Systems and methods of selecting machine learning models/algorithms for a candidate dataset are disclosed. A computer system may access historical data of a set of algorithms applied to a set of benchmark datasets; select a first algorithm of the set of algorithms; apply the first algorithm to an input dataset to create a model of the input dataset; evaluate and store results of the applying; and add the first algorithm to a set of tried algorithms. The computer system may select a next algorithm of the algorithm set via submodular optimization based on the historical data and the set of tried algorithms; apply the next algorithm to the input dataset; capture a next result based on the applying; add the next result to update the set of tried algorithms; and repeat the submodular optimization. The procedure may continue until a termination condition is reached.

An apparatus comprises: a prediction storage structure comprising a plurality of prediction state entries representing instances of predicted instruction behaviour; prediction training circuitry to perform a training operation to train the prediction state entries based on actual instruction behaviour; prediction circuitry to output at least one control signal for triggering a speculative operation based on the predicted instruction behaviour represented by a prediction state entry for which the training operation has provided sufficient confidence in the predicted instruction behaviour; an allocation filter comprising at least one allocation filter entry representing a failed predicted instruction behaviour for which the training operation failed to provide said sufficient confidence; and prediction allocation circuitry to prevent allocation of a new entry in the prediction storage structure for a failed predicted instruction behaviour represented by an allocation filter entry of the allocation filter.

Embodiments are directed to a method of performing autonomous learning for updating input features used for an artificial intelligence model, the method comprising receiving updated data of an information space that includes a graph of nodes having a defined topology, the updated data including historical data of requests to the artificial intelligence model and output results associated with the requests, wherein different categories of input data corresponds to different input nodes of the graph. The method may further comprise updating edge connections between the nodes of the graph by performing path optimizations that each use a set of agents to explore the information space over cycles to reduce a cost function, each connection including a strength value, wherein during each path optimization, path information is shared between the rest of agents at each cycle for determining a next position value for each of the set of agents in the graph.

A learning unit 81 generates a plurality of sample groups from samples to be used for learning, and generates a plurality of prediction models while inhibiting overlapping of a sample group to be used for learning among the generated sample groups. An optimization unit 82 generates an objective function based on an explained variable predicted by the prediction model and based on a constraint condition for optimization, and optimizes a generated objective function. An evaluation unit 83 evaluates an optimization result by using a sample group that has not been used in learning of a prediction model used for generating an objective function targeted for the optimization.

A learning unit 81 generates a plurality of sample groups from samples to be used for learning, and generates a plurality of prediction models while inhibiting overlapping of a sample group to be used for learning among the generated sample groups. An optimization unit 82 generates an objective function based on an explained variable predicted by the prediction model and based on a constraint condition for optimization, and optimizes a generated objective function. An evaluation unit 83 evaluates an optimization result by using a sample group that has not been used in learning of a prediction model used for generating an objective function targeted for the optimization.

A failure analysis device 10 is provided with an identification unit 11 that discriminates whether a predetermined failure has occurred on the basis of a learning model for discriminating the presence or absence of an occurrence of the predetermined failure learned by using a cause attribute which is associated with a cause of the predetermined failure and on the basis of a value of the attribute, and that identifies the cause of the predetermined failure discriminated to have occurred and countermeasures therefor.

Systems and methods include determination of a first plurality of sets of data, each including values associated with respective ones of a first plurality of features, partial training of a first machine-learning model based on the first plurality of sets of data, determination of one or more of the first plurality of features to remove based on the partially-trained first machine-learning model, removal of the one or more of the first plurality of features to generate a second plurality of sets of data, partial training of a second machine-learning model based on the second plurality of sets of data, determination that a performance of the partially-trained second machine-learning model is less than a threshold, addition, in response to the determination, of the one or more of the first plurality of features to the second plurality of sets of data, and training of the partially-trained first machine-learning model based on the first plurality of sets of data.

Embodiments described a field extraction system that does not require field-level annotations for training. Specifically, the training process is bootstrapped by mining pseudo-labels from unlabeled forms using simple rules. Then, a transformer-based structure is used to model interactions between text tokens in the input form and predict a field tag for each token accordingly. The pseudo-labels are used to supervise the transformer training. As the pseudo-labels are noisy, a refinement module that contains a sequence of branches is used to refine the pseudo-labels. Each of the refinement branches conducts field tagging and generates refined labels. At each stage, a branch is optimized by the labels ensembled from all previous branches to reduce label noise.

A computer-implemented method is presented for automatically generating alerting rules. The method includes identifying, via offline analytics, abnormal patterns and normal patterns from history logs based on machine learning, statistical analysis and deep learning, the history logs stored in a history log database, automatically generating the alerting rules based on the identified abnormal and normal patterns, and transmitting the alerting rules to an alerting engine for evaluation. The method further includes receiving a plurality of online log messages from a plurality of computing devices connected to a network, augmenting the plurality of online log messages, and extracting information from the plurality of augmented online log messages to be provided to the alerting engine, the alerting engine configured to approve and enforce the alerting rules automatically generated by the offline analytics processing.

A machine learning system and method are provided for using fiber-optic Distributed Acoustic Sensor (DAS) and Distributed Temperature Sensor (DTS) data to predict pressure along one or more optical fiber cables. DAS and DTS data are used to train a model to predict pressure based on the DAS and DTS data corresponding to optical signals carried on the fiber cable(s). The trained model is then used to process acquired DAS and DTS data corresponding to optical signals carried on the fiber cable(s) to the predict pressure distributed along the cable(s).