Abstract: An example embodiment includes a neural network unit to which a plurality of element values based on learning target data are input, and a learning unit that trains the neural network unit. The neural network unit has a plurality of learning cells each including a plurality of input nodes that perform predetermined weighting on each of the plurality of element values and an output node that sums the plurality of weighted element values and outputs the sum, and in accordance with an output value of each of the learning cells, the learning unit updates weighting coefficients of the plurality of input nodes of each of the learning cells or adds a new learning cell to the neural network unit.

Abstract: A method provides learning with noisy labels. The method includes generating a first network of a machine learning model with a first set of parameter initial values, and generating a second network of the machine learning model with a second set of parameter initial values. First clean probabilities for samples in a training dataset are generated using the second network. A first labeled dataset and a first unlabeled dataset are generated from the training dataset based on the first clean probabilities. The first network is trained based on the first labeled dataset and first unlabeled dataset to update parameters of the first network.

Abstract: Methods, apparatus, and processor-readable storage media for data integration demand management using artificial intelligence are provided herein. An example computer-implemented method includes obtaining at least one data integration demand, wherein the at least one data integration demand comprises textual information provided by at least one user; determining multiple parameters of the at least one data integration demand by applying one or more machine learning natural language processing techniques to at least a portion of the textual information provided by the at least one user; generating at least one delivery date prediction for the at least one data integration demand by applying one or more artificial intelligence techniques to the multiple determined parameters of the at least one data integration demand; and performing one or more automated actions based at least in part on the at least one generated delivery date prediction.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for few-shot learning-based generator training are disclosed. An exemplary method may start with obtaining a teacher model and a plurality of training samples, as well as a generator for generating more training samples. After generating a plurality of additional training samples using the method may continue with feeding the plurality of generated additional training samples into the teacher model to obtain a plurality of first statistics; and feeding the plurality of training samples into the teacher model to obtain a plurality second statistics. Then the method further includes training the generator to minimize a distance between the plurality of first statistics and the plurality of second statistics.

Abstract: An N modular redundancy method, system, and computer program product include a computer-implemented N modular redundancy method for neural networks, the method including selectively replicating the neural network by employing one of checker neural networks and selective N modular redundancy (N-MR) applied only to critical computations.

Abstract: The disclosure relates to a system and a method for generating a neural network model for image processing by interacting with at least one client terminal. The method may include receiving via a network, a plurality of first training samples from the at least one client terminal. The method may also include training a first neural network model based on the plurality of first training samples to generate a second neural network model. The method may further include transmitting, via the network, the second neural network model to the at least one client terminal.

Abstract: In implementations of the present disclosure, a solution for optimization of a learning network in an equivalent class space is provided. In this solution, base paths running through layers of a learning network are determined. Each node utilizes an activation function with a scaling invariant property to process an input from a node of a previous layer, each base path comprises a single node in each layer, and processing in the base paths is linearly independent from each other. A combined value of parameters associated with nodes in each base path is updated. A parameter associated with a node is used to adjust an input obtained from a node of a previous layer. Values of parameters associated with nodes in the base paths are updated based on updated combined values of parameters. Through this solution, optimization efficiency can be improved and more accurate optimized values of parameters are achieved.

Abstract: A method operating a Graphics Processing Unit (GPU) memory can be provided by accessing specified training parameters used to train a Deep Neural Network (DNN) using a GPU with a local GPU memory, the specified training parameters including at least a specified batch size of samples configured to train the DNN. A sub-batch size of the samples can be defined that is less than or equal to the specified batch size of samples in response to determining that an available size of the local GPU memory is insufficient to store all data associated with training the DNN using one batch of the samples. Instructions configured to train the DNN using the sub-batch size can be defined so that an accuracy of the DNN trained using the sub-batch size is about equal to an accuracy of the DNN trained using the specified batch size of the samples.

Abstract: A computerized neural network training and testing environment trains and validates a neural network to produce outputs corresponding to a digital signal processing (DSP) algorithm. After validation and testing, the neural network is replicable in any processing environment, independent of device architecture. Such devices may also include a neural network having a reversed process flow to produce a digital signal corresponding to an inverse of the DSP algorithm.

Abstract: Data sets can be processed using machine learning or artificial intelligence models to generate outputs predictive of a degree to which performing a protocol can positively modify an expected result associated with a condition. Generating the output may include accessing a user data set, inputting the user data set into a trained machine learning model to generate an output, and selecting an incomplete subset of a set of genes based on the output.

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: Systems and methods for remote intervention are disclosed herein. The system can include memory including: a user profile database; a content database; and a model database. The system can include a remote device including: a network interface; and an I/O subsystem. The system can include a content management server that can: receive a first electrical signal from the remote device; generate and send an electrical signal to the remote device directing the launch of the content authoring interface; receive a second electrical signal including content received by the content authoring interface from the remote device; identify a plurality of response demands in the received content; determine a level of the received content based on the identified plurality of response demands; determine the acceptability of the received content based on the identified plurality of response demands; and generate and send an alert to the remote device.

Abstract: A soldering process method includes steps of: establishing a material component database; establishing a working parameter database; analyzing material and component characteristics required for a new soldering process; comparing the characteristics with information in the material component database; selecting operating parameters corresponding to the material and component characteristics similar to those required for the new soldering process; performing the soldering process using the operating parameters corresponding to the material and component characteristics similar to those required for the new soldering process; measuring and recording the soldering process execution information and the final product information; determining whether the final product of the solder process meets the quality control requirements; using the machine learning method to fit the soldering process execution information and the final product information of the solder process to get the operating parameters for the next sol

Abstract: A system includes a computing platform having a hardware processor, and a system memory storing a software code and a content labeling predictive model. The hardware processor is configured to execute the software code to scan a database to identify content assets stored in the database, parse metadata stored in the database to identify labels associated with the content assets, and generate a graph by creating multiple first links linking each of the content assets to its corresponding label or labels. The hardware processor is configured to further execute the software code to train, using the graph, the content labeling predictive model, to identify, using the trained content labeling predictive model, multiple second links among the content assets and the labels, and to annotate the content assets based on the second links.

Abstract: One of the major artifacts that pushed Information Technology companies ahead of its competitors is undoubtedly contextual domain knowledge. When a new development problem comes to an IT team, how problem solving and steps of action can be automatically formulated is the major area of research. A method and system for utilizing domain knowledge to identify solution to a problem has been provided. The problem is reformulated as recommending a workflow like a pipeline of connected steps, by leveraging contextual domain knowledge and technical knowledge, finally planning and scheduling solutions steps, given a problem of a domain & use case. This is achieved by Contextual sequence-aware recommendation of steps, backed by semantic web technologies and pattern recognition steps. Finally a plan is derived by automated planning techniques which can be executed based on software orchestration by connecting a repository of re-usable annotated code blocks.

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: Aspects of the present disclosure relate to interactive search training. A training canvas comprises results associated with a search query. The training canvas may be used as part of a training session that occurs during normal use of a search platform. When the search platform is first used, the results may be provided based on an existing model. An irrelevant result may be removed from the training canvas, such that a replacement result is added in its place. Additionally, results may be reordered, thereby indicating a ranking with which results should be displayed. Such interactions with the training canvas may be used to generate training data, such that a new model is trained accordingly. Thus, interactions with the training canvas yield high-quality training data that is usable to generate a model having equal or greater performance than a model that was trained using an equivalent amount of implicit training data.

Abstract: A platform for providing employment assistance services to enterprises and candidates is disclosed. For example, the platform trains, based on personal attributes of employees of multiple enterprise and work culture attributes associated with each employer of the multiple enterprises, a machine learning model that defines associations between the personal attributes and the work culture attributes. Further, the platform extracts information associated with a person from one or more sources on the Web where the person is represented, generates, based on the information associated with the person, a user profile associating personal attributes with the person, applies the user profile to the machine learning model; and receives an indication, from the machine learning model, of an employer profile that is compatible with the user profile, the employer profile including work culture attributes associated with an employer.

Abstract: Aspects of the present invention disclose a method for recommending an activity based on a social media profile, IoT devices, and historical engagements of the user. The method includes one or more processors determining a past activity of a user based at least in part on social media posts and internet of things (IoT) enabled devices of the user. The method further includes determining a set of historical conditions corresponding to the past activity, wherein the set of conditions correspond to a positive sentiment of the user. The method further includes identifying a location of the user. The method further includes generating an activity recommendation based on the location of the user and the set of historical conditions corresponding to the past activity, wherein the activity recommendation includes a set of future conditions of a future activity, wherein the set of future conditions correlate with the set of historical conditions.

Abstract: Systems and methods are described for tailoring shareable content object reference model (SCORM)-compliant content to one or more users. A learning management system (LMS), configured to be SCORM-compliant, initiates shareable content object (SCO) to provide content to users. The LMS implements an instance of application programming interface (API) comprising a plurality of functions to be called by SCO during runtime to access data model elements accessible via LMS. The LMS is configured to support one or more data model elements undefined by SCORM. Further, LMS receives a call to a function of the plurality of functions of the API from SCO to access information about users. The call references a name of a data model element undefined by SCORM. The data model element identifies information about users. The LMS provides information about the users to SCO and the SCO tailors the content to the users based on the information.

Abstract: This disclosure describes systems and techniques for detecting events, determining a result of each respective event using a first hypothesis source, and calculating a likelihood that a second (and/or additional) hypothesis source would determine the same result of the respective event. The calculated likelihood may then be used to be determine whether to request that the second hypothesis source determine the result of the event, determine an amount of resources of the second hypothesis source to use to make this determination, and/or like.

Abstract: A condition determination system includes: an operation condition data obtaining unit that obtains operation condition data indicating an operation condition of a facility; and a determination unit that determines, based on the operation condition data, a level of a phenomenon that occurs due to the operation condition of the facility.

Abstract: Methods, systems, and computer-readable media for interactive workflow generation for machine learning lifecycle management are disclosed. A machine learning management system determines one or more prompts associated with use of a machine learning model. Input representing one or more responses to the one or more prompts is received. The one or more responses are provided via a user interface. The machine learning management system determines one or more workflows associated with the machine learning model. The workflow(s) are determined based at least in part on the one or more responses. The workflow(s) comprise a plurality of tasks associated with use of the machine learning model at a plurality of stages of a lifecycle of the model. One or more computing resources are determined, and at least a portion of the workflow(s) is performed using the one or more computing resources.

Abstract: A computer implemented method includes receiving an exception generated based on programming code, generating exception features from the received exception, the generated exception features being generated based on a set exception features derived from search logs, and executing a machine learning model on the received exception and generated exception features to provide information from the search logs identified as most helpful to resolve the received exception, wherein the machine learning model was trained on training data comprising extracted exceptions and the set of exception features derived from the search logs.

Abstract: A system and method are disclosed for bottom-up modeling and prediction of asset anomalies. In one embodiment, the system receives first sensor data from a first sensor, the first sensor associated with a first asset; smooths the first sensor data; determines a first stage within sensor data, the sensor data including the first sensor data; determines a first set of anomalies within the first stage; generates a first asset state space associated with the first asset; trains a base model describing a first group of one or more assets, the first group of one or more assets including the first asset; and trains, using the base model, a final model particular to the first asset.

Abstract: A method and system is disclosed for determining a probability that an encountered platform was of a specific type given that a plurality of emitters exist on the platform and each emitter has a computed probability that it is of each of a set of types. A preprocessing stage operates on a description of the environment and determines the probability of a set of events that are independent of any observation. A runtime processing stage uses the terms computed in the preprocessing stage along with data assembled from a set of observations to determine the conditional probability that a particular platform type was the type encountered.

Abstract: A quantum computing device is provided, including a logical qubit encoding surface including a plurality of plaquettes. Each plaquette of the plurality of plaquettes may include a plurality of measurement-based qubits. The plurality of measurement-based qubits may include four data qubits and a first ancilla qubit. The first ancilla qubit may be electrically connected to the four data qubits and a second ancilla qubit included in the logical qubit encoding surface.

Abstract: Apparatus and method for performing a quantum rotation operation. For example, one embodiment of an apparatus comprises: a decoder to decode a plurality of instructions; execution circuitry to execute a first instruction or first set of the instructions to generate a floating point (FP) value and to store the FP value in a first register; the execution circuitry to execute a second instruction or second set of the one or more of the instructions to read the FP value from the first register and compress the FP value to generate a compressed FP value having a precision selected for performing quantum rotation operations; and quantum interface circuitry to process the compressed FP value to cause a quantum rotation to be performed on one or more qubits of a quantum processor.

Abstract: A technique relates to configuring a superconducting router. The superconducting router is operated in a first mode. Ports are configured to be in reflection in the first mode in order to reflect a signal. The superconducting router is operated in a second mode. A given pair of the ports is connected together and in transmission in the second mode, such that the signal is permitted to pass between the given pair of the ports.

Abstract: A fault tolerant quantum error correction protocol is implemented for a surface code comprising Gottesman Kitaev Preskill (GKP) qubits. Analog information is determined when measuring position or momentum shifts, wherein the analog information indicates a closeness of the shift to a decision boundary. The analog information may further be used to determine confidence values for error corrected measurements from the GKP qubits of the surface code.

Abstract: Implementations detailed herein include description of a computer-implemented method. In an implementation, the method at least includes receiving an application instance configuration, an application of the application instance to utilize a portion of an attached accelerator during execution of a machine learning model and the application instance configuration including: an indication of the central processing unit (CPU) capability to be used, an arithmetic precision of the machine learning model to be used, an indication of the accelerator capability to be used, a storage location of the application, and an indication of an amount of random access memory to use.

Abstract: A computer system and process extract information from a literary work regarding relationships between entities (e.g., characters, locations, etc.) described or represented in the literary work, and generate a graph representing these relationships. The graph data is parsed into sub-graphs, and the subgraphs are used to generate a signature of the literary work. The respective signatures of different literary works may be compared for purposes of generating literary work recommendations for users.

Abstract: Systems, computer-implemented methods, and computer program products that can facilitate applying a reinforcement learning policy to available actions are described. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a state encoder that maps, based on one or more encoding parameters, a state of an environment on to one or more qubits of a quantum device. The system can further comprise a variational component that combines a reinforcement learning policy with a sampling of the one or more qubits, resulting, based on one or more variational parameters, in a probability distribution of a plurality of available actions at the state of the environment.

Abstract: A learning device is configured to perform learning of a decision tree by gradient boosting. The learning device includes a plurality of learning units and a plurality of model memories. The plurality of learning units are configured to perform learning of the decision tree using learning data divided to be stored in a plurality of data memories. The plurality of model memories are each configured to store data of the decision tree learned by corresponding one of the plurality of learning units.

Abstract: Embodiments of the present disclosure relate to a method for training a trajectory classification model. The method includes: acquiring trajectory data; computing a trajectory feature of the trajectory data based on a temporal feature and a spatial feature of the trajectory data, the trajectory feature comprising at least one of a curvature or a rotation angle; and training the trajectory feature to obtain the trajectory classification model. Embodiments of the present disclosure further provide an apparatus for training a trajectory classification model, an electronic device, and a computer readable medium.

Abstract: Embodiments relate to a system, program product, and method for employing feature engineering to improve classifier performance. A first machine learning (ML) model with a first learning program is selected. The first selected ML model is operatively associated with a first structured dataset. First features in the first dataset directed at performance of the selected ML model are identified. A second structured dataset is assessed with respect to the identified features in the first dataset, and new features in the second dataset are identified, where the new features are semantically related to the identified features in the first dataset. The first dataset is dynamically augmented with the identified new features in the second dataset. The dynamically augmented first dataset is applied to the selected ML model to subject an embedded learning algorithm of the selected ML model to training using the augmented first dataset.

Abstract: A method for operating a detector that is set up to check whether a data signal that is supplied to a machine learning system has been manipulated. The machine learning system is first trained in adversarial fashion using a manipulated data signal, the manipulated data signal having been ascertained by manipulation of a training data signal, and the machine learning system being trained to provide in each case the same output signal when the training data signal or the manipulated data signal is supplied to it. The detector is trained using another manipulated data signal that is produced as a function of the trained machine learning system.

Abstract: A loose coupling between Internet of Things (“IoT”) devices and environmental sensors is generated. Once the loose coupling has been generated, conditions in a physical environment can be managed utilizing the loosely coupled devices. For example, a hybrid machine learning/expert system can be utilized to activate the IoT devices in an environment to achieve a desired condition in an optimized manner.

Abstract: A processor may include a set of primitive operators, receive a set of data-driven operators, at least one of the set of data-driven operators including a machine learning model, and receive an input-output data pair set. Based on a grammar specifying rules for linking the set of primitive operators and the set of data-driven operators, the processor may search among the set of primitive operators and the set of data-driven operators to find a symbolic model that fits the input-output data set.

Abstract: A machine learning system passively monitors sensor data from the living space of a patient. The sensor data may include audio data. Audio features are generated. A trained machine learning model is used to detect a change in condition. In some implementations, the machine learning model is trained in a learning phase based on training data that includes questionnaires completed by caregivers and identified audio features.

Abstract: A system for a generating an alimentary element prediction machine-learning model, the system comprising a computing device configured to provide, to a user, a plurality of compatible alimentary elements as a function of user biochemistry, receive training data relating a plurality of temporally preceding alimentary elements as a function of the plurality of compatible alimentary elements presented to a user, train, using a machine-learning process, a computer model as a function of the user-selection training data to predict user-selectable alimentary elements, generate an alimentary profile as a function of the computer model, receive a user input for an alimentary element, and present, as a function of the user input, the alimentary element as a function of the alimentary profile.

Abstract: A computing system can include a plurality of clients located outside a cloud-based computing environment, where each of the clients may be configured to encode respective original data with a respective unique secret key to generate data hypervectors that encode the original data. A collaborative machine learning system can operate in the cloud-based computing environment and can be operatively coupled to the plurality of clients, where the collaborative machine learning system can be configured to operate on the data hypervectors that encode the original data to train a machine learning model operated by the collaborative machine learning system or to generate an inference from the machine learning model.

Abstract: A vehicle sharing system includes a vehicle having interior transceiver modules associated with different passenger seating areas and a vehicle computing system (VCS) including a processor and a memory in communication with the modules and programmed to detect occupancy status of each seating area based on signals from the modules and to communicate the occupancy statuses to a remote server to facilitate scheduling of ride-sharing passengers for a specified seating area of the vehicle. The reserved seating location may be used to align the seating location/door with a passenger during pick-up, adjust vehicle accessory settings associated with the reserved seating location, and activate a visual indicator to direct the passenger to the assigned/reserved seating location.

Abstract: A system, method, and computer-readable medium are disclosed for configuring and offering upgrade capability to information handling systems. A deep learning or machine learning model (DL/ML) model is trained to optimize a particular configuration and use cases for an information handling system and provides various levels of upgrades for the use cases. Levels are identified as base or upgrade and mapped to a licensing layer that enables or disables use of performance levels based on weights that enable base output level classes and disable upgrade output level classes. An offer to upgrade is made as to upgrade levels upon a determination of probabilities of performance output level classes.

Abstract: Embodiments described herein include systems and methods for processing behavioral assessments. One embodiment includes a computing device that stores logic that causes the system to receive data from a first behavioral assessment, the first behavioral assessment assessing a first behavioral characteristic of a first person, receive data from a second behavioral assessment, the second behavioral assessment assessing a second behavioral characteristic of the first person, and utilize the first behavioral characteristic from the first behavioral assessment and the second behavioral characteristic from the second behavioral assessment to calculate a behavioral parameter for the first person. In some embodiments, the logic causes the system to compare the behavioral parameter against a corresponding behavioral parameter for a second person to determine how the first person and the second person would work together and provide data about how the first person and the second person would work together.

Abstract: A system and a method for assigning a tutor to a cohort of students. The system receives information from a tutor. The information comprises a name, academic details, preferred languages, a subject of interest, a topic of interest, an introductory video of the tutor, and available time slots. The system further automatically generates a question for a tutor in real-time based on the information. Furthermore, the system receives an answer to the question from the tutor in an answer format. Subsequently, the system generates an assessment report of the tutor. Further, the system computes a similarity index of the tutor with a profile of a cohort of the students. Finally, the system assigns the tutor to the cohort of the students based on the similarity index, feedback received from the cohort of the students, and the available time slots of the tutor.

Abstract: A method of and system for selecting users for a rollout process of a feature is carried out by receiving an indication of the rollout process for the feature being rolled out, accessing a rollout plan, the rollout plan including a plurality of stages for the rollout process, and selecting users from a user population for each of the plurality of stages of the rollout process. Selecting the users from a user population includes examining a property to determine if a user in the user population is indicated as opted into being a late-stage receiver, and upon determining that the user is opted into being the late-stage receiver, excluding the user from the user population for one or more early stages of the rollout and including the user into the user population in one or more late stages of the rollout process.

Abstract: Methods, systems and apparatus for implementing a security awareness program are provided which allow a device of a security awareness system to receive attributes of an implementation of a security awareness program from an entity, such as a company. Responsive to the attributes, the device determines a configuration for each of a baseline simulated phishing campaign, electronic based training of users of the entity for security awareness and one or more subsequent simulated phishing campaigns. The device initiates execution of the baseline simulated phishing campaign to identify a percentage of users of the entity that are phish-prone.

Abstract: Systems and methods for limiting autonomous vehicle requests are provided. The method includes obtaining data indicative of a request for access to a software service for facilitating one or more transportation services. The method can include granting access to the software service based on a rate limit associated with the request and a request history. The rate limit can be associated with any combination of a vehicle provider determined based on the request, the software service for which access is requested, or current data. The rate limit can define a threshold number of requests over a period of time. The method can include determining the routing action for the request based on the rate limit and a request history associated the vehicle provider, the software service, or current data. The routing action can include granting access if the request history is less than the threshold number of requests.

Abstract: A system, method, and computer readable device that detects hidden correlation relationships among entities, such as companies and/or individuals is presented. A dataset that corresponds to a predefined set of correlation relationships of these companies and/or individuals may be collected. The dataset may be stored in a graph database and a machine learning system may be built using features computed from the graph database. At least a new pair of companies or a new pair of an individual and a company may be evaluated. The system, method, and/or computer readable device may determine whether a hidden correlation relationship exists between them.