Abstract: Various examples are provided related to identification and management of compliance-related information associated with data breach events. In one example, a method includes receiving a first data file collection associated with a first data breach event; generating information associated with presence or absence of protected information elements of all or part of the first data file collection and incorporating data files including the protected information elements in a second data file collection; analyzing data files selected from the second data file collection; and incorporating the information associated with the analysis into machine learning information that may be used for subsequent analysis of data file collections.

Abstract: According to some embodiments, a system may include a design experience data store containing electronic records associated with prior industrial asset item designs. A deep learning model platform, coupled to the design experience data store, may include a communication port to receive constraint and load information from a designer device. The deep learning platform may further include a computer processor adapted to automatically and generatively create boundaries and geometries, using a deep learning model associated with an additive manufacturing process, for an industrial asset item based on the prior industrial asset item designs and the received constraint and load information. According to some embodiments, the deep learning model computer processor is further to receive design adjustments from the designer device. The received design adjustments might be for example, used to execute an optimization process and/or be fed back to continually re-train the deep learning model.

Abstract: Systems and methods for detecting indirect bias in machine learning models are provided. A computer-implemented method includes: receiving, by a computer device, a user request to detect transitive bias in a machine learning model; determining, by the computer device, correlations of attributes of neighboring data not included in a dataset of the machine learning model; ranking, by the computer device, the attributes based on the determined correlations; and returning, by the computer device, a list of the ranked attributes to a user that generated the user request.

Abstract: Embodiments of the invention include methods, systems, and computer program products for predicting olfactory perception. A non-limiting example of the method includes receiving a library including a plurality of indexed olfactory descriptors. The method also includes receiving an olfactory target descriptor. The method also includes calculating a coefficient matrix and a perceptual distance between an indexed olfactory descriptor and an olfactory target descriptor. The method also includes generating a perceptual descriptor prediction for the olfactory target.

Abstract: An online system determines a stability metric that indicates overlap between the set of entities associated with a particular entity when embeddings have been adjusted due to modifications in the input data of an embedding model. The online system generates a stability score for the embedding model by computing a statistic for one or more stability metrics. The online system determines a stability metric for a particular content provider by identifying a first cluster of content providers in a set of first embeddings, and a second cluster of content providers in a set of second embeddings. The second embeddings are generated after modifications have been made to input data. The online system determines the stability metric based on an overlap between the first cluster and the second cluster of content providers. The stability score can be an indicator of model performance that can be used to select embedding models.

Abstract: Techniques are described for implementing automated control systems that manipulate operations of specified target systems, such as by modifying or otherwise manipulating inputs or other control elements of the target system that affect its operation (e.g., affect output of the target system). An automated control system may in some situations have a distributed architecture with multiple decision modules that each controls a portion of a target system, and may further have one or more components that interacts with one or more users to obtain a description of the target system, including restrictions related to the various elements of the target system, and one or more goals to be achieved during control of the target system. The component(s) then perform various automated actions to generate, test and deploy one or more executable decision modules to use in performing the control of the target system based on the user-specified information.

Abstract: A data architecture for use within a cognitive information processing system environment comprising: a plurality of data sources, the plurality of data sources comprising a public data source and a private data source, the public data source comprising publicly available healthcare information, the private data source comprising privately managed, company specific healthcare information; and, a cognitive data management module, the cognitive data management module accessing information from the plurality of data sources and providing the information to an inference and learning system.

Abstract: A system and method to explain model behavior, which can benefit not only those seeking to meet regulatory requirements when using machine learning models but also help guide users of the model to assess and increase robustness associated with model governance processes. The method described utilizes changes in behavior of a time series to identify the latent factors that drive explanation.

Abstract: A text log feature vector generator generates a text log feature vector on the basis of a text log. A numerical log feature vector generator generates a numerical log feature vector on the basis of a numerical log. A system feature vector generator generates a system feature vector on the basis of the text log feature vector and the numerical log feature vector. A learning unit learns a plurality of appearance values of the system feature vector to generate a system state model as a model indicating a state of the system. A determination unit determines the state of the system at determination target time on the basis of the system feature vector at the determination target time and the system state model.

Abstract: Predicting probable activity consequences is provided. Information is collected from data sources to identify various activities. Patterns of how any identified activity is linked with a corresponding event are detected based on analyzing the information. The patterns are indexed with data having a relationship to a particular event. Activity context information associated with a set of identified activities corresponding to the particular event is extracted from the information. A cognitive model of how the set of identified activities corresponding to the particular event are related to a set of activity consequences is generated. Probable activity consequences with degree of severity corresponding to the activity context information is predicted based on the cognitive model. A recommendation to perform a set of action steps to reduce impact of the probable activity consequences on different aspects of the activity context information associated with the set of identified activities is generated.

Abstract: Computing device and method for inferring a predicted number of data chunks writable on a flash memory before the flash memory wears out. The computing device stores a predictive model generated by a neural network training engine. A processing unit of the computing device executes a neural network inference engine, using the predictive model for inferring the predicted number of data chunks writable on the flash memory before the flash memory wears out based on inputs. The inputs comprise a total number of physical blocks previously erased from the flash memory, a size of the data chunk, and optionally an operating temperature of the flash memory. In a particular aspect, the flash memory is comprised in the computing device, and an action may be taken for preserving a lifespan of the flash memory based at least on the predicted number of data chunks writable on the flash memory.

Abstract: A machine learning system for evaluating at least one characteristic of a heart valve, an inflow tract, an outflow tract or a combination thereof may include a training mode and a production mode. The training mode may be configured to train a computer and construct a transformation function to predict an unknown anatomical characteristic and/or an unknown physiological characteristic of a heart valve, inflow tract and/or outflow tract, using a known anatomical characteristic and/or a known physiological characteristic the heart valve, inflow tract and/or outflow tract. The production mode may be configured to use the transformation function to predict the unknown anatomical characteristic and/or the unknown physiological characteristic of the heart valve, inflow tract and/or outflow tract, based on the known anatomical characteristic and/or the known physiological characteristic of the heart valve, inflow tract and/or outflow tract.

Abstract: A machine learning system for evaluating at least one characteristic of a heart valve, an inflow tract, an outflow tract or a combination thereof may include a training mode and a production mode. The training mode may be configured to train a computer and construct a transformation function to predict an unknown anatomical characteristic and/or an unknown physiological characteristic of a heart valve, inflow tract and/or outflow tract, using a known anatomical characteristic and/or a known physiological characteristic the heart valve, inflow tract and/or outflow tract. The production mode may be configured to use the transformation function to predict the unknown anatomical characteristic and/or the unknown physiological characteristic of the heart valve, inflow tract and/or outflow tract, based on the known anatomical characteristic and/or the known physiological characteristic of the heart valve, inflow tract and/or outflow tract.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that leverage artificial intelligence and machine learning to analyze and categorize events associated with an equipment asset, such as industrial machinery, to determine a status (e.g., insight) associated with the equipment asset, and to determine maintenance actions to be performed with respect to the equipment asset to prevent, or reduce the likelihood or severity of, occurrence of a fault at the equipment asset. Machine learning (ML) models may be trained to categorize events that are detected based on operating characteristics data associated with the equipment asset, to determine a status of the equipment asset, and to recommend one or more maintenance actions (or other actions). Output that indicates the maintenance actions may be displayed to a user or used to automatically initiate performance of one or more of the maintenance actions.

Abstract: An intrusion detection method for detecting an intrusion in data traffic on a data communication network parses the data traffic to extract at least one protocol field of a protocol message of the data traffic, and associates the extracted protocol field with a model for that protocol field. The model is selected from a set of models. An assessment is made to determine if a contents of the extracted protocol field is in a safe region as defined by the model, and an intrusion detection signal is generated in case it is established that the contents of the extracted protocol field is outside the safe region. The set of models may comprise a corresponding model for each protocol field of a set of protocol fields.

Abstract: Methods and systems for personalized trust recommendation based on a dynamic trust model. In an example embodiment, a trust framework can be derived from a set of use-case specific factors. Invasive data and non-invasive data can be collected from a user (or a group of users) based on activity data and profile data associated with the user. A dynamic trust profile can be created (or learned) based on the invasive data and the non-invasive data collected from the user. A recommended level of trustworthiness can be then provided to the user respect to a particular situation and/or entity (e.g. other users) within the trust framework based on the dynamic trust profile of the user and which is personalized for the user.

Abstract: An unsupervised model evaluation computer-implemented method, medium, and system are disclosed. In one computer-implemented method, S node vectors corresponding to S nodes from N node vectors obtained by using an unsupervised model are determined, where both N and S are positive integers. A neighboring node and a non-neighboring node of each of the S nodes is determined. Based on a node vector of a first S node and the neighboring node, a similarity between the first S node and the neighboring node as a positive sample predicted value is determined. Based on the node vector of the first S node and the non-neighboring node, a similarity between the first S node and the non-neighboring node as a negative sample predicted value is determined. The unsupervised model is evaluated based on the positive sample predicted value and the negative sample predicted value.

Abstract: A compatibility is ascertained between a configuration of a quantum processor (q-processor) of a quantum cloud compute node (QCCN) in a quantum cloud environment (QCE) and an operation requested in a first instruction in a portion (q-portion) of a job submitted to the QCE, the QCE including the QCCN and a conventional compute node (CCN), the CCN including a conventional processor configured for binary computations. In response to the ascertaining, a quantum instruction (q-instruction) is constructed corresponding to the first instruction. The q-instruction is executed using the q-processor of the QCCN to produce a quantum output signal (q-signal). The q-signal is transformed into a corresponding quantum computing result (q-result). A final result is returned to a submitting system that submitted the job, wherein the final result comprises the q-result.

Abstract: Methods, systems, and computer-readable media for anything-but matching using finite-state machines are disclosed. A rule base is compiled based at least in part on one or more rule patterns, including an anything-but rule pattern. The rule patterns comprise one or more field values. The rule base represents one or more finite-state machines comprising a plurality of states and encode a specified value for the anything-but rule pattern. A plurality of events are received comprising field values describing resources in a provider network. The rule patterns are evaluated against the events using the rule base. Events matching the specified value using the rule base are excluded from a set of events matching the anything-but rule pattern.

Abstract: A method for building a factual database of concepts and entities that are related to the concepts through a learning process. Training content (e.g., news articles, books) and a set of entities (e.g., Bill Clinton and Barack Obama) that are related to a concept (e.g., Presidents) is received. Groups of words that co-occur frequently in the textual content in conjunction with the entities are identified as templates. Templates may also be identified by analyzing parts-of-speech patterns of the templates. Entities that co-occur frequently in the textual content in conjunction with the templates are identified as additional related entities (e.g., Ronald Reagan and Richard Nixon). To eliminate erroneous results, the identified entities may be presented to a user who removes any false positives. The entities are then stored in association with the concept.