Abstract: Models to predict quality of service metrics are disclosed. A response time is predicted using an occupancy status of an infrastructure and models that have been trained to predict a response time. Estimating a metric, such as the response time, allows the infrastructure to adjust to issues such that requests better satisfy quality of service requirements.

Abstract: A system and method place an incoming workload within a data center having infrastructure elements (IEs) for execution. Instrumentation data are collected for both individual IEs in the data center, and workload instances executing on each of these IEs. These data are used to train a future load model according to machine learning techniques, especially supervised learning. Future loads, in turn, are used to train a ranking model that ranks IEs according to suitability to execute additional workloads. After receiving an incoming workload, the first model is used to predict, for each IE, the load on its computing resources if the workload were executed on that IE. The resulting predicted loads are then fed into the second model to predict the best ranking of IEs, and the workload is placed on the highest-ranked IE that is available to execute the workload.

Abstract: Machine learning model training using real and/or synthetic data is disclosed. Nodes contribute data to a central machine learning service. The data is used to train corresponding models whose generators, when trained, are configured to generate synthetic data according to a node's distribution. When a node is unavailable or for other reasons, the data contributed by the node for retraining a machine learning model includes at least some synthetic data from an enabled generator.

Abstract: One example method includes receiving a rule-set, including a combination of rules, that was determined to occur in a set of ground truth documents, applying the rule-set to a new document that was not included in the set of ground truth documents, determining whether or not a rule in the rule-set succeeded or failed when applied to a word in the new document, and when the rule is determined to have failed, identifying the failed rule, identifying a confidence level in the determination that the rule failed, and when the confidence level is below a threshold confidence level, identifying the word, to which the failed rule was applied, as a candidate for verification by a human.

Abstract: Techniques described herein relate to a method for predicting field values of documents. The method may include identifying a field prediction model generation request; obtaining, training documents from a document manager; selecting a first training document; making a first determination that the first training document is a text-based document; performing text-based data extraction to identify first words and first boxes included in the first training document; identifying first keywords and first candidate words included in the first training document based on the first words and the first boxes; and generating a first annotated training document using the first keywords and the first candidate words, wherein the first annotated training document comprises color-based representation masks for the first keywords, the first candidate words, and first general words included in the first training document.

Abstract: One example method includes, for each document in a group of annotated documents, extracting a set of words from the annotated document, and each of the words is positioned in a respective field of the annotated document. The method further includes using an aggregation function to determine, for one of the fields, a similarity of each one of the annotated documents to all of the other annotated documents, creating a document layout graph with nodes that each correspond to a respective annotated document, and each node is connected to all other nodes for which a similarity threshold for the one field has been met, and running an algorithm on the document layout graph to identify a clique of the annotated documents, and each annotated document in the clique has a similar layout to respective layouts of the other annotated documents in the clique.

Abstract: One example method includes receiving parameter values relating to execution of a simulation of a quantum algorithm, deriving quantum attributes from the parameter values, generating, based on the quantum attributes, a classical computing resource prediction, and translating the classical computing resource prediction into elements of a classical computing infrastructure. The classical computing infrastructure may be sized and configured to support computationally efficient, and cost efficient, execution of the simulation of the quantum algorithm.

Abstract: A system for accelerator functions as a service is disclosed. The system may receive a job that includes a computer (CPU) portion and an accelerator portion. When the accelerator portion is performed, an execution time associated with a time for the accelerator to return results is determined. Resources or a portion thereof allocated to the job, or the CPU portion are freed or reallocated to another job at least during the execution time. The job is queued to receive resources when the results are received from the accelerator.

Abstract: Techniques for table row identification using machine learning are disclosed herein. For example, a method can include detecting a table body in a document by processing the document using a machine learning (ML)-based table body model; predicting an initial table row index for one or more words among a plurality of words obtained in the document, wherein the one or more words are determined to be within the table body; and determining a table row index for the one or more words using an ML-based table row model that is trained based on the predicted initial table row index for the one or more words.

Abstract: One method includes extracting word-elements, each corresponding to a respective element of a ground truth cell-item array from an annotated document, applying logic rules to the extracted word-elements so that the applicability, or not, of each logic rule to each element of the ground truth cell-item array is determined. Based on the applying of the logic rules, metrics are obtained that indicate, for each word-element of the annotated document, the applicability of the logic rules, and the frequency with which applicable logic rules is satisfied. A first aggregation process is performed that aggregates the metrics across a group of unstructured, and annotated, documents, and a second aggregation process is performed that aggregates the metrics regarding a model-generated cell item array that was created based on the group of annotated documents. Finally, respective outcomes of the first and second aggregation processes are compared so as to identify logic rules of interest.

Abstract: One example method includes selecting items to be repatriated from a cloud site to an on-premises site, and the items include a workload and a data set accessed by the workload, transmitting a repatriation request from the on-premises site to the cloud site, and the repatriation request identifies the selected items, receiving, by the on-premises site from the cloud site, a compressed data set which includes the data set in compressed form, receiving, by the on-premises site from the cloud site, a compressed workload which includes the workload in compressed form, and the compressed workload and the compressed data set have been compressed with a compression algorithm automatically selected based on content, and/or context, of data in the data set, decompressing, at the on-premises site, the compressed data set and the compressed workload, and deploying the decompressed data set and the decompressed workload locally at the on-premises site.

Abstract: One example method includes accessing input data elements from logs that identify user problems with computing system components, the data elements each associated with a respective original class label that identifies a class of computing system components to which the data element relates, the respective original class labels forming a group of class labels, and a first of the original class labels is overrepresented in the group, and reducing overrepresentation of the first original class label in the group by creating an arbitrary aggregation of some of the class labels that includes the first original class label. The method includes creating, based on a hierarchical modeling structure, prepared data in which an original class label is replaced by the aggregation. Next a hierarchical model and benchmark model are trained, and each model generates respective predictions for comparison. An inferencing process is performed to determine which predicted label will be used.

Abstract: One example method includes receiving stream data batches at a client node. The client node determines if the stream data batches are compressible. For the compressible stream data batches, a request is sent to a server node for an on-demand stream compression service, the request including an indicator of a stream data type for the compressible data batches. The on-demand stream compression service is deployed and launched at the client node. The on-demand stream compression service includes a compressor pool of compressors that are able to compress the stream data type of the compressible stream data batches. A compressor of the compressor pool is selected and used to compress the compressible stream data batches. The compressed stream data batches are sent to the server node.

Abstract: Facilitating detection of anomalies of a target entity is provided herein. A system can comprise a processor and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations. The operations can comprise training a model on a first set of variables that are constrained by a second set of variables. The second set of variables can characterize elements of a defined entity. The first set of variables can define a normality of the defined entity. The operations also can comprise employing the model to identify expected parameters and unexpected parameters associated with the defined entity to at least a defined level of confidence.

Abstract: Techniques are disclosed for predicting a table column using machine learning. For example, a system can include at least one processing device including a processor coupled to a memory, the processing device being configured to implement the following: determining a local word density for words in a table, the local word density measuring a count of other words in a first region surrounding the words; determining a local numeric density for the words, the local numeric density measuring a proportion of digits in a second region surrounding the words; determining semantic associations for the words by processing the words using an ML-based semantic association model trained based on surrounding words in nearby table columns and rows; and predicting a table column index for the words by processing the table using an ML-based table column model trained based on the local word density, local numeric density, and semantic association.

Abstract: One example method includes collecting annotated unstructured documents that each include a table with words whose respective column indices are known, using the documents to train a model to detect a table header in a given document, identifying, by the model, a region of a document that corresponds to a table header in a new document that is not part of the training data, using an algorithm to perform a segmentation process on the table header that identifies column boundaries in the table header, and to use the identified column boundaries to preliminarily assign a respective column index to each word in the table header. Finally, a graph neural network model is run on a graph that includes the words in the table, and running the graph neural network generates a refined prediction of a respective column index for each of the words in the table of the new document.

Abstract: Techniques for table row identification using machine learning are disclosed herein. For example, a method can include detecting a table body in a document by processing the document using a machine learning (ML)-based table body model; predicting an initial table row index for one or more words among a plurality of words obtained in the document, wherein the one or more words are determined to be within the table body; and determining a table row index for the one or more words using an ML-based table row model that is trained based on the predicted initial table row index for the one or more words.

Abstract: One example method includes receiving a computation workflow defined by a graph that includes quantum computing nodes, receiving a catalogue of quantum computing instances that are available in a hybrid classic-quantum computation infrastructure, transforming the graph to create a first graph transformation, and each of the quantum computing nodes is assigned a respective candidate resource allocation that identifies candidate resources operable to execute a respective quantum algorithm associated with that quantum computing node, and the transforming is performed using information from the catalogue, and optimizing the computation workflow by selecting, for each of the quantum computing nodes, a resource from the candidate resource allocation associated with that quantum computing node, and the optimizing includes transforming the first graph transformation to create a second graph transformation that specifies the selected resources for each node.

Abstract: A compression system is disclosed. A compression service removes compression responsibilities from an application. The compression system can deploy virtual network engines to locations near the applications. The virtual network engines compress the data using a compressor selected from multiple compressors. The compressed data can then be transmitted, decompressed, and delivered to the destination.

Abstract: One example method includes file specific compression selection. Compression metrics are generated for a chunk of a file. Using a set of training data, the compression metrics are corrected using a correction factor to determine estimated file compression metrics. A compressor is then selected to compress the file based on at least the estimated file compression metrics.