Abstract: An object-extraction method includes generating multiple partition objects based on an electronic document, and receiving a first user selection of a data element via a user interface of a compute device. In response to the first user selection, and using a machine learning model, a first subset of partition objects from the multiple partition objects is detected and displayed via the user interface. A user interaction, via the user interface, with one of the partition objects is detected, and in response, a weight of the machine learning model is modified, to produce a modified machine learning model. A second user selection of the data element is received via the user interface, and in response and using the modified machine learning model, a second subset of partition objects from the multiple partition objects is detected and displayed via the user interface, the second subset different from the first subset.

Abstract: By way of example, the technology disclosed by this document is capable of receiving signal data from one or more sensors; inputting the signal data into an input layer of a deep neural network (DNN), the DNN including one or more layers; generating, using the one or more layers of the DNN, one or more spatial representations of the signal data; generating, using one or more hierarchical temporal memories (HTMs) respectively associated with the one or more layers of the DNNs, one or more temporal predictions by the DNN based on the one or more spatial representations; and generating an anticipation of a future outcome by recognizing a temporal pattern based on the one or more temporal predictions.

Abstract: A machine learning device capable of preventing spoofing of an operator to secure safety during an operation of a robot is provided. A machine learning device includes: an input data acquisition means that acquires, as input data, operation data including a measurement value related to a movement of at least a portion of a body of the operator and a shape of the body, detected when the operator is caused to perform a predetermined operation associated with a training operation panel of the robot controller; a label acquisition means that acquires identification information of the operator as a label; and a learning means that constructs a learning model that performs user identification for authenticating operators of the robot controller by performing supervised learning using a pair of the input data and the label as training data.

Abstract: Techniques in advanced deep learning provide improvements in one or more of accuracy, performance, and energy efficiency. An array of processing elements performs flow based computations on wavelets of data. Each processing element has a compute element and a routing element. Each compute element has memory. Each router enables communication via wavelets with nearest neighbors in a 2D mesh. Routing is controlled by respective virtual channel specifiers in each wavelet and routing configuration information in each router. A compute element receives a particular wavelet comprising a particular virtual channel specifier and a particular data element. Instructions are read from the memory of the compute element based at least in part on the particular virtual channel specifier. The particular data element is used as an input operand to execute at least one of the instructions.

Abstract: Systems and Methods for multi-modal or multimedia image retrieval are provided. Automatic image annotation is achieved based on a probabilistic semantic model in which visual features and textual words are connected via a hidden layer comprising the semantic concepts to be discovered, to explicitly exploit the synergy between the two modalities. The association of visual features and textual words is determined in a Bayesian framework to provide confidence of the association. A hidden concept layer which connects the visual feature(s) and the words is discovered by fitting a generative model to the training image and annotation words. An Expectation-Maximization (EM) based iterative learning procedure determines the conditional probabilities of the visual features and the textual words given a hidden concept class. Based on the discovered hidden concept layer and the corresponding conditional probabilities, the image annotation and the text-to-image retrieval are performed using the Bayesian framework.

Abstract: A question database storing questions and a conditional probability of one question to be asked given that a previous question was asked is searched to predict a future question based on the conditional probability stored in the question database given an input question as the previous question. The future question is suggested to a user. Responsive to receiving an acceptance of the future question, the question database is updated to strengthen the conditional probability associated with the future question occurring given the input question. An answer to the future question is provided and searching, predicting, suggesting and updating may be repeated, with the future question as the input question, until the future question is declined.

Abstract: An apparatus can include a first state machine engine configured to receive a first portion of a data stream from a processor and a second state machine engine configured to receive a second portion of the data stream from the processor. The apparatus includes a buffer interface configured to enable data transfer between the first and second state machine engines. The buffer interface includes an interface data bus coupled to the first and second state machine engines. The buffer interface is configured to provide data between the first and second state machine engines.

Abstract: Embodiments are directed to assessing performances of physical activities. Assessment engines may collect performance content that includes information associated with performances of activities. The assessment engines may employ classifiers to classify the performance content to determine occurrences of features of the performance content and classify assessment content to determine scores that are associated with features included in the performances. The assessment engines may provide correlation values associated with the performances based on historical performance content, assessment content, or scores. The assessment engine may provide a report that includes a localized evaluation of the performances based on the correlation values, performance content, assessment content, and scores. In some cases, the performance content may include videos of the performances.

Abstract: A system includes one or more memory devices storing instructions, and one or more processors configured to execute the instructions to perform steps of a method for generating a data tree structure for expediting rule-based decision-making. The system may receive a rules file having a plurality of rules, where each rule has one or more conditions and one or more actions. The system may generate a plurality of condition frequency counts that represent the total number of rules having a condition of a particular unique condition type. The system may then generate a tree structure based on the plurality of rules and the plurality of condition frequency counts, where the tree structure includes a root node and one or more node branches, where each node branch includes a first-level node and zero or more second-level nodes that each include a node condition and zero or more node actions.

Abstract: An auxiliary analysis system using expert information comprises a user interface and a determination module. The user interface includes a plurality of analysis items which can be triggered by a user. The determination module coupled with the user interface includes a plurality of preliminary results corresponding to the analysis items. Each of the analysis items corresponds to at least one of the preliminary results. The user selects a plurality of analysis items to generate multiple preliminary results, and the preliminary results further generate a final judgment result by an operation process.

Abstract: In some aspects, a method for performing analog matrix inversion on a matrix with a network of resistive device arrays B, W, Q, and C is described. The method may include initializing arrays W, Q, B and C, updating the connections of array W in parallel and array Q in parallel until a predetermined condition is satisfied, and responsive to determining that the predetermined condition is satisfied, outputting an inverted matrix based on outputs from the connections of arrays B, W, Q, and C.

Abstract: Provided is an information processing apparatus including: a behavior recognition mode setting unit that sets a behavior recognition mode on a basis of wearing position information of a setting target device, a behavior recognition unit that recognizes a user's behavior on a basis of the set behavior recognition mode and a detection value of a sensor corresponding to the setting target device, and a process control unit that controls execution of a process corresponding to the recognized user's behavior.

Abstract: After first installation of an application program on a computing device, the computing devices monitors a behavior of the application program for a period of time and then builds a behavior profile of the application program from the behavior. After the period of time has elapsed, such as specified period of time, the computing device may prevent the application program from deviating from the behavior profile. After the period of time has elapsed, such as when an update or patch to the application program has been applied or installed, the computing device may continue to monitor the behavior of the application program, and in response to determining that the behavior of the application program after the period of time deviates from the behavior profile, perform an action with respect to the application program.

Abstract: A system, method and a computer program product may be provided for automatically creating and parameterizing a semantically-enriched diagnosis model for an entity. The system receives a list of data points, from sensors or a database, to be used to create a diagnosis model. The system automatically creates the diagnosis model based on the received list of data points and data stored in a database and parameterizes the diagnosis model. The parameterized diagnosis model reflects rules that determine one or more potential causes of one or more abnormalities of one or more physical conditions in the entity.

Abstract: Each time evolution processing is performed, an information recording unit records increase-decrease information indicating a type of partial program changed in number between pre- and post-evolution individuals and difference between fitness levels calculated from the pre- and post-evolution individuals in a storage unit. A probability setting unit determines, per partial program, a contribution level indicating how much a partial program contributes to increasing a fitness level, based on the information stored in the storage unit within a predetermined period and sets a selection probability per partial program in such a manner that a partial program having a higher contribution level is given a higher selection probability. When the evolution processing is performed, a generation processing unit selects a partial program to be included in the post-evolution individual in mutation processing according to the set selection probabilities.

Abstract: A method and apparatus for training an algorithm to recognize a walking state of a user wearing a walking assistance apparatus are provided. The method and apparatus may generate virtual sensing data associated with walking of a virtual human model through a dynamic simulation, and may train the algorithm based on the virtual sensing data.

Abstract: An approach is provided for optimally routing events in an IT system to solvers which provide resolutions of the events. Event streams originating from the IT system are defined. Events are classified into the event streams. An optimization problem is solved that minimizes costs incurred for using respective solvers based on constraints which include success rates of the solvers. Based on the solved optimization problem, policies are defined that associate the event streams to the solvers in a many-to-one correspondence. In real time, the defined policies are applied to the event streams. Based on the applied policies and the classified events, the events are routed to respective solvers. An indication is received that the events are resolved by the respective solvers, which reduces downtime in the IT system.

Abstract: Methods and apparatus for determining whether a media presentation device is in an on state or an off state are disclosed. A disclosed example method comprises determining contribution values from at least one of a signal measured from a sensing device or an output signal accessed from the presentation device, wherein the contribution values are indicative of a state of a presentation device. Summing, via a logic circuit, a first plurality of the contribution values corresponding to a first measurement cycle to generate a first intermediate fuzzy score for the first measurement cycle. Storing the first intermediate fuzzy score in a buffer including a plurality of intermediate fuzzy scores corresponding to respective measurement cycles. Combining, via the logic circuit, the intermediate fuzzy scores corresponding to a first time period to form a final fuzzy score.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing parallel generation of output from an autoregressive sequence to sequence model. In one aspect, a blockwise parallel decoding method takes advantage of the fact that some architectures can score sequences in sublinear time. By generating predictions for multiple time steps at once then backing off to a longest prefix validated by the scoring model, the methods can substantially improve the speed of greedy decoding without compromising performance.

Abstract: According to one embodiment of the present invention, a prediction system is provided. The system comprises a first data decomposition facility configured to decompose a provided time series of consumption data into a plurality of different training sets for different types of days and a second data decomposition facility configured to decompose each one of the plurality of training sets into at least a seasonal component and a trend component. The system further comprises a regression facility configured to perform a regression analysis on the decomposed consumption data based on at least the trend component and chronological information associated with the consumption data of the respective training set to train a prediction function and a prediction facility configured to estimate predicted energy consumption data based on the trained prediction function and the type of a day for which the prediction is performed.