Abstract: Aspects of the disclosure relate to artificial intelligence (AI)-based processing of account transfers between different accounts associated with a client. In particular, various aspects of this disclosure relate to triggering transfers based on data associated with electronic transfers (e.g., between accounts associated with different users) and/or information associated with card-based transactions. Additional aspects of the disclosure relate to using internet of things (IOT) modules to determine predicted consumption associated with utilities, and at least triggering account transfers based on the predicted consumption.

Abstract: A network system may include a plurality of trainer devices and a computing system disposed within a remote network management platform. The computing system may be configured to: receive, from a client device of a managed network, information indicating (i) training data that is to be used as basis for generating a machine learning (ML) model and (ii) a target variable to be predicted using the ML model; transmit an ML training request for reception by one of the plurality of trainer devices; provide the training data to a particular trainer device executing a particular ML trainer process that is serving the ML training request; receive, from the particular trainer device, the ML model that is generated based on the provided training data and according to the particular ML trainer process; predict the target variable using the ML model; and transmit, to the client device, information indicating the target variable.

Abstract: Embodiments of the present disclosure relate to a method and apparatus for generating a neural network. The method includes: acquiring a target neural network, the target neural network corresponding to a preset association relationship, and being configured to use two entity vectors corresponding to two entities in a target knowledge graph as an input, to determine whether an association relationship between the two entities corresponding to the inputted two entity vectors is the preset association relationship, the target neural network comprising a relational tensor predetermined for the preset association relationship; converting the relational tensor in the target neural network into a product of a target number of relationship matrices, and generating a candidate neural network comprising the target number of converted relationship matrices; and generating a resulting neural network using the candidate neural network.

Abstract: A machine learning system includes a coach machine learning system that uses machine learning to help a student machine learning system learn its system. By monitoring the student learning system, the coach machine learning system can learn (through machine learning techniques) “hyperparameters” for the student learning system that control the machine learning process for the student learning system. The machine learning coach could also determine structural modifications for the student learning system architecture. The learning coach can also control data flow to the student learning system.

Abstract: A machine learning system includes a coach machine learning system that uses machine learning to help a student machine learning system learn its system. By monitoring the student learning system, the coach machine learning system can learn (through machine learning techniques) “hyperparameters” for the student learning system that control the machine learning process for the student learning system. The machine learning coach could also determine structural modifications for the student learning system architecture. The learning coach can also control data flow to the student learning system.

Abstract: An information processing method includes: deciding a timing when transfer to a memory is completed in a total time that is a sum of a calculation time at one or plurality of second layers at which calculation is carried out earlier than a first layer regarding a timing when data relating to calculation of the first layer is stored in the memory based on a calculation time estimated in advance regarding each of one layer or a given number of layers in a plurality of layers included in a neural network and a time of transfer of data relating to calculation of each of the one layer or the given number of layers to the memory; and storing the data relating to calculation of the first layer in the memory based on the decided timing in sequentially carrying out calculation of each layer of the neural network.

Abstract: At a machine learning service, a data structure generated during the training phase of a machine learning model, as well as an input records associated with a result of the model, are analyzed. A first informational data set pertaining to the result, which indicates an alternative result, is generated. The first informational data set is transmitted to a presentation device with a directive to display a visual representation of the data set. In response to an exploration request pertaining to the first informational data set, a second informational data set indicating one or more observations of a training data set used for the model is transmitted to the presentation device.

Abstract: An integrated neural network and semantic system applies a neural network to interpret an image, determines a syntactical element corresponding to the image in accordance with the interpretation, and determines a first probability that represents a confidence level that the correspondence is accurate. A semantic chain and associated second probability are then generated based on the syntactical element and the first probability, whereby the second probability represents the system's confidence level that the semantic chain accurately reflects objective reality. A natural language communication is generated for delivery to a user that comprises syntactical elements that are in accordance with the semantic chain and the second probability. The communication may further be expected to result in receiving information that will influence the confidence level that the semantic chain accurately reflects objective reality.

Abstract: One aspect of the disclosure relates to systems and methods for determining probabilities of successful synthesis of materials in the real world at one or more points in time. The probabilities of successful synthesis of materials in the real world at one or more points in time can be determined by representing the materials and their pre-defined relationships respectively as nodes and edges in a network form, and computation of the parameters of the nodes in the network as input to a classification model for successful synthesis. The classification model being configured to determine probabilities of successful synthesis of materials in the real world at one or more points in time.

Abstract: Roughly described, an evolutionary data mining system includes at least two processing units, each having a pool of candidate individuals in which each candidate individual has a fitness estimate and experience level. A first processing unit tests candidate individuals against training data, updates an individual's experience level, and assigns each candidate to one of multiple layers of the candidate pool based on the individual's experience level. Individuals within the same layer of the same pool compete with each other to remain candidates. The first processing unit selects a set of candidates to retain based on the relative novelty of their responses to the training data. The first processing unit reports successful individuals to the second processing unit, and receives individuals for further testing from the second processing unit. The second processing unit selects individuals to retain based on their fitness estimate.

Abstract: Aspects of data modification for neural networks are described herein. The aspects may include a connection value generator configured to receive one or more groups of input data and one or more weight values and generate one or more connection values based on the one or more weight values. The aspects may further include a pruning module configured to modify the one or more groups of input data and the one or more weight values based on the connection values. Further still, the aspects may include a computing unit configured to update the one or more weight values and/or calculate one or more input gradients.

Abstract: Aspects of data modification for neural networks are described herein. The aspects may include a connection value generator configured to receive one or more groups of input data and one or more weight values and generate one or more connection values based on the one or more weight values. The aspects may further include a pruning module configured to modify the one or more groups of input data and the one or more weight values based on the connection values. Further still, the aspects may include a computing unit configured to update the one or more weight values and/or calculate one or more input gradients.

Abstract: Disclosed is a computer-implemented method for estimating an uncertainty of a prediction generated by a machine learning system, the method including: receiving first data; training a first machine learning model component of a machine learning system with the received first data, the first machine learning model component is trained to generate a prediction; generating an uncertainty estimate of the prediction; training a second machine learning model component of the machine learning system with second data, the second machine learning model component is trained to generate a calibrated uncertainty estimate of the prediction. Also disclosed is a corresponding system.

Abstract: Technologies described herein can be used to generate and distribute neural network models and executable code using feedback data received from one or more client computing devices. A neural network model can be generated by a server computer. Executable code can also be generated by the server that, when executed by a client computing device, causes the client device to generate a prediction using the neural network model. The server can transmit the model and code to one or more client computing devices. The server can receive feedback data from the client device(s) based on predictions generated by the client device(s) using the neural network model and the executable code. The server can generate an updated version of the neural network model and/or an updated version of the executable code base on the feedback data, and can transmit the updated model and/or the updated code to the client device(s).

Abstract: Example wireless feedback control systems disclosed herein include a receiver to receive a first measurement of a target system via a first wireless link. Disclosed example systems also include a neural network to predict a value of a state of the target system at a future time relative to a prior time associated with the first measurement, the neural network to predict the value of the state of the target system based on the first measurement and a prior sequence of values of a control signal previously generated to control the target system during a time interval between the prior time and the future time, and the neural network to output the predicted value of the state of the target system to a controller. Disclosed example systems further include a transmitter to transmit a new value of the control signal to the target system via a second wireless link.

Abstract: Systems and methods are provided for estimating travel time and distance. Such method may comprise obtaining a vehicle trip dataset comprising an origin, a destination, a time-of-day, a trip time, and a trip distance associated with each of a plurality of trips, and training a neural network model with the vehicle trip dataset to obtain a trained model. The neural network model may comprise a first module and a second module, the first module may comprise a first number of neuron layers, the first module may be configured to obtain the origin and the destination as first inputs to estimate a travel distance, the second module may comprise a second number of neuron layers, and the second module may be configured to obtain the information of a last layer of the first module and the time-of-day as second inputs to estimate a travel time.

Abstract: An intelligent target object detection and alerting platform may be provided. The platform may receive a content stream from a content source. A target object may be designated for detection within the content stream. A target object profile associated with the designated target object may be retrieved from a database of learned target object profiles. The learned target object profiles may be associated with target objects that have been trained for detection. At least one frame associated with the content stream may be analyzed to detect the designated target object. The analysis may comprise employing a neural net, for example, to detect each target object within each frame. A parameter for communicating target object detection data may be specified. In turn, when the parameter is met, the detection data may be communicated.

Abstract: To select the content to be presented to the user, a first latent vector is determined for a content item based on a first object associated with the content item. A second latent vector is determined for the content item based on a second object associated with the content item. A content item vector is then determined based on the first and second latent vectors. Furthermore, a user vector is determined based on interactions of the user with the first set of content objects and the second set of content objects. A score indicative of the likelihood of the user interacting with the content item is determined based on the content item vector and the user vector.

Abstract: An early warning and event monitoring computer device for predicting events is provided. The computer device programmed to a) store a plurality of models associated with a plurality of future events, b) receive a plurality of data from a plurality of data sources, c) preprocess the plurality of data to remove noise and populate the plurality of models with the plurality of data, d determine a subset of models of the plurality of models to execute based on a user query, e) execute the subset of models to receive a plurality of results, f) ensemble the plurality of results from the subset of models to determine a combination model, and g) execute the combination model to forecast at least one future event based on the user query. The computer device uses predictive analytical results to visualize which actors, events, sentiments, and key variables across the topologies are critical to support.

Abstract: Disclosed is a method for automatically compressing multi-task oriented pre-trained language model and a platform thereof. According to the method, a meta-network of a structure generator is designed, a knowledge distillation coding vector is constructed based on a knowledge distillation method of Transformer layer sampling, and a distillation structure model corresponding to a currently input coding vector is generated by using the structure generator; at the same time, a Bernoulli distribution sampling method is provided for training the structure generator; in each iteration, each encoder unit is transferred by Bernoulli distribution sampling to form a corresponding coding vector; by changing the coding vector input to the structure generator and a small batch of training data, the structure generator and the corresponding distillation structure are jointly trained, and a structure generator capable of generating weights for different distillation structures can be acquired.