Abstract: A method includes receiving historical interaction data, which includes a plurality of historical interactions. Each historical interaction is associated with a plurality of data fields. The method includes assigning a plurality of weights to the plurality of data fields, generating a neural network using the plurality of weights and the plurality of data fields, identifying a first plurality of feature indicators indicative of a first class, the first class being different from a second class; receiving a second plurality of feature indicators derived from data relating to compromised accounts, updating, a probability distribution component using the first plurality of feature indicators and the second plurality of feature indicators, and receiving current data for an interaction. The method also includes applying the probability distribution component to the current data, and scoring the interaction using the probability distribution component.

Abstract: Various embodiments are generally directed to techniques for determining artificial neural network topologies, such as by utilizing probabilistic graphical models, for instance. Some embodiments are particularly related to determining neural network topologies by bootstrapping a graph, such as a probabilistic graphical model, into a multi-graphical model, or graphical model tree. Various embodiments may include logic to determine a collection of sample sets from a dataset. In various such embodiments, each sample set may be drawn randomly for the dataset with replacement between drawings. In some embodiments, logic may partition a graph into multiple subgraph sets based on each of the sample sets. In several embodiments, the multiple subgraph sets may be scored, such as with Bayesian statistics, and selected amongst as part of determining a topology for a neural network.

Abstract: Techniques are disclosed for accurately identifying distinct physical user devices in a cross-device context. An example embodiment applies a multi-phase approach to generate labeled training datasets from a corpus of unlabeled device records. Such labeled training datasets can be used for training machine learning systems to predict the occurrence of device records that have been wrongly (or correctly, as the case may be) attributed to different physical user devices. Such identification of improper attribution can be particularly helpful in web-based analytics. The labeled training datasets include labeled pairs of device records generated using multiple strategies for inferring whether the two device records of a pair of device records represent the same physical user device (or different physical user devices). The labeled pairs of device records can then be used to train classifiers to predict with confidence whether two device records represent or do not represent the same physical user device.

Abstract: In some embodiments, user-selectable/connectable model representations may be provided via a user interface to facilitate artificial intelligence development. The model representations may comprises first and second machine learning model (ML) representations corresponding to first and second ML models, and non-ML model representations corresponding to non-ML models. Based on user input indicating selection of the first and second ML model representations and a non-ML model representation corresponding to a non-ML model, at least a portion of a software application may be generated such that the software application comprises (i) an instance of the first ML model, an instance of the second ML model, and an instance of the non-ML model and (ii) an input/output data path between the instance of the first ML model and at least one other instance, the at least one other instance comprising the instance of the second ML model or the instance of the non-ML model.

Abstract: Disclosed is a method for meta-knowledge fine-tuning and platform based on domain-invariant features. According to the method, highly transferable common knowledge, i.e., domain-invariant features, in different data sets of the same kind of tasks is learnt, the common domain features in different domains corresponding to different data sets of the same kind of tasks learnt in the network set are fine-tuned to be quickly adapted to any different domains. According to the present application, the parameter initialization ability and generalization ability of the universal language model of the same kind of tasks are improved, and finally a common compression framework of the universal language model of the same kind of downstream tasks is obtained through fine tuning. In the meta-knowledge fine-tuning network, a loss function of the domain-invariant features is designed in the present application, and domain-independent universal knowledge is learn.

Abstract: A method and corresponding system identify missing interactions in incompletely known datasets represented as complex networks. The method identifies missing connections in a complex network. The method accesses an electronic representation of the network. The network includes nodes and links, the nodes represent entities, and the links represent interactions between the entities. For each pair of nodes not directly connected by a link, the method determines a number of paths connecting the pair of nodes and calculates a prediction score for the pair of nodes based on the number of paths connecting the pair of nodes. The method ranks the pairs of nodes based on the prediction scores, resulting in an ordered list of node pairs, and selects at least a subset of the pairs of nodes based on the ordered list of node pairs. The selected pairs of nodes represent missing connections in the network.

Abstract: The present disclosure relates to a method and an apparatus for object preference prediction, and a computer readable medium. The method includes: acquiring evaluation information indicating preference values of partial users in a user set for partial objects in an object set; acquiring auxiliary information of at least one of the user set and the object set, wherein the auxiliary information indicates an attribute of at least one of a corresponding user in the user set and a corresponding object in the object set; determining a user feature representation and an object feature representation using a matrix decomposition model, based on the evaluation information and the auxiliary information; and determining a preference prediction value of a target user in the user set for a target object in the object set based on the user feature representation and the object feature representation.

Abstract: The present invention discloses an edge calculation-oriented reparametric neural network architecture search method, including the following steps: S1: designing linear operators and multi-branch block structures; S2: constructing a hypernetwork by stacking the multi-branch block structures; S3: training the hypernetwork through a gradient-based first-stage search algorithm; S4: deleting redundant branches in the hypernetwork to construct an optimal subnetwork; S5: converting the multi-branch optimal subnetwork into a single-branch network; and S6: completing task reasoning by using the single-branch network. The method is used to search the neural network structure capable of performing reparameterization, and ensures the reasoning real-time performance and the high efficiency of model operation while ensuring the reasoning precision.

Abstract: An example method for updating convolutional neural network includes: obtaining a sample with a classification label; performing a first operation on the sample based on parameters of each layer of front-end network, to obtain a first operation result; performing a second operation on the sample based on the first operation result and the parameters of each layer of back-end network that the first GPU has, to obtain a second operation result; separately sending the first operation result to the other GPUs; receiving a third operation result obtained after each other GPU performs a third operation on the sample based on their parameters of each layer of back-end network and the first operation result; combining the second and third operation results to obtain a classification result; determining a prediction error based on the classification result and the classification label; and updating the convolutional neural network based on the prediction error.

Abstract: At a centralized model trainer, one or more neural network based models are trained using an input data set. At least a first set of parameters of a model is transmitted to a model deployment destination. Using a second input data set, one or more adaptive parameters for the model are determined at the model deployment destination. Using the adaptive parameters, one or more inferences are generated at the model deployment destination.

Abstract: Clustering and outlier detection in anomaly and causation detection for computing environments is disclosed. An example method includes receiving an input stream having data instances, each of the data instances having multi-dimensional attribute sets, identifying any of outliers and singularities in the data instances, extracting the outliers and singularities, grouping two or more of the data instances into one or more groups based on correspondence between the multi-dimensional attribute sets and a clustering type, and displaying the grouped data instances that are not extracted in a plurality of clustering maps on an interactive graphical user interface, wherein each of the plurality of clustering maps is based on a unique clustering type.

Abstract: A method and system are herein disclosed. The method includes developing a joint latent variable model having a first variable, a second variable, and a joint latent variable representing common information between the first and second variables, generating a variational posterior of the joint latent variable model, training the variational posterior, and performing inference of the first variable from the second variable based on the variational posterior.

Abstract: A cloud computing system can be configured to generate data models. A model optimizer of the cloud computing system can provision computing resources of the cloud computing system with a data model. A dataset generator of the cloud computing system can generate a synthetic dataset for training the data model. The computing resources can train the data model using the synthetic dataset. The model optimizer can store the data model and metadata of the data model in a model storage. The cloud computing system can receive production data from a data source by a production instance of the cloud computing system using a common file system. The production data can be processed using the data model by the production instance. The computing resources, the dataset generator, and the model optimizer can be hosted by separate virtual computing instances of the cloud computing system.

Abstract: A method, computer system, and a computer program product for estimating the probability of invoking information technology (IT) disaster recovery at a location based on an incident risk is provided. The present invention may include receiving a piece of data associated with an incident at the location. The present invention may also include estimating a similarity value associated with the incident based on a plurality of past incidents from a knowledge base. The present invention may then include receiving a plurality of mined data based on the location. The present invention may further include predicting the incident risk to the location based on the received plurality of mined data and the estimated similarity value to the plurality of past incidents.

Abstract: Provided are a method for adjusting a continuous variable, a method and an apparatus for analyzing a correlation using the same. A method for adjusting a continuous variable according to an exemplary embodiment of the present disclosure is a method for adjusting a continuous variable by an apparatus including: determining at least one confounder from analysis data; classifying the analysis data into a plurality of subgroups having the same combination of confounders; and generating a new continuous variable for each subgroup based on a representative value of a continuous variable distribution.

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 mechanism is described for facilitating storage management for machine learning at autonomous machines. A method of embodiments, as described herein, includes detecting one or more components associated with machine learning, where the one or more components include memory and a processor coupled to the memory, and where the processor includes a graphics processor. The method may further include allocating a storage portion of the memory and a hardware portion of the processor to a machine learning training set, where the storage and hardware portions are precise for implementation and processing of the training set.

Abstract: Cooperative neural networks may be implemented by providing an input to a first neural network including a plurality of first parameters, and updating at least one first parameter based on an output from a recurrent neural network provided with the input, the recurrent neural network including a plurality of second parameters.

Abstract: A machine learning system and method. The machine learning system includes at least one computation circuit that performs a weighted summation of incoming signals and provides a resulting signal. The weighted summation is carried out at least in part by a magnetic element in which weights are adjusted based on changes in effective magnetic susceptibility of the magnetic element.

Abstract: An online system generates predicted outcomes for a content distribution program that distributes content to users of the online system, the predicted outcome indicating a likelihood for the occurrence of an outcome of a content presentation. The online system transmits the one or more predicted outcomes to the third-party system, and receives prediction improvement data from the third-party system, the prediction improvement data indicating an adjustment to errors in the predicted outcomes based on a prediction by the third-party system. The online system updates the properties of a content distribution program based on the prediction improvement data, the updated content distribution program causing the online system to generate new predicted outcomes based on the prediction improvement data in content presentation opportunities. The online system also transmits content to users of the online system based on the updated content distribution program.