Abstract: Techniques are provided for selection of machine learning algorithms based on performance predictions by using hyperparameter predictors. In an embodiment, for each mini-machine learning model (MML model), a respective hyperparameter predictor set that predicts a respective set of hyperparameter settings for a data set is trained. Each MML model represents a respective reference machine learning model (RML model). Data set samples are generated from the data set. Meta-feature sets are generated, each meta-feature set describing a respective data set sample. A respective target set of hyperparameter settings are generated for said each MML model using a hypertuning algorithm. The meta-feature sets and the respective target set of hyperparameter settings are used to train the respective hyperparameter predictor set. Each hyperparameter predictor set is used during training and inference to improve the accuracy of automatically selecting a RML model per data set.

Abstract: The illustrative embodiments provide a method, system, and computer program product for validating quantum algorithms using a machine learning model. In an embodiment, a method includes receiving a training data set. In an embodiment, a method includes training, by a first processor, a machine learning model with the training data set for validation of quantum circuits. In an embodiment, a method includes generating, by the machine learning model, a set of rules for validation of quantum circuits.

Abstract: Various embodiments, methods and systems for implementing a distributed computing system crowdsourcing engine are provided. Initially, a source asset is received from a distributed synthetic data as a service (SDaaS) crowdsource interface. A crowdsource tag is received for the source asset via the distributed SDaaS crowdsource interface. Based in part on the crowdsource tag, the source asset is ingested. Ingesting the source asset comprises automatically computing values for asset-variation parameters of the source asset. The asset-variation parameters are programmable for machine-learning. A crowdsourced synthetic data asset comprising the values for asset-variation parameters is generated.

Abstract: An apparatus is for unsupervised domain adaptation for allowing a deep learning model with supervised learning on a source domain completed to be subjected to unsupervised domain adaptation to a target domain. The apparatus includes a first learning unit to perform a forward pass by inputting a pair (xsi, ysi) of first data xsi of the source domain and a label ysi for each of the first data and second data xTj belonging to the target domain, and insert a dropout following a Bernoulli distribution into the deep learning model in performing the forward pass, and a second learning unit to perform a back propagation to minimize uncertainty about the learning parameter of the deep learning model by using a predicted value for each class output through the forward pass and the label ysi, and an uncertainty vector for the second data xTj output through the forward pass as inputs.

Abstract: A computing system and a compressing method for neural network parameters are provided. In the method, multiple neural network parameters are obtained. The neural network parameters are used for a neural network algorithm. Every at least two neural network parameters are grouped into an encoding combination. The number of neural network parameters in each encoding combination is the same. The encoding combinations are compressed with the same compression target bit number. Each encoding combination is compressed independently. The compression target bit number is not larger than a bit number of each encoding combination. Thereby, the storage space can be saved and excessive power consumption for accessing the parameters can be prevented.

Abstract: Examples of artificial intelligence-based reasoning explanation are described. In an example implementation, a knowledge model having a plurality of ontologies and a plurality of inferencing rules is generated. Once the knowledge model is generated, based on a real-world problem, a knowledge model from amongst various knowledge models is selected to be used for resolving a real-world problem. The data procured from the real-world problem is clustered and classified into an ontology of the determined knowledge model. Inferencing rules to be used for deconstructing the real-world problem are identified, and a machine reasoning is generated to provide a hypothesis for the problem and an explanation to accompany the hypothesis.

Abstract: Embodiments operate a configurator that generates a quote for a product or service configuration, the quote including a quote workflow that includes at least one required quote approval and the quote includes a plurality of quote attributes that define the quote. Embodiments input the plurality of quote attributes into a first neural network model and a second neural network model and generate with a gradient descent a likelihood that the quote will be approved and a time required for the quote to be approved. Embodiments generate one or more attributes with the largest gradient values for the likelihood that the quote will be approved and the time required for the quote to be approved. Embodiments receive a change to one or more of the attributes and regenerate the likelihood that the quote will be approved and/or the time required for the quote to be approved based on the change.

Abstract: Embodiments relate generally to computer network architectures for machine learning, and more specifically, to computer network architectures in the context of program rules, using combinations of defined patient clinical episode metrics and other clinical metrics, thus enabling superior performance of computer hardware. Aspects of embodiments herein are specific to patient clinical episode definitions, and are applied to the specific outcomes of highest concern to each episode type. Furthermore, aspects of embodiments herein produce more accurate and reliable predictions of possible patient outcomes and metrics.

Abstract: A method and system for overlaying content on a multimedia content element. The method includes: partitioning the multimedia content element into a plurality of partitions; generating at least one signature for each partition of the multimedia content element, wherein each generated signature represents a concept; determining, based on the generated at least one signature, at least one link to content; identifying, based on the generated at least one signature, at least one of the plurality of partitions as a target area of user interest; and adding, as an overlay to the multimedia content element, the determined at least one link to content, wherein the at least one link is overlaid on the at least one target area.

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: One embodiment provides a method that includes determining candidate ontologies for alignment from multiple available knowledge bases. An initial target ontology is selected from the candidate ontologies and correcting the initial selected ontology with received refinement input. Concepts in the selected initial ontology are aligned with concepts of the target ontology using a deep learning hierarchical classification with received review input. A user is assisted to build, change and grow the selected initial ontology exploiting both the target ontology and new facts extracted from unstructured data.

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: The present disclosure relates to generating fillable digital forms corresponding to paper forms using a form conversion neural network to determine low-level and high-level semantic characteristics of the paper forms. For example, one or more embodiments applies a digitized paper form to an encoder that outputs feature maps to a reconstruction decoder, a low-level semantic decoder, and one or more high-level semantic decoders. The reconstruction decoder generates a reconstructed layout of the digitized paper form. The low-level and high-level semantic decoders determine low-level and high-level semantic characteristics of each pixel of the digitized paper form, which provide a probability of the element type to which the pixel belongs. The semantic decoders then classify each pixel and generate corresponding semantic segmentation maps based on those probabilities. The system then generates a fillable digital form using the reconstructed layout and the semantic segmentation maps.

Abstract: A first system creates and sends encryption key data to multiple data sources. A second system receives data encrypted using the encryption key data from the multiple data sources; the data may include noise data such that, even if decrypted, the original data cannot be discovered. Because the encryption is additively homomorphic, the second system may create encrypted summation data using the encrypted data. The first system separately receives the noise data encrypted using the same technique as the encrypted data. The second system may send the encrypted summation data to the first system, which may then remove the noise data from the encrypted summation data to create unencrypted summation data.

Abstract: Systems and methods of selecting machine learning models/algorithms for a candidate dataset are disclosed. A computer system may access historical data of a set of algorithms applied to a set of benchmark datasets; select a first algorithm of the set of algorithms; apply the first algorithm to an input dataset to create a model of the input dataset; evaluate and store results of the applying; and add the first algorithm to a set of tried algorithms. The computer system may select a next algorithm of the algorithm set via submodular optimization based on the historical data and the set of tried algorithms; apply the next algorithm to the input dataset; capture a next result based on the applying; add the next result to update the set of tried algorithms; and repeat the submodular optimization. The procedure may continue until a termination condition is reached.

Abstract: A method of controlling computing operations in a deep neural network (DNN) is provided. A network structure of the DNN including a plurality of layers is analyzed. A hyper parameter is set based on the network structure and real-time context information of a system configured to drive the DNN. The hyper parameter is used for performing an early-stop function. Depth-wise jobs are assigned to resources included in the system based on the hyper parameter to execute the depth-wise jobs. Each of the depth-wise jobs includes at least a part of the computing operations. When an early-stop event for a first layer among the layers is generated while the plurality of depth-wise jobs are executed, a subset computing operations included in at least one second layer are performed and a remainder of the computing operations are stopped. The at least one second layer is arranged prior to the first layer.

Abstract: Some embodiments provide a method for training a machine-trained (MT) network that processes input data using network parameters. The method maps input instances to output values by propagating the instances through the network. The input instances include instances for each of multiple categories. For a particular instance selected as an anchor instance, the method identifies each instance in a different category as a negative instance. The method calculates, for each negative instance of the anchor, a surprise function that probabilistically measures a surprise of finding an output value for an instance in the same category as the anchor that is a greater distance from the output value for the anchor instance than output value for the negative instance. The method calculates a loss function that emphasizes a maximum surprise calculated for the anchor. The method trains the network parameters using the calculated loss function value to minimize the maximum surprise.

Abstract: An online system, such as a social networking system, generates shared models for one or more clusters of categories. A shared model for a cluster is common to the categories assigned to the cluster. In this manner, the shared models are specific to the group of categories (e.g., selected content providers) in each cluster while requiring a reasonable computational complexity for the online system. The categories are clustered based on the performance of a model specific to a category on data for other categories.

Abstract: An event-driven neural network including a plurality of interconnected core circuits is provided. Each core circuit includes an electronic synapse array that has multiple digital synapses interconnecting a plurality of digital electronic neurons. A synapse interconnects an axon of a pre-synaptic neuron with a dendrite of a post-synaptic neuron. A neuron integrates input spikes and generates a spike event in response to the integrated input spikes exceeding a threshold. Each core circuit also has a scheduler that receives a spike event and delivers the spike event to a selected axon in the synapse array based on a schedule for deterministic event delivery.

Abstract: A system receives application data to be used in requests made on behalf of an applicant to a selection of evaluator devices. The system includes a predictive model which predicts actual eligibility criteria for acceptance of a request by the evaluator devices, and is trained with a library of application data including previously evaluated requests and outcomes to the previously evaluated requests. The system compiles the application data into separate requests by synchronizing the application data and identifying a common core of data required by each selected evaluator device and compiling the common core of data along with particular requirements of individual evaluator devices. An applicant can thereby complete a multi-request application which generates requests to a plurality of evaluator devices and which avoids duplication of data storage and data transmission, and reduces effort required by the applicant. Implementations include students making applications for admission to academic institutions.