Abstract: Methods and systems for creating ensembles of hypersurfaces in high-dimensional feature spaces, and to machines and systems relating thereto. More specifically, exemplary aspects of the invention relate to methods and systems for generating supervised hypersurfaces based on user domain expertise, machine learning techniques, or other supervised learning techniques. These supervised hypersurfaces may optionally be combined with unsupervised hypersurfaces derived from unsupervised learning techniques. Lower-dimensional subspaces may be determined by the methods and systems for creating ensembles of hypersurfaces in high-dimensional feature spaces. Data may then be projected onto the lower-dimensional subspaces for use, e.g., in further data discovery, visualization for display, or database access.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a convolutional neural network (CNN). The system includes a plurality of workers, wherein each worker is configured to maintain a respective replica of each of the convolutional layers of the CNN and a respective disjoint partition of each of the fully-connected layers of the CNN, wherein each replica of a convolutional layer includes all of the nodes in the convolutional layer, and wherein each disjoint partition of a fully-connected layer includes a portion of the nodes of the fully-connected layer.

Abstract: A system and method is disclosed for knowledge engineering using a computerized graphical editor to manage and create knowledge-based systems containing a navigable graph of modal pages with conditional content and user interface knowledge. The invention enables the entire knowledge engineering workflow to be performed within a non-technical graphical environment and without requiring a computer programming or mathematical background. Further, the presentation of knowledge as modal pages allows for simple ontological discovery and end-user player operation. Once editing is complete, the method allows for the set of pages, variables, and settings of which the knowledge-based system is composed to be exported into an independently executable knowledge-based system player containing an embedded inference engine.

Abstract: A non-deterministic finite state machine module for use in a regular expression matching system. The system includes a computational unit implementing a non-deterministic finite state machine representing a regular expression, wherein the computational unit is configured to: receive an input data stream, wherein an occurrence of the regular expression is determined, and an activation signal; process the input data stream with respect to the non-deterministic finite state machine depending on the activation signal; and provide at least one branch data output for initializing an additional non-deterministic finite state machine module if the processing of an element of the input data stream according to the non-deterministic finite state machine results in a branching of a processing thread.

Abstract: A control method of the present disclosure is a control method of an information processing apparatus which includes a storage unit that stores predetermined resource information related to a resource required for a living activity of a user, the method including: an acquiring step of acquiring device information; an estimating step of estimating a living activity of the user; a competition extracting step of extracting a living activity group including living activities for which the resources are likely to compete among the living activities, based on the resource information; a resource judging step of judging whether a required resource has been secured for each of the living activities, based on the device information and the resource information; and an inhibition extracting step of extracting, as an inhibited living activity, a living activity for which it has been judged that the required resource has not been secured.

Abstract: Methods, systems and apparatus that provide for perceptual, cognitive, and motor behaviors in an integrated system implemented using neural architectures. Components of the system communicate using artificial neurons that implement neural networks. The connections between these networks form representations—referred to as semantic pointers—which model the various firing patterns of biological neural network connections. Semantic pointers can be thought of as elements of a neural vector space, and can implement a form of abstraction level filtering or compression, in which high-dimensional structures can be abstracted one or more times thereby reducing the number of dimensions needed to represent a particular structure.

Abstract: The disclosed embodiments include a method, apparatus, and computer program product for generating facies definition. One embodiment is a computer-implemented method that includes the steps of receiving well logging data indicative of one or more properties of geologic formations penetrated by one or more wellbores, wherein no assumptions are being introduced to the well logging data; determining a type well; developing an appropriate scaling of the well logging data based on the type well; creating a training set by drawing samples from the well logging data at random depths; modifying the training set to remove interfering data; performing an unsupervised classification procedure on the training set to group samples in the training set; comparing a suite of values of the well logging data in the groups to classify lithofacies of the type well; develop classification functions; and classifying unknown wells using the classification functions to generate the facies definition.

Abstract: A first representation of a feature processing recipe is received at a machine learning service. The recipe includes a section in which groups of variables on which common transformations are to be applied are defined, and a section in which a set of transformation operations are specified. The first representation of the recipe is validated based at least in part on a library of function definitions supported by the service, and an executable version of the recipe is generated. In response to a determination that the recipe is to be executed on a particular data set, a set of provider network resources is used to implement a transformation operation indicated in the recipe.

Abstract: A digital camera includes an image optimization engine configured to generate an optimized image based on a raw image captured by the digital camera. The image optimization engine implements one or more machine learning engines in order to select rendering algorithms and rendering algorithm arguments that may then be used to render the raw image.

Abstract: A dataset including at least one temporal event sequence is collected. A one-class sequence classifier f(x) that obtains a decision boundary is statistically learned. At least one new temporal event sequence is evaluated, wherein the at least one new temporal event sequence is outside of the dataset. It is determined whether the at least one new temporal event sequence is one of a normal sequence or an abnormal sequence based on the evaluation. Numerous additional aspects are disclosed.

Abstract: A biological signal processing apparatus includes: a provider which provides state probability which corresponds to a value of a first biological signal; an acquirer which acquires a first biological signal in time series from a living body and which acquires state probability in time series which corresponds to a value of the acquired first biological signal from the provider; and a determiner which acquires determination probability based on the state probability acquired by the acquirer and which performs determination whether a process is performed or not by using the determination probability.

Abstract: A spelling system derives a language model for a particular domain of structured data, the language model enabling determinations of alternative spellings of queries or other strings of text from that domain. More specifically, the spelling system calculates (a) probabilities that the various query entity types—such as STREET, CITY, or STATE for queries in the geographical domain—are arranged in each of the various possible orders, and (b) probabilities that an arbitrary query references given particular ones of the entities, such as the street “El Camino Real.” Based on the calculated probabilities, the spelling system generates a language model that has associated scores (e.g., probabilities) for each of a set of probable entity name orderings, where the total number of entity name orderings is substantially less than the number of all possible orderings.

Abstract: Techniques and mechanisms described herein facilitate adaptive fuzzy fallback stratified sampling. According to various embodiments, an actual or estimated minimum vertex cover of a feature dependency graph representing a dataset may be determined. The dataset may include a plurality of feature vectors and a plurality of features. Each feature vector may include a plurality of feature values that correspond with the features. The feature dependency graph may represent a plurality of conditional dependencies between the features. The minimum vertex cover may designate a subset of the features for strata selection. The feature vectors may be partitioned into a plurality of strata based on the designated subset of features. Each stratum may include one or more of the feature vectors. Each feature vector may be assigned to a corresponding stratum based on the values of the designated subset of features for the feature vector.

Abstract: An improved technique involves generating KBA questions based on facts from fact sources pointed to by an activity log. A KBA system obtains an activity log from a computer of a user in an organization. For example, the computer records the user's web browsing history. The KBA system then considers each entry in the activity log as a source of facts for deriving KBA questions. In the case of a web browsing history, the KBA system generates facts from web pages that the user visited. The KBA system then derives new KBA questions from the facts so derived.

Abstract: In an embodiment, information for use in identifying a plurality of sub-solvers may be acquired. The plurality of sub-solvers may be used in a first attempt to find at least one solution to a problem that may be defined in the acquired information. At least two of the sub-solvers in the plurality of sub-solvers may be of different sub-solver types. The sub-solvers may be identified based on the acquired information. One or more starting points for the identified sub-solvers may be identified and transferred to the identified sub-solvers. One or more outputs, that indicate one or more results associated with the first attempt to find at least one solution to the problem, may be acquired from the identified sub-solvers. One or more sub-solvers may be identified, based on the acquired one or more outputs, for use in a second attempt to find at least one solution to the problem.

Abstract: A technique for structuring a navigation data base in order to support incremental data updates is provided. A method implementation of the technique includes the steps of providing at least two data levels, wherein a first data level is associated with route links representing road segments of regional distance roads, partitioning the first data level into local tiles, wherein each local tile is associated with route links representing road segments of regional distance roads for a specific local geographic area, and interlinking those route links of neighboring local tiles that represent road segment portions of a regional distance road extending over neighboring local tiles.

Abstract: A system combines inputs from human processing and machine processing, and employs machine learning to improve processing of individual tasks based on comparison of human processing results. Once performance of a particular task by machine processing reaches a threshold, the level of human processing used on that task is reduced.

Abstract: A system and method provides video recommendations for a target video in a video sharing environment. The system selects one or more videos that are on one or more video playlists together with the target video. The video co-occurrence data of the target video associates the target video and another video on one or more same video playlists and frequency of the target video and another video on the video playlists is computed. Based on the video co-occurrence data of the target video, one or more co-occurrence videos are selected and ranked based on the video co-occurrence data of the target video. The system selects one or more videos from the co-occurrence videos as video recommendations for the target video.

Abstract: A method is used in analyzing device similarity. Data describing a device is received and a similarity analysis is applied to the data. Based on the similarity analysis, a measure of similarity between the device and a previously known device is determined.

Abstract: A method for directed mining of a heterogeneous dataset with a computer comprising: populating a rule base with known rules, wherein each rule has a context and a situation; populating a case base with known cases, wherein each case has a context and a situation, and wherein the case base is partitioned from the rule base; ascribing a natural language semantics to predicates of the known cases and rules; randomly transforming the known rules and the known cases to form new rules by extracting a maximum number of common predicates; segmenting the rules and the cases on the basis of shared predicates without making distinction between context and situation predicates; abducing new knowledge from the dataset by fuzzily matching the context of a new rule to a situation the new rule does not cover; and issuing a query to a user to supply missing predicates of the fuzzy match.