Abstract: Techniques for detecting and correcting anomalies in computer-based reasoning systems are provided herein. The techniques can include obtaining current context data and determining a contextually-determined action based on the obtained context data and a reasoning model. The reasoning model may have been determined based on one or more sets of training data. The techniques may cause performance of the contextually-determined action and, potentially, receiving an indication that performing the contextually-determined action in the current context resulted in an anomaly. The techniques include determining a portion of the reasoning model that caused the determination of the contextually-determined action based on the obtained context data and causing removal of the portion of the model that caused the determination of the contextually-determined action, to produce a corrected reasoning model.

Abstract: The techniques herein include using an input context to determine a suggested action and/or cluster. Explanations may also be determined and returned along with the suggested action. The explanations may include (i) one or more most similar cases to the suggested case (e.g., the case associated with the suggested action) and, optionally, a conviction score for each nearby cases; (ii) action probabilities, (iii) excluding cases and distances, (iv) archetype and/or counterfactual cases for the suggested action; (v) feature residuals; (vi) regional model complexity; (vii) fractional dimensionality; (viii) prediction conviction; (ix) feature prediction contribution; and/or other measures such as the ones discussed herein, including certainty. The explanation data may be used to determine whether to perform a suggested action.

Abstract: A method of training a quantum computer employs quantum algorithms. The method comprises loading, into the quantum computer, a description of a quantum Boltzmann machine, and training the quantum Boltzmann machine according to a protocol, wherein a classification error is used as a metric for the protocol.

Abstract: A feature data segment may be determined by applying a feature segmentation model to a test data observation. The feature segmentation model may be pre-trained via a plurality of training data observations and may divide the plurality of training data observations into a plurality of feature data segments. A predicted target value may be determined by applying to a test data observation a prediction model pre-trained via a plurality of training data observations. One or more distance metrics representing a respective distance between the test data observation and the feature data segment along one or more dimensions may be determined. The one or more distance metrics may be represented in a user interface. An updated prediction model and an updated feature segmentation model that both incorporate the test data observation and the training data observations may be determined based on user input.

Abstract: Systems and methods for predicting account action failures are disclosed. An example method is performed by one or more processors of a system and includes detecting a character sequence being entered for identifying an account to be used in an account action, extracting a set of subsequences from the character sequence, determining, for the character sequence and each subsequence extracted from the character sequence, a feature value for each of a predefined set of features for characterizing sequences, the determining based on a number of characters included in at least one portion of the character sequence, and generating, using the feature values as input to a model trained in conjunction with a machine learning (ML) algorithm, a predictive value suggestive of a likelihood that the detected character sequence, if submitted, will result in the account action failing.

Abstract: A dataset is received that is for processing by a machine learning model. A scoring payload for the dataset and that regards the machine learning model is also received. A set of features of the machine learning model is determined by analyzing the scoring payload. The scoring payload is structured in accordance with the set of features such that the structured scoring payload is ready for analysis for a monitor of the machine learning model.

Abstract: Techniques for detecting and correcting anomalies in computer-based reasoning systems are provided herein. The techniques can include obtaining current context data and determining a contextually-determined action based on the obtained context data and a reasoning model. The reasoning model may have been determined based on one or more sets of training data. The techniques may cause performance of the contextually-determined action and, potentially, receiving an indication that performing the contextually-determined action in the current context resulted in an anomaly. The techniques include determining a portion of the reasoning model that caused the determination of the contextually-determined action based on the obtained context data and causing removal of the portion of the model that caused the determination of the contextually-determined action, to produce a corrected reasoning model.

Abstract: There is a need for more effective and efficient prediction data analysis. This need can be addressed by, for example, solutions for performing first-occurrence multi-disease prediction. In one example, a method includes determining a per-event-type loss value for each event type of a group of event types; determining a cross-event-type loss value based at least in part on each per-event-type loss value; training a multi-event-type prediction model based at least in part on the cross-event type loss value; generating a first-occurrence prediction based at least in part on the multi-event-type prediction model, wherein the first occurrence-prediction comprises a first-occurrence prediction item for each event type of the group of event types; and performing one or more prediction-based actions based at least in part on the first-occurrence prediction.

Abstract: The techniques herein include using an input context to determine a suggested action. One or more explanations may also be determined and returned along with the suggested action. The one or more explanations may include (i) one or more most similar cases to the suggested case (e.g., the case associated with the suggested action) and, optionally, a conviction score for each nearby cases; (ii) action probabilities, (iii) excluding cases and distances, (iv) archetype and/or counterfactual cases for the suggested action; (v) feature residuals; (vi) regional model complexity; (vii) fractional dimensionality; (viii) prediction conviction; (ix) feature prediction contribution; (x) conviction ratio; (xi) contribution ratio; and/or other measures such as the ones discussed herein, including certainty. In some embodiments, the explanation data may be used to determine whether to perform a suggested action.

Abstract: The disclosed embodiments provide a system for streamlining machine learning. During operation, the system determines a resource overhead for a baseline version of a machine learning model that uses a set of features to produce entity rankings and a number of features to be removed to lower the resource overhead to a target resource overhead. Next, the system calculates importance scores for the features, wherein each importance score represents an impact of a corresponding feature on the entity rankings. The system then identifies a first subset of the features to be removed as the number of features with lowest importance scores and trains a simplified version of the machine learning model using a second subset of the features that excludes the first subset of the features. Finally, the system executes the simplified version to produce new entity rankings.

Abstract: The present disclosure relates to a concept for training one or more model parameters of a predictive parking difficulty model for different locations based on collected telemetry data. A ground truth ranking related to subjective parking difficulties at the different locations is obtained based on pairwise comparison of parking difficulties between pairs of the different locations by one or more humans. A prediction loss between a model ranking of the different locations obtained by the predictive parking difficulty model and the ground truth ranking is determined. The one or more model parameters are adjusted to minimize the prediction loss between the model ranking and the ground truth ranking.

Abstract: A computing system, computer-readable storage medium, and method for individual treatment effect (ITE) estimation under high-order interference in hypergraphs are described herein. The method includes accessing, via a processor, a hypergraph dataset including multi-way interactions among nodes within each hyperedge of a corresponding hypergraph, where the hypergraph dataset corresponds to a treatment assignment for each node. The method includes performing representation learning on the hypergraph dataset to control for confounders corresponding to features of each node and to learn a confounder representation for each node. The method also includes modeling a high-order interference representation for each node by propagating the learned confounder representation and the treatment assignment for each node through a hypergraph neural network.

Abstract: Methods, systems, and apparatus for improving recommendation systems. In one aspect, a method includes obtaining training data including data sets, wherein each data set includes a value that corresponds to the target feature and multiple values that each correspond to a respective input feature of a set of input features; assigning an input feature from the set of input features to a root node of the quantum decision tree based on calculated information gain values for the input features; creating a path from the root node by iteratively: calculating a cumulative information gain value for unassigned input features; identifying a maximal cumulative information gain value for the unassigned input features and assigning the unassigned input feature corresponding to the maximal cumulative information gain value to a current leaf node in the path creating a new leaf node.

Abstract: Systems and methods related to hardware-assisted gradient optimization using streamed gradients are described. An example method in a system comprising a memory configured to store weights associated with a neural network model comprising L layers, where L is an integer greater than one, a gradient optimizer, and a plurality of workers is described. The method includes during a single burst cycle moving a first set of gradients, received from each of the plurality of workers, from at least one gradient buffer to the gradient optimizer and moving weights from at least one buffer, coupled to the memory, to the gradient optimizer. The method further includes during the single burst cycle writing back the new weights, calculated by the gradient optimizer, to the memory. The method further includes during the single burst cycle transmitting the new weights, from the gradient optimizer, to each of the plurality of workers.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for obtaining data defining a sequence for an aptamer, the aptamer comprising a string of nucleobases; encoding the data defining the sequence for the aptamer as a neural network input; and processing the neural network input using a neural network to generate an output that characterizes how strongly the aptamer binds to a particular target molecule, wherein the neural network has been configured through training to receive the data defining the sequence and to process the data to generate predicted outputs that characterize how strongly the aptamer binds to the particular target molecule.

Abstract: A system for neural networks and virtual agents is provided. A computing device analyzes (i) one or more consumer requests and (ii) one or more underlying attributes. A computing device generates a threshold level of prediction of a response profile based on, but is not limited to, output data from the neural network. A computing device distributes the predicted response from the neural network to one or more cognitive service agents.

Abstract: One example method of operation may include identifying a number of features associated with information of one or more entities, accessing a probability distribution store comprising defined numerical ranges as potential possibilities for being paired with the features of the one or more entities, determining first probability distributions for each of the defined numerical ranges indicating probabilities that each defined numerical range is assigned to each entity having one or more of the features, determining second probability distributions for each of the defined numerical ranges indicating probabilities that each defined numerical range is assigned to each entity having one or more additional features, determining a merged probability distribution based on the first probability distributions and the second probability distributions, determining and storing one or more prediction sets based on the merged probability distribution, selecting one or more content items to display on a device interface based

Abstract: Disclosed embodiments are a computing system and a computer-implemented method for distributed training of a machine learning model over a plurality of computing nodes, in a plurality of iterations, characterized by gradient gap based mitigation of the gradient staleness problem. The disclosed method evaluates the staleness of the gradient based on the difference in gradients between a central point, for example an iteration's common starting point, and the points reached by the respective computing node during one or more iterations, and aggregates the update steps from the plurality of computing nodes, while giving more weight to computing nodes having a lesser change in the gradient.

Abstract: In an example, an apparatus comprises a plurality of execution units comprising and logic, at least partially including hardware logic, to traverse a solution space, score a plurality of solutions to a scheduling deep learning network execution, and select a preferred solution from the plurality of solutions to implement the deep learning network. Other embodiments are also disclosed and claimed.

Abstract: A system and method include techniques for: generating, by a quantum autoencoder, based on a set of quantum states encoded in a set of qubits, a decoder circuit that acts on a subset of the set of qubits, a size of the subset being less than a size of the set; and generating a reduced-cost circuit, the reduced-cost circuit comprising: (1) a new parameterized quantum circuit acting only on the subset of the set of qubits, and (2) the decoder circuit.