Abstract: The present disclosure includes methods and systems for generating digital predictive models by progressively sampling a repository of data samples. In particular, one or more embodiments of the disclosed systems and methods identify initial attributes for predicting a target attribute and utilize the initial attributes to identify a coarse sample set. Moreover, the disclosed systems and methods can utilize the coarse sample set to identify focused attributes pertinent to predicting the target attribute. Utilizing the focused attributes, the disclosed systems and methods can identify refined data samples and utilize the refined data samples to identify final attributes and generate a digital predictive model.

Abstract: Methods and apparatus to generate data for geographic areas are disclosed. An example method includes identifying a first geographic area for which a database does not include a model, determining a first data element of the first geographic area, identifying a first trained model corresponding to a second geographic area with the first data element, identifying a second trained model corresponding to a third geographic area with the first data element, mixing the first trained model and the second trained model to generate a composite model, and using the composite model to represent the first geographic area in the database.

Abstract: Examples of techniques for determining an interval duration and a training period length for log anomaly detection are disclosed. In one example implementation according to aspects of the present disclosure, a computer-implemented method may include: determining, by a processing resource, an interval duration for a time series from a plurality of message IDs; and determining, by the processing resource, a training period length based on the interval duration.

Abstract: Systems, methods, and apparatuses are provided for permeability prediction. The method acquires data associated with one or more geological formations, calculates, using processing circuitry and a trained Hidden Markov model, log-likelihood values to group the data into a plurality of clusters, and trains an artificial neural network for each of the plurality of clusters when the mode of operation is training mode. Further, the method acquires one or more formation properties corresponding to a geological formation, determines using the trained Hidden Markov model, a log-likelihood score associated with the one or more formation properties, identifies a cluster associated with the one or more formation properties as a function of the log-likelihood score, and predicts a permeability based at least in part on the one or more formation properties and a trained artificial neural network associated with the identified cluster when the mode of operation is forecasting mode.

Abstract: An analog neuromorphic circuit is disclosed having resistive memories that provide a resistance to an input voltage signal as the input voltage signal propagates through the resistive memories generating a first output voltage signal and to provide a resistance to a first error signal that propagates through the resistive memories generating a second output voltage signal. A comparator generates the first error signal that is representative of a difference between the first output voltage signal and the desired output signal and generates the first error signal so that the first error signal propagates back through the plurality of resistive memories. A resistance adjuster adjusts a resistance value associated with each resistive memory based on the first error signal and the second output voltage signal to decrease the difference between the first output voltage signal and the desired output signal.

Abstract: Managing answers in a question-answering environment is disclosed. Managing answers in the question-answering environment can include sorting, based on a set of answer categories for a subject matter, a first set of answers into a first answer category and a second set of answers into a second answer category. Managing answers in the question-answering environment can include determining, using the subject matter, a first category sequence including the first answer category and the second answer category, and establishing, based on the first category sequence, a first answer sequence established from a portion of the first set of answers from the first answer category and a portion of the second set of answers from the second answer category.

Abstract: A neural network is structured with a plurality of levels of nodes. Each level has a level-specific stabilization parameter that adjusts a learning rate, at a corresponding level, during training. The stabilization parameter has a value that varies inversely relative to a change in an objective training function during back-propagation of the error through the level.

Abstract: Computer-based models can be developed, deployed, and managed in an automated manner. For example, a model building tool can be selected based on the model building tool being compatible with one or more parameters. A first machine-learning model can be generated using the model building tool and trained using a training dataset. The first machine-learning model can then be used to perform a task. Thereafter, a new model-building tool can be selected based on the new model-building tool being compatible with the one or more parameters. A second machine-learning model can be generated using the new model-building tool and trained using the training dataset. The accuracy of the first machine-learning model can be compared to the accuracy of the second machine-learning model. Based on the second machine-learning model being more accurate, the second machine-learning model can be used to perform the particular task rather than the first machine-learning model.

Abstract: A data collecting device includes a receiver configured to receive an optical signal; an optical-to-electrical converter configured to convert the optical signal received by the receiver into an electrical signal; an analog-to-digital converter configured to convert the electrical signal into a digital signal; a data reducing circuit configured to reduce the digital signal output from the analog-to-digital converter; and a transmitter configured to transmit, to a managing device that manages the data collecting device, a signal obtained by reducing the digital signal by the data reducing circuit.

Abstract: A data processing system is disclosed for machine learning. The system comprises a sampling module (13) and a computational module (15) interconnected by a data communications link (17). The computational module is configured to store a parameter vector representing an energy function of a network having a plurality of visible units connected using links to a plurality of hidden units, each link being a relationship between two units. The sampling module is configured to receive the parameter vector from the first processing module and to sample from the probability distribution defined by the parameter vector to produce state vectors for the network. The computational module is further configured to receive the state vectors from the second processing module and to apply an algorithm to produce new data. The sampling and computational modules are configured to operate independently from one another.

Abstract: A method of generating the knowledge base used for a programmable fuzzy controller comprising the steps of determining the relevant input and output variables to be controlled; creating artificial potential fields for each of said variables; sampling each of said potential fields in order to generate fuzzy membership functions; compiling said fuzzy membership functions into fuzzy sets; and mapping inputs fuzzy set to output fuzzy sets through a rule base. The relevant input and output variables are including: minimum, maximum, and equilibrium values; an importance weight; a non-linearity value; a control direction; and information as to whether said variable is an input or output variable. Further provided is a programmable fuzzy controller whose fuzzy knowledge base is obtained by the method described.

Abstract: Techniques for generating a warning filter to filter the warnings output from a static program analysis tool are provided. In one example, a computer-implemented method comprises determining feature vector data for a set of warnings, wherein the set of warnings is generated in response to static analysis of a computer program, and wherein the feature vector data comprises a feature vector indicative of an attribute of a warning of the set of warnings. The computer-implemented method also comprises determining a warning filter that identifies a first subset of the set of warnings as representing true positives based on the feature vector data and classified warning data, and wherein the classified warning data represents a second subset of the set of warnings that have been classified to indicate whether respective members of the second subset are indicative of true positives.

Abstract: A method for inferring a location where each textual message was posted by a test user method includes partitioning an area into a plurality of sub-areas, associating textual messages posted by training users with respective sub-areas where each textual message was posted, extracting a keyword characterizing each sub-area among one or more keywords obtained from each textual message posted by the training users associated with each sub-area, constructing a feature vector of the given sub-area based on each extracted keyword, computing a transition probability for the given sub-area by time-series of location information associated with the textual messages posted by the training user, computing a plurality of scores of each location, using the feature vector, where each textual message was posted by the test user, and computing, based on the plural scores and the transition probability, time-series of locations where each textual message was posted by the test user.

Abstract: A learning method for providing a functional safety by warning a driver about a potential dangerous situation by using an explainable AI which verifies detection processes of a neural network for an autonomous driving is provided.

Abstract: An apparatus comprises a processing platform configured to implement a machine learning system for automated classification of documents comprising text data of at least one database. The machine learning system comprises a clustering module configured to assign each of the documents to one or more of a plurality of clusters corresponding to respective topics identified from the text data in accordance with at least one topic model, and an interface configured to present portions of documents assigned to a particular one of the clusters by the clustering module and to receive feedback regarding applicability of the corresponding topic to each of one or more of the presented portions on a per-portion basis. The topic model is updated based at least in part on the received feedback. The feedback may comprise, for example, selection of a confidence level for applicability of the topic to a given one of the presented portions.

Abstract: The disclosed embodiments relate to a technique for training a prognostic pattern-recognition system to detect incipient anomalies that arise during execution of a computer system. During operation, the system gathers and stores telemetry data obtained from n sensors in the computer system during operation of the computer system. Next, the system uses the telemetry data gathered from the n sensors to train a baseline model for the prognostic pattern-recognition system. The prognostic pattern-recognition system then uses the baseline model in a surveillance mode to detect incipient anomalies that arise during execution of the computer system. The system also uses the stored telemetry data to train a set of additional models, wherein each additional model is trained to operate with one or more missing sensors. Finally, the system stores the additional models to be used in place of the baseline model when one or more sensors fail in the computer system.

Abstract: Particular embodiments may locally store, at a client device of a first user, information associated with a plurality of nodes and a plurality of edges of a social graph received from a social-networking system. The first user may be associated with a first node of the social graph. The client device may detect that the first user is entering an input term. The client device may provide predictive typeahead results as the first user enters the input term. The predictive typeahead results may be based on the input term. Each predictive typeahead result may correspond to one of the nodes of the social graph stored locally on the client device. Each predictive typeahead result may include at least one image associated with the corresponding node.

Abstract: Generating loosely coupled parts by forming couplings between partial nodes in a hierarchical neural network in accordance with a check matrix of an error correcting code.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using dynamic minibatch sizes during neural network training. One of the methods includes receiving, by each of a plurality of host computer, a respective batch of training examples, each training example having zero or more features, computing, by each host computer, a minimum number of minibatches into which the host computer can divide the respective batch of training examples so that the host computer can process each minibatch using an embedding layer of the neural network without exceeding available computing resources, determining a largest minimum number of minibatches (N) into which any host computer can divide its respective batch of training examples, generating, by each host computer, N minibatches from the respective batch of training examples received by the host computer, and processing, by each host computer, the N minibatches using the embedding layer.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining a control policy for a vehicles or other robot through the performance of a reinforcement learning simulation of the robot.