Abstract: A neuromorphic memory circuit including a programmable resistive memory element, an axon LIF line to transmit an axon LIF pulse, and a dendrite LIF line to build up a dendrite LIF charge over time. A first transistor provides a discharge path for the dendrite LIF charge through the programmable resistive memory element when the axon LIF line transmits the axon LIF pulse. An axon STDP line transmits an axon STDP pulse. The axon STDP pulse is longer than the axon LIF pulse. A dendrite STDP line is configured to transmit a dendrite STDP pulse after voltage at the dendrite LIF line falls below a threshold voltage. A second transistor is coupled to the axon STDP line and the programmable resistive memory element. The second transistor provides an electrical path for the dendrite STDP pulse through the programmable resistive memory element when the axon STDP line transmits the axon STDP pulse.

Abstract: A system and method for generating a heuristic is provided. A heuristic is capable of identifying data patterns. The method includes: extracting a data set from multiple input sources; creating a set of unique elements used across the data set; organizing the data set into a geometric structure; grouping portions of the data in the geometric structure into a plurality sub geometric structures; determining base attributes for each sub geometric structure using the set of unique elements; identifying trends in the base attributes among the sub geometric structures; and outputting the heuristic as a combination of the base attributes and the trends.

Abstract: The claimed subject matter includes a system and method for attribution of search activity in multi-user settings. The method includes training a classifier to distinguish between machines that are single-user and multi-user based on activity logs of an identified machine. The identified machine is determined to be multi-user based on the classifier. A number of users is estimated for the identified machine. Activity of the users is clustered based on the number of users estimated. A similarity function is learned for the number of users estimated. The method also includes assigning new activity to one of the users based on the clustering, and the similarity function.

Abstract: In an example, one or more computing devices operate to provide a context-aware reputation of a place, such as in relation to a human user. Context may include the user's identity and purpose, as well as environmental factors such as time of day, weather, and political drivers. The device may communicate with a server to receive globalized safety intelligence. When the user enters a zone, the device may determine a context-sensitive reputation, such as “Green,” “Yellow,” or “Red.” Depending on the reputation, the device may then take an appropriate action, such as warning the user or providing additional information.

Abstract: A parallel convolutional neural network is provided. The CNN is implemented by a plurality of convolutional neural networks each on a respective processing node. Each CNN has a plurality of layers. A subset of the layers are interconnected between processing nodes such that activations are fed forward across nodes. The remaining subset is not so interconnected.

Abstract: Embodiments are directed to managing operations. If Operations events are provided, event clusters may be associated with one or more Operations events, such that the Operations events may be associated with the event clusters based on characteristics of the Operations events. Metrics including resolution metrics, root cause analysis, notes, and other remediation information may be associated with the event clusters. Then a modeling engine may be employed to train models based on the Operations events, the event clusters, and the resolution metrics, such that the trained model may be trained to correlate and predict the resolution metrics from real-time Operations events. If real-time Operations events may be provided, the trained models may be employed to predict the resolution metrics that are associated with the real-time Operations events. If model performance degrades beyond accuracy requirements, new observations may be added to the training set and the model re-trained.

Abstract: The present invention discloses a rule matching method including: receiving a packet; detecting feature information in content of the packet, and determining whether the detected feature information in the packet conforms to a classification characteristic of one rule group among a plurality of preset rule groups; if yes, determining a state machine corresponding to the one rule group as a first state machine; and determining whether the first state machine is stored in an on-chip memory, and if yes, using the first state machine to match the packet to obtain a matching result; and if no, when an off-chip memory stores the first state machine, loading the first state machine from the off-chip memory into the on-chip memory, and using the first state machine to match the packet to obtain a matching result. Embodiments of the present invention enable a product to achieve better performance.

Abstract: Embodiments of the invention provide a neurosynaptic system comprising a first set of one or more neurosynaptic core circuits configured to receive input data comprising multiple input regions, and extract a first set of features from the input data. The features of the first set are computed based on different input regions. The system further comprises a second set of one or more neurosynaptic core circuits configured to receive the first set of features, and generate a second set of features by combining the first set of features based on synaptic connectivity information of the second set of core circuits.

Abstract: A system and method for evaluating sequential decision problems that have multidimensional states. The system and method maximizes the value, as defined by the value functional equation, received by the user, for both finite and infinite horizon decision problems and provides decision making advice to the user based upon input actions, states, rewards and transition probabilities.

Abstract: Using the short form information people tend to use in their calendar locations (not full address or GPS location), machine learning techniques are used to map gathered location information to these short form names.

Abstract: A machine learning based procurement system comprises a machine learning classifier to classify bids. The procurement system determines a price risk score and a supplier risk score for each of the bids based on the classifications, and determines if any of the bids are associated with a high-risk procurement based on comparing the price risk score and the supplier risk score to the respective threshold. The procurement system includes a graphical user interface that can display bid evaluation links, which are accessible to provide information explaining high-risk procurements.

Abstract: Methods and apparatus are disclosed for determining supervised training data, such as travel-related supervised training data, for training a machine learning system. In some implementations, supervised training data may be determined that includes input features based on information items of users and desired output features based on one or more physical locations visited by users.

Abstract: A computing unit obtains a graph including nodes and edges and representing a communication condition at first timing and at second timing and detects an edge that is added between the first and second timing among the edges. The computing unit calculates probabilities of transmitting information from each node to nodes coupled to the added edge, selects a subset of the nodes based on the calculated probabilities, selects nodes included in the subset as the starting points of information, calculates first probabilities of transmitting information from the selected nodes to each node based on the graph obtained at the first timing and second probabilities of transmitting information from the selected nodes to each node based on the graph obtained at the second timing, and detects a change in the communication condition between the first and second timing by comparing the first probabilities with the second probabilities.

Abstract: A method of evaluating trading rules. A plurality of trading rules are received. Each trading rule includes at least one respective condition. Each condition includes at least one respective attribute, at least one respective value, and at least one respective operator that describes a relationship between the at least one respective attribute and the at least one respective value. The conditions of the plurality of trading rules are parsed into a collection of conditions so that the collection of conditions does not include duplicate conditions. A mapping is maintained from the collection of conditions to the plurality of trading rules that allows reconstruction of the plurality of trading rules from the collection of conditions. The conditions in the collection of conditions are evaluated. The rules are evaluated by referencing the evaluated conditions and the mapping.

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: A method includes receiving meteorological forecast data at an electronic device. The method includes predicting multiple risk levels associated with an aircraft using one or more runways of an airport during a forecast time interval based on the meteorological forecast data. The method further includes generating a graphical user interface (GUI) that includes multiple risk indicators based on the multiple risk levels. The multiple risk indicators may correspond to multiple time sub-intervals during the forecast time interval.

Abstract: Predictive modeling based focus error prediction method and system are disclosed. The method includes obtaining wafer geometry measurements of a plurality of training wafers and grouping the plurality of training wafers to provide at least one training group based on relative homogeneity of wafer geometry measurements among the plurality of training wafers. For each particular training group of the at least one training group, a predictive model is develop utilizing non-linear predictive modeling. The predictive model establishes correlations between wafer geometry parameters and focus error measurements obtained for each wafer within that particular training group, and the predictive model can be utilized to provide focus error prediction for an incoming wafer belonging to that particular training group.

Abstract: An object investigation and classification system may include an object test system, a data storage system, and a data processing system. The object test system may receive a command to perform at least one action with a test object, perform the at least one action with the test object, and return test information indicative of at least one percept resulting from the at least one action. The data storage system may contain an experience database containing data indicative of multiple classifications and, for each classification, at least one action that was performed with at least one previously-observed reference object having this classification, and at least one percept value that is based in whole or in part on the test information resulting from the at least one action.

Abstract: A network-based enterprise or other system that makes items available for selection to users may implement real-time updates to item recommendation models based on matrix factorization. An item recommendation model may be maintained that is generated from a singular value decomposition of a matrix indicating selections of items by users. A user-specific update to the item recommendation model may be calculated in real-time for a particular user such that the calculation may be performed without performing another singular value decomposition to generate an updated version of the item recommendation model. Item recommendations may then be made based on the user-specific update and the item recommendation model. In various embodiments, the item recommendations may be made in response to an indication or request for item recommendations for the particular user.

Abstract: Computer-implemented systems and methods are disclosed for data driven expertise mapping. The systems and methods provide for obtaining data sets from data sources, wherein the data sets include services related data, analyzing the data sets, wherein the analysis generates information representative of the services related data, and generating training sets related to the data sets, wherein the training sets are based on known values. The systems and methods further provide for generating models, wherein the models are based on determining services provided by service providers using a combination of the services related data, the analysis of the data sets and the training sets, and provide a mapping of at least one service to service providers. The systems and methods additionally include evaluating the models based on known values and storing an indication for providing to a graphical user interface based on more models.