Abstract: A technique for generating a performance prediction of a machine learning model with uncertainty intervals includes obtaining a first model configured to perform a task and a production dataset. At least one metric predicting a performance of the first model at performing the task on the production dataset is generated using a second model. The second model is a meta-model associated with the first model. At least one value predicting an uncertainty of the at least one metric predicting the performance of the first model at performing the task on the production dataset is generated using a third model. The third model is a meta-meta-model associated with the second model. An indication of the at least one metric and the at least one value is provided.

Abstract: Machine teaching in an embodiment can include receiving a user annotated concept for a given image in given context. The given image can be broken into parts and classified. Relationships can be determined associated with the parts. The created relationships can be stored along with the user annotated concept in a knowledge base. One or more similar images can be annotated using the parts and relationships. A second image associated the given context can be retrieved, decomposed into parts. The parts can be classified. Relationships can be determined associated with the second image's parts. Classifications and relationships associated with the second image's parts can be compared with classifications and relationships associated with the given image's parts. Based on comparing, the second image can be annotated with the user annotated concept for the given image.

Abstract: Aspects of the invention include systems and methods to obtain meta features of a dataset for training in a deep learning application. A method includes selecting an initial search space that defines a type of deep learning architecture representation that specifies hyperparameters for two or more neural network architectures. The method also includes applying a search strategy to the initial search space. One of the two or more neural network architectures are selected based on a result of an evaluation according to the search strategy. A new search space is generated with new hyperparameters using an evolutionary algorithm and a mutation type that defines one or more changes in the hyperparameters specified by the initial search space, and, based on the mutation type, the new hyperparameters are applied to the one of the two or more neural networks or the search strategy is applied to the new search space.

Abstract: A mechanism is provided for implement a discrepancy detection mechanism for detecting discrepancies between clinical notes and administrative records. Clinical concepts are extracted from the clinical notes and the administrative records in a patient's electronic medical records (EMRs). The extracted clinical concepts are filtered based on semantic type information to identify concepts that reference diseases or syndromes while also removing negated instances. Utilizing the positive mentions of diseases in clinical notes, the positive mentions of diseases or syndromes in the clinical notes are compared against each positive entry in the administrative records. A discrepancy summary is then generated for diseases or syndromes that failed to translate correctly from clinical notes to the administrative records in the patient's EMRs.

Abstract: A network architecture may receive situational data. The network architecture may acquire participant data associated with a participant. The network architecture may accept object data associated with an object. The network architecture may generate likelihood of infectiousness of the object based on the participant data and the object data. The network architecture may display the likelihood of infectiousness to one or more users.

Abstract: A technique relates to an integrated circuit (IC). The IC includes a conductive line formed on a conductive via, the conductive line being formed though a dielectric material. The IC includes an etch stop layer having one or more extended portions intervening between one or more edge portions of the conductive line and the conductive via, the one or more edge portions being at a periphery of the conductive line and the conductive via, the etch stop layer including a higher dielectric breakdown than the dielectric material. The one or more extended portions of the etch stop layer cause the conductive line to be formed with a bottom part having a reduced dimension than an upper part of the conductive line.

Abstract: An apparatus for thermal interface material detection includes a heat dissipating device stack up that includes a heat dissipating device, a thermal interface material, a heat generating component, and a printed circuit board. The heat dissipating device is disposed on the thermal interface material, the thermal interface material is disposed on the heat generating component, and the heat generating component is disposed on the printed circuit board. A channel in a body of the heat dissipating device includes an embedded conductive probe, where a first end of the embedded conductive probe leads to a lower surface of the body of the heat dissipating device and a second end of the embedded conductive probe leads to an upper surface of the body of the heat dissipating device.

Abstract: Key management for encrypted data. A node, such as a storage device, obtains a shared key to be used in cryptographic operations. The obtaining includes using an identifier of another node, such as a host of the computing environment, and a unique identifier of the shared key to obtain the shared key. The obtained shared key is then used in one or more cryptographic operations.

Abstract: A computer-implemented method for automatically pairing two devices is disclosed. The computer-implemented method includes detecting a first type of movement from a first device. The computer-implemented method further includes determining that the first device is located within a threshold distance of a second device when the first type of movement from the first device is detected. The computer-implemented method further includes determining whether an auto-pairing policy matches the first type of movement from the first device and the threshold distance between the first and second devices. The computer-implemented method further includes, responsive to determining that the auto-pairing policy matches the first type of movement from the first device and the threshold distance between the first and second devices, automatically pairing the first device and the second device.

Abstract: A system includes an authenticated encryption layer comprising logic configured to encrypt data received at the authenticated encryption layer from an authorized application at a source node. The data is encrypted using a first key to obtain first encrypted data. The logic is configured to encrypt the first encrypted data using a second key to obtain second encrypted data and generate a watermark for the first encrypted data and/or a watermark for the second encrypted data. The logic is configured to generate a watermark token for the first encrypted data and/or a watermark token for the second encrypted data.

Abstract: Multimedia stream enhancement includes automatically analyzing a multimedia stream and identifying items of interest therein, building metadata, about the stream, that describes the identified items of interest and includes indications of each item of interest and a respective location of that item of interest, providing, by a stream producer device, the stream and the metadata to stream consumer devices, receiving feedback from at least one stream consumer device as the stream producer device provides the stream to the at least one stream consumer device, and using the feedback to generate updated metadata about the stream for provision to one or more stream consumer devices of the stream consumer devices.

Abstract: Aspects include a cryptographic hardware security module having a secure embedded heat pipe and methods for assembling the same. The cryptographic hardware security module can include a printed circuit board having one or more components. The cryptographic hardware security module can further include an encapsulation structure having a top can and a bottom can. The top can is fixed to a first surface of the printed circuit board and the bottom can is fixed to second surface of the printed circuit board opposite the first surface. A heat pipe is positioned between the top can and the component. The heat pipe includes two or more 180-degree bends. A portion of the heat pipe extends beyond a secure region of the encapsulation structure.

Abstract: Using interaction profiling data and deployment state data of a software application, an observability module configuration plan is generated, the configuration plan comprising an event to be observed and an observability parameter. Using infrastructure state estimation data of the infrastructure on which the software application is executing, the observability module configuration plan is adjusted, the adjusting resulting in an adjusted reconfiguration plan, the adjusted reconfiguration plan comprising a second event to be observed, the second event associated with a node failure within the infrastructure. A set of observability modules is reconfigured according to the adjusted reconfiguration plan, the reconfiguring comprising causing an observability module in the set of observability modules to be activated to monitor the event.

Abstract: Using a trained keyphrase generation model, a set of keyphrases corresponding to an input document is generated, a keyphrase in the set of keyphrases comprising a word summarizing a portion of a document. A relevance score measuring a similarity between the keyphrase and the document is calculated for a keyphrase in the set of keyphrases. The relevance score is adjusted according to a diversity balancing function.

Abstract: An embodiment analyzes a predictive model and its input data for the predictive model using an explainability algorithm resulting in a feature importance value of a feature. The embodiment analyzes feature values of the feature using a generalization function resulting in a set of candidate feature values. The embodiment determines an alternative feature based on the set of candidate feature values, wherein the alternative feature is a generalization of the feature. The embodiment compares an accuracy of the predictive model to a threshold performance value and, responsive to the accuracy being above the threshold performance value, maps feature values in the input data that are in the set of candidate feature values to a generalized representative value in the generalized domain.

Abstract: An embodiment includes generating feature explainability data associated with a feature in a set of features of a sample represented by input data for a predictive model, where the explainability value is based at least in part on a significance of the feature for an output of the predictive model for the sample. The embodiment extracts feature value data from the input data that is representative of a feature value of the feature for the sample. The embodiment constructs a generalization group comprising the feature of the sample by detecting that the feature value and the explainability value satisfy a predetermined condition. The embodiment generates generalized domain data indicative of a generalized domain that comprises a generalized feature value that corresponds to a plurality of feature values in a domain of the generalization group such that the generalized feature is a generalization of the feature of the sample.

Abstract: A generated signal is injected into a first network node in a set of network nodes. The generated signal comprises a predetermined pattern, the predetermined pattern comprises a plurality of time periods, wherein during each time period in the plurality of time periods a first data traffic is prevented from exiting the first network node. By monitoring data flow within the set of network nodes while the generated signal is being injected, a correlation with the generated signal is detected, the correlation correlating a second network node with the first network node. The second network node is associated with the first network node. Responsive to the association, traffic from the second network node to the set of network nodes is blocked.

Abstract: An embodiment monitors an operational state of a processor-based system and identifies a system error that satisfies a reboot condition for a reboot event. The embodiment generates debug data indicative of the operational state of the system when the system error occurred. The embodiment stores the debug data in a memory that retains data during the reboot event. The embodiment intercepts a debug data requests from an untrusted entity, thereby preventing the untrusted entity from directly accessing the debug data in the memory. The embodiment analyzes the debug data using a sensitive data detection process where the analyzing detects sensitive data in the debug data. The embodiment generates modified debug data by performing a data protection process on the debug data and then sends, as a response to the debug data requests, the modified debug data to the untrusted entity.

Abstract: A computer-implemented system, platform, method and computer program product for optimizing a data analytics fraud prediction/detection pipeline that includes a combination of a classical machine learned classifier model with a quantum machine learned model to optimize the performance of the fraud prevention model. The feature selection uses different feature maps: one determined by the classic classifier and the other determined by the quantum model implementation that exploits the entanglement quantum property. The quantum method can include a quantum support vector machine implementing a built feature forward algorithm that uses a quantum kernel estimate for feature mapping. This quantum model can be run on a quantum computer or quantum simulator that can run a quantum algorithm built for extracting feature importance.

Abstract: A computer-implemented method according to one embodiment includes identifying a job creation request within a system; determining a current amount of available resources within the system; and conditionally deploying a reusable group of containers for the job, based on the current amount of available resources for the system.