.

Abstract: Systems and methods are disclosed for triggering an update to a machine-learning model upon detecting that a distribution of particular (e.g., recently collected) input data set is sufficiently different from a distribution training input data set used to train the model. The distributions may be determined to be sufficiently different when a classifier can identify to which distribution individual data elements belong (e.g., to at least a predetermined degree). An update to the machine-learning model can include morphing weights used by the model and/or retraining the model.

Abstract: A method and device for presenting a prediction model, and a method and device for adjusting a prediction model. The method for presenting a prediction model includes: obtaining at least one prediction result of a prediction model for at least one prediction sample; obtaining at least one decision-making tree training sample for training a decision-making tree model according to the at least one prediction sample and the at least one prediction result, the decision-making tree model being used for fitting the prediction model; training the decision-making tree model by using at least one decision-making tree training sample; and visually presenting the trained decision-making tree model. By means of the method, a prediction model hard to understand can be approximated to a decision-making tree model, and the approximated decision-making tree model is presented, so that a user better understands the prediction model according to the presented decision-making tree model.