Abstract: A processor includes an execution unit for executing a message padding instruction including an operand field indicating a register buffering a message block segment of a message block to be padded and a mode field indicating which hash functions is to be applied to the message block. The execution unit includes a padding circuit configured to receive a message block segment from a register indicated by the operand field, where the message block spans multiple registers in a register file. Based on which hash function is indicated by the mode field, the padding circuit selects a byte location in the message block segment at which to insert at least one padding byte and inserts the at least one padding byte at the byte location within the message block segment. The message block segment as padded by the at least one padding byte is written back to the register file.

Abstract: Embodiments of the present invention provide computer-implemented methods, computer program product, and computer systems. One or more processors assign an identifier that specifies a number of resources and a category associated with a respective image layer of a plurality of image layers. One or more processors, in response to receiving a user request, identify image layers of the plurality of image layers that match the identifier based on dependencies between the plurality of image layers. One or more processors can retrieve matched layers based on the functionality of respective image layers and the dependencies of those respective image layers.

Abstract: Adaptive verifiable training enables the creation of machine learning models robust with respect to multiple robustness criteria. In general, such training exploits inherent inter-class similarities within input data and enforces multiple robustness criteria based on this information. In particular, the approach exploits pairwise class similarity and improves the performance of a robust model by relaxing robustness constraints for similar classes and increasing robustness constraints for dissimilar classes. Between similar classes, looser robustness criteria (i.e., smaller ?) are enforced so as to minimize possible overlap when estimating the robustness region during verification. Between dissimilar classes, stricter robustness regions (i.e., larger ?) are enforced. If pairwise class relationships are not available initially, preferably they are generated by receiving a pre-trained classifier and then applying a clustering algorithm (e.g., agglomerative clustering) to generate them.

Abstract: The present invention provides techniques for learning Mahalanobis distance similarity metrics from data for individually fair machine learning models. In one aspect, a method for learning a fair Mahalanobis distance similarity metric includes: obtaining data with similarity annotations; selecting, based on the data obtained, a model for learning a Mahalanobis covariance matrix ?; and learning the Mahalanobis covariance matrix ? from the data using the model selected, wherein the Mahalanobis covariance matrix ? fully defines the fair Mahalanobis distance similarity metric.

Abstract: A computer-implemented method includes receiving performing a fused modular multiply and add operation to compute d=((a*b)+c) % p, wherein a, b, and c, are provided as a set of operands. A first multiply-and-accumulate unit computes a binary multiplication to compute a*b. A second multiply-and-accumulate unit computes a first intermediate result by updating a result of the binary multiplication using p. An accumulator of a third multiply-and-accumulate unit is initialized with c. The third multiply-and-accumulate unit computes a second intermediate result using the first intermediate result and c. An adder unit subtracts a portion of the second intermediate result from a portion of the result of the binary multiplication. The output of the adder is provided as a result of the fused modular multiply and add operation.

Abstract: A computer implemented method creates microservices for an application. A number of processor units clusters programs and data structures for the application using runtime metadata to form groups of the programs and data structures. The runtime metadata is obtained from running the application. The number of processor units creates a design for the microservices for the application using the groups of the programs and the data structures.

Abstract: One or more systems, devices and/or methods of use provided herein relate to a device that can facilitate reduction of inter-qubit cross talk and/or allow for increased interaction strengths between qubits as compared to existing technologies. A device can comprise a qubit lattice comprising a plurality of repeated and connected unit cells, and the unit cells comprising individual sets of qubits, wherein the unit cells comprise different cross talk groups of qubits having qubit islands connected together by couplers in different orders, and wherein the different cross talk groups are repeated among the unit cells of the qubit lattice. A device can comprise a qubit lattice comprising a plurality of different, interconnected cross talk groups of qubits, wherein the different cross talk groups are repeated within the qubit lattice.

Abstract: Methods and systems for performing transfer learning with basis scaling and pruning. One method includes obtaining a pre-trained deep convolutional neural network (DCNN), decomposing each weight matrix of the DCNN, and decomposing each convolutional layer by applying the respective decomposed weight matrix to the convolution layer to form a first layer which comprises the left matrix for convolution, and a second layer which comprises the right matrix for convolution. The method also includes providing a basis-scaling convolutional layer having a weight matrix that is derived by a function of singular values and the right singular vectors and training the basis scaling factors of the basis-scaling convolutional layers.

Abstract: A computer-implemented method is provided for model training. The method includes training a second end-to-end neural speech recognition model that has a bidirectional encoder to output same symbols from an output probability lattice of the second end-to-end neural speech recognition model as from an output probability lattice of a trained first end-to-end neural speech recognition model having a unidirectional encoder. The method also includes building a third end-to-end neural speech recognition model that has a unidirectional encoder by training the third end-to-end neural speech recognition model as a student by using the trained second end-to-end neural speech recognition model as a teacher in a knowledge distillation method.

Abstract: A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations. The operations may include receiving an input, extracting features from the input, and mining object relations using the features. The operations may include determining feature vectors using the object relations and generating, using the feature vectors, an output indicating a target region, wherein the target region corresponds to the input.

Abstract: Embodiments for providing an enhanced codebase in a computing environment by a processor. One or more container specification files may be automatically updated with one or more changes to a codebase.

Abstract: Aspects of the present disclosure relate to collaborative rulesets for vehicles. A collaborative ruleset for a set of vehicles can be received, the collaborative ruleset defining relative positions each vehicle is required to maintain with respect to other vehicles within the set of vehicles. Sensor data indicating current positions of each vehicle within the set of vehicles while the set of vehicles are operating can be received. A command to display, on an augmented reality (AR) device of a user of a first vehicle within the set of vehicles, AR content for complying with the collaborative ruleset can be issued.

Abstract: A cache hit-miss prediction is determined for a memory access instruction using a predictor. The predictor includes a tracker for the memory access instruction. The tracker is used to provide a prediction confidence level of the cache hit-miss prediction for the memory access instruction. Using the tracker, the prediction confidence level of the cache hit-miss prediction is ascertained. Based on the prediction confidence level indicating the cache hit-miss prediction is to be used, the cache hit-miss prediction is provided to be used in instruction execution scheduling.

Abstract: Mechanisms are provided for performing a tournament selection process of a computer function. A request is received to execute the computer function on an input vector data structure, where a result of the computer function is provided by executing the tournament selection process. The input vector data structure is received, comprising a plurality of values where each value corresponds to a vector slot. An index vector data structure is received that comprises indices of the vector slots of the input vector. Iteration(s) of the tournament selection process are executed to identify a value in the input vector satisfying a criterion of the computer function. An operation is performed on the index vector data structure to generate an indicator vector data structure that uniquely identifies a slot in the input vector data structure that is a result of the computer function being executed on the input vector data structure.

Abstract: Techniques for improving a quantum simulator are provided. In one example, a system includes a simulation component and a snapshot component. The simulation component determines a set of random numbers and simultaneously provides the set of random numbers to an arithmetic decoder to perform a stochastic simulation process. The snapshot component generates snapshot data indicative of a state of the stochastic simulation process based on data associated with a stochastic branching point for the stochastic simulation process.

Abstract: A metal halide battery includes an intercalation anode, a cathode that includes a metal halide incorporated into an electrically conductive material, an oxidizing gas, and an electrolyte in contact with the intercalation anode, the cathode, and the oxidizing gas. The battery has a cycle life reaching 1000 cycles at a current density that enables the battery to charge within 10-15 minutes. Electrolytes that may be used in the metal halide batteries include (i) carbonate ester-based compounds with at least one ethyl group and an ion-conducting salt and/or (ii) at least one cyclic ester compound.

Abstract: Solutions preparing container images and data for container workloads prior to start times of workloads predicted through workload trend analysis. Local storage space on the node is managed based on workload trends, optimizing local storage of image files without requiring frequent reloading and/or deletion of image files, avoiding network intensive I/O operations when pulling images to local storage by workload scheduling systems. Systems perform collection of historical data including image and workload properties; analyze historical data for workload trends, including predicted start times, image files needed, number of nodes and types of nodes. Based on predicted future workload start times, nodes are selected from an ordered list of node requirements and workload properties.

Abstract: An enhanced threat disposition analysis technique is provided. In response to receipt of a security threat identified in an alert, a threat disposition score (TDS) is retrieved. The TDS is generated from a machine learning scoring model that is built from information about historical security threats, including historical disposition of one or more alerts associated with the historical security threats. The TDS is based in part on an effectiveness of a prior calculated TDS to predict a particular historical disposition associated with the alert. The system augments an alert to include the threat disposition score, optionally together with a confidence level, to generate an enriched alert. The enriched alert is then presented to the security analyst for handling directly. Preferably, the machine learning model is updated continuously as the system handles security threats, thereby increasing the predictive benefit of the TDS scoring.

Abstract: Aspects of the invention include techniques for providing a learned join cardinality estimation using a join graph representation. A non-limiting example method includes building a join cardinality estimation model. The model can be built by generating a training query having a known join cardinality, generating an adjacency matrix encoding a join graph of the training query, encoding one side of a diagonal axis of the adjacency matrix, and training the join cardinality estimation model using the encoded adjacency matrix and the known join cardinality. The method includes performing an inference using the join cardinality estimation model. The inference includes a predicted join cardinality for a query. The method includes executing a query execution plan for the query using the predicted join cardinality.

Abstract: A magneto-resistive random access memory with segmented bottom electrode includes a magnetic tunnel junction pillar above a first portion of a bottom electrode layer, the first portion of the bottom electrode layer includes a metal region. A sidewall spacer is disposed along sidewalls of the magnetic tunnel junction pillar and above a second portion of the bottom electrode layer including a metal-oxide region. The first portion of the bottom electrode layer composed of the metal region and the second portion of the bottom electrode layer composed of the metal-oxide region form the segmented bottom electrode.