Abstract: Semi-supervised random decision forests for machine learning are described, for example, for interactive image segmentation, medical image analysis, and many other applications. In examples, a random decision forest comprising a plurality of hierarchical data structures is trained using both unlabeled and labeled observations. In examples, a training objective is used which seeks to cluster the observations based on the labels and similarity of the observations. In an example, a transducer assigns labels to the unlabeled observations on the basis of the clusters and certainty information. In an example, an inducer forms a generic clustering function by counting examples of class labels at leaves of the trees in the forest. In an example, an active learning module identifies regions in a feature space from which the observations are drawn using the clusters and certainty information; new observations from the identified regions are used to train the random decision forest.

Abstract: A cellular computational platform is disclosed that includes a multiplicity of functionally identical, repeating computational hardware units that are interconnected electrically and optically. Each computational hardware unit includes a reprogrammable local memory and has interconnections to other such units that have reconfigurable weights. Each computational hardware unit is configured to transmit signals into the network for broadcast in a protocol-less manner to other such units in the network, and to respond to protocol-less broadcast messages that it receives from the network. Each computational hardware unit is further configured to reprogram the local memory in response to incoming electrical and/or optical signals.

Abstract: DFA construction may be aborted if the DFA will become too big for the computing device to handle or based on user preferences. A DFA may be constructed from an NFA, which is constructed from an expression. The expression may have a total number of operands and operators r. The determination to abort DFA construction may be based on the operands. If the number of DFA nodes constructed is more than a lower threshold and the number of DFA nodes constructed is greater than a function, f(r), the DFA construction may be aborted. If the number of DFA nodes is greater than a higher threshold, the DFA construction may be aborted. The lower threshold may be determined based on computing device capabilities and user preference. The higher threshold may be based on computing device capabilities.

Abstract: A quasiparticle interactor induces interactions between non-Abelian quasiparticles. State information is teleported between non-Abelian quasiparticles due to the interactions. The interactions induced by the quasiparticle interactor may be induced adiabatically and may be localized. The teleportation of state information may be utilized to generate quasiparticle exchange transformation operators acting on the state space of non-Abelian quasiparticles.

Abstract: An approach is provided for mining threaded online discussions. In the approach, performed by an information handling system, a natural language processing (NLP) analysis is performed on threaded discussions pertaining to a given topic. The analysis is performed across multiple web sites with each of the web sites including one or more threaded discussions. The analysis results in harvested discussions pertaining to the topic. The harvested discussions are correlated and a question is identified from the harvested discussions. A set of candidate answers is also identified from the harvested discussions, with one of the candidate answers being selected as the most likely answer to the identified question.

Abstract: Users are enabled to provide structured ratings for various attributes of items or other such content in an electronic environment. Users are able to rate existing attributes associated with an item, or new attributes that the users want to associate with the item. In addition to allowing users to provide a rating for each attribute, users can be prompted to include information relating to these attributes in reviews for the respective item(s). Attributes can be automatically applied to various items using a process that determines aspects of items that are indicative of each attribute being relevant, and automatically applies the attributes to items having at least some of those or similar aspects. Various models and algorithms are described for providing such functionality.

Abstract: A machine learning apparatus includes an analytical information storage unit that stores therein two or more pieces of analytical information each associating input/output information used for machine learning with time-point information indicating a time point of the input/output information, an analysis-object-set specifying unit that specifies an analysis object set containing a unit-period input-output set being a set of pieces of the input/output information corresponding to pieces of the time-point information indicating the time point in a unit period and an amount of the pieces of the input/output information of the set being dependent on a period between the time point of the unit periods and a specific time point, and a machine learning unit that performs machine learning by using the pieces of the input/output information contained in the analysis object set.

Abstract: A neural network portion comprising N pre-synaptic neurons capable each of firing an action potential, wherein the number N can be encoded in a word of n bits; the neural network portion being provided for, upon firing of a number F of pre-synaptic neurons in a predetermined period of time: if F.n<N, generating a first type message, the message comprising a unique address for each pre-synaptic neuron having fired in said predetermined period of time, each address being encoded as a word of n bits; and if F.n>N, generating a second type message, the message comprising N bits and being encoded in words of n bits, wherein each one of said N pre-synaptic neurons is represented by a unique bit, each bit having a first value if the pre-synaptic neuron represented by the bit fired in said predetermined period of time, and a second value otherwise.

Abstract: A method and apparatus for pushing network information are provided. The method includes: obtaining browser data uploaded by a browser; classifying the browser data uploaded via a classification model and determining a category of the browser data; obtaining network information related to the category, pushing the network information obtained to the browser.

Abstract: A data processing apparatus may utilize an artificial neuron network configured to reduce dimensionality of input data using a sparse transformation configured using receptive field structure of network units. Output of the network may be analyzed for temporally persistency that is characterized by similarity matrix. Elements of the matrix may be incremented when present activity unit activity at a preceding frame. The similarity matrix may be partitioned based on a distance measure for a given element of the matrix and its closest neighbors. Stability of learning of temporally proximal patterns may be greatly improved as the similarity matrix is learned independently of the partitioning operation. Partitioning of the similarity matrix using the methodology of the disclosure may be performed online, e.g., contemporaneously with the encoding and/or similarity matrix construction, thereby enabling learning of new features in the input data.

Abstract: Techniques for providing a prompt for real-time cognitive assistance. A method includes analyzing input from at least one environmental sensor to identify context information pertaining to a user situation, identifying a likely subsequent cognitive task of the user in the user situation based on the context information and use of a learned model, determining an action with respect to information to be suggested to the user via a corresponding prompt, wherein the determining is based on the likely subsequent cognitive task, the context information and information learned from at least one previous user situation, computing a confidence value to represent a level of certainty in the action, and providing the prompt to the user if the action has a confidence value greater than a threshold value corresponding to the action.

Abstract: A method and system for selecting a batch of input data from available input data for parallel evaluation by a function is disclosed. The function is modeled as drawn from a Gaussian process. Observations are used to determine a mean and a variance of the modeled function. An upper confidence bound is determined from the determined mean and variance. A decision rule is applied to select input data from the available input data to add to the batch of input data. The selection of the input data is based on a domain-specific time varying parameter. Intermediate observations are hallucinated within the batch. The hallucinated observations are used with the decision rule to select subsequent input data from the available input data for the batch of input data. The input data of the batch is evaluated in parallel with the function. The resulting determined data outputs are stored.

Abstract: A method, apparatus and product useful for classification reliability prediction. The method being a computer-implemented method performed by a processor, the method comprising: obtaining a prediction of a label for a dataset made by a classifier tool, wherein the classifier tool is aimed at predicting the label based on a classification model and in view of a set of features defining the dataset; obtaining a reliability prediction of a reliability label relating to the prediction of the classifier tool based on a reliability classifier tool, wherein the reliability classifier tool is aimed at predicting the reliability label based on a classification model and in view of a second set of features; and outputting to a user the label prediction and an associated reliability prediction.

Abstract: A method and system comprise providing means and method for producing, modifying, and/or exploiting the structure of a policy manifold. Each of the policies at least comprises information for mapping state and/or sensory information as input to action preferences as output. One or more processing units assign each of the policies a policy coordinate on a policy manifold. The policy coordinate may in part be determined by a dissimilarity matrix or other means for organizing the coordinates of the policies on the policy manifold according to the properties of the policies and the topology of the policy manifold. The policy manifold comprises a dimensionality that is lower than a combined dimensionality of the input and the output, wherein the policy manifold at least in part determines a behavior of the intelligent artificial agent.

Abstract: A matching circuit includes pattern circuits, and a signal path in which the pattern circuits are series-connected, wherein each of the pattern circuits connected to a preceding-stage pattern circuit through the signal path is settable in a first operation mode and in a second operation mode, wherein each of the pattern circuits in the first operation mode generates a result of matching in response to both a result of matching supplied from a preceding-stage pattern circuit and a result obtained by matching data supplied from the preceding-stage pattern circuit against part of a regular expression pattern, and wherein each of the pattern circuits in the second operation mode generates a result of matching in response to a result obtained by matching the data supplied from the preceding-stage pattern circuit against part of a regular expression pattern, without relying on a result of matching supplied from the preceding-stage pattern circuit.

Abstract: Systems and methods are disclosed for building and using decision trees, preferably in a scalable and distributed manner. Our system can be used to create and use classification trees, regression trees, or a combination of regression trees called a gradient boosted regression tree (GBRT). Our system leverages approximate histograms in new ways to process large datasets, or data streams, while limiting inter-process communication bandwidth requirements. Further, in some embodiments, a scalable network of computers or processors is utilized for fast computation of decision trees. Preferably, the network comprises a tree structure of processors, comprising a master node and a plurality of worker nodes or “workers,” again arranged to limit necessary communications.

Abstract: An authentication system authenticates an object. The authentication system includes a capture device for capturing at least one biometric output data record (BD) for the object; a reading device for reading configuration data (Konf), associated with the object, for an artificial neural network; a processing device designed to produce the artificial neural network and to input the BD into the neural network; a verification device which captures an output from the neural network to authenticate the object, wherein the neural network is a bidirectional associative memory, particularly a Hopfield network, having a multiplicity of network states. The verification device is designed to determine the output from the neural network by capturing a final state derived from the input of the BD. The neural network stores a key associated with a particular person. The key is released only when appropriate biometric data are input into the neural network.

Abstract: Techniques for modifying search results associated with a search request based on a determination that a member profile attribute is inaccurate are described. According to various embodiments, an existing member profile attribute included in a member profile page of a particular member of an online social network service is identified. Member profile data and behavioral log data associated with a plurality of members of the online social network service is then accessed. Prediction modeling to verify the existing member profile attribute is performed using the accessed data. Additionally, a confidence score associated with the existing member profile attribute is generated based on the prediction modeling. Moreover, the existing member profile attribute is determined to be inaccurate based on the generated confidence score. Furthermore, the search results associated with a search request is modified based on the determination.

Abstract: Provided is a user question processing method and system. The method includes: extracting first feature information from a user question; calculating the similarity between the first feature and second feature information of each of at least two websites; posting the question on at least one of the at least two websites according to the similarity. The solution of the embodiment can be applied to a website providing a question and answer service, and the website can post a received user question on another website related to the concerned field of the question, thereby enlarging the scope of the user information exchange.

Abstract: Certain aspects of the present disclosure support a technique for adaptive bit-allocation in neural systems. Bit-allocation for neural signals and parameters in a neural network described in the present disclosure may comprise for a plurality of synapse circuits in the neural simulator network, dynamically allocating a number of bits to the neural circuit signals based on at least one characteristic of one or more neural potential in the neural simulator network; and for the plurality of synapse circuits in the neural simulator network, dynamically allocating a number of bits to at least one neural processing parameter of the synapse circuit based on at least one condition of the neural simulator network.