2380results about "Biological neural network models" patented technology

Method and system for diagnosing whether vehicular components are operating abnormally based on data obtained from sensors arranged on a vehicle. In a training stage, output from the sensors during normal operation of the components is obtained, each component is adjusted to induce abnormal operation thereof and output from the sensors is obtained during the induced abnormal operation. A determination is made as to which sensors provide data about abnormal operation of each component based on analysis of the output from the sensors during normal operation and during induced abnormal operation of the components. During operation of the vehicle, the output from the sensors is obtained and analyzed, e.g., by inputting it into a pattern recognition algorithm or neural network generated during the training stage, in order to output an indication of abnormal operation of any components being diagnosed.

A mental-model elicitation process and apparatus, called the Mental-Model Elicitation Device (MMED) is described. The MMED is used to give rise to more effective end-user mental-modeling activities that require executive function and working memory functionality. The method and apparatus is visual analysis based, allowing visual and other sensory representations to be given to thoughts, attitudes, and interpretations of a user about a given visualization of a mental-model, or aggregations of such visualizations and their respective blending. Other configurations of the apparatus and steps of the process may be created without departing from the spirit of the invention as disclosed.

A process and system for database storage and retrieval are described along with methods for obtaining semantic profiles from a training text corpus, i.e., text of known relevance, a method for using the training to guide context-relevant document retrieval, and a method for limiting the range of documents that need to be searched after a query. A neural network is used to extract semantic profiles from text corpus. A new set of documents, such as world wide web pages obtained from the Internet, is then submitted for processing to the same neural network, which computes a semantic profile representation for these pages using the semantic relations learned from profiling the training documents. These semantic profiles are then organized into clusters in order to minimize the time required to answer a query. When a user queries the database, i.e., the set of documents, his or her query is similarly transformed into a semantic profile and compared with the semantic profiles of each cluster of documents. The query profile is then compared with each of the documents in that cluster. Documents with the closest weighted match to the query are returned as search results.

A flow processing facility, which uses a set of artificial neurons for pattern recognition, such as a self-organizing map, in order to provide security and protection to a computer or computer system supports unified threat management based at least in part on patterns relevant to a variety of types of threats that relate to computer systems, including computer networks. Flow processing for switching, security, and other network applications, including a facility that processes a data flow to address patterns relevant to a variety of conditions are directed at internal network security, virtualization, and web connection security. A flow processing facility for inspecting payloads of network traffic packets detects security threats and intrusions across accessible layers of the IP-stack by applying content matching and behavioral anomaly detection techniques based on regular expression matching and self-organizing maps. Exposing threats and intrusions within packet payload at or near real-time rates enhances network security from both external and internal sources while ensuring security policy is rigorously applied to data and system resources. Intrusion Detection and Protection (IDP) is provided by a flow processing facility that processes a data flow to address patterns relevant to a variety of types of network and data integrity threats that relate to computer systems, including computer networks.

The present invention relates to a scaleable automatic method of using multiple techniques to generate models and combinations of models from data and prior knowledge. The system provides unprecedented ease of use in that many of the choices of technique and parameters are explored automatically by the system, without burdening the user, and provides scaleable learning over distributed processors to achieve speed and data-handling capacity to satisfy the most demanding requirements.

The different advantageous embodiments may provide a method, apparatus, and computer program product for passively learning and autonomously executing tasks on behalf of a user. The different advantageous embodiments may provide an apparatus that comprises a processing unit and a synthetic representation process executed by the processing unit. The synthetic representation process may be capable of executing a number of tasks for a user.

A quality prognostics system and a quality prognostics method for predicting the product quality during manufacturing processes are disclosed. The present invention utilizes the current production tool parameters sensed during the manufacturing process and several previous quality data collected from the measurement tool to predict the future product quality. The quality prognostics system is composed of conjecture modeling means and prediction modeling means. The conjecture modeling means itself also can be applied for the purpose of virtual metrology. Further, the quality prognostics method possesses a self-searching means and a self-adjusting means for searching the best combination of various parameters/functions used by the conjecture algorithm or prediction algorithm; and meeting the requirements of new equipment parameters and conjecture/prediction accuracy.

Provided are, among other things, systems, methods and techniques for forecasting information. One representative embodiment involves obtaining data that has been provided by each of a number of individual people; dividing the people into clusters by utilizing a statistical clustering technique; calculating statistics of the data in each of at least some of the clusters; and combining the statistics for such clusters so as to obtain a combination forecast.

Systems and methods are disclosed for routing callers to agents in a contact center utilizing a multi-layer processing approach to matching a caller to an agent. A first layer of processing may include two or more different computer models or methods for scoring or determining caller-agent pairs in a routing center. The output of the first layer may be received by a second layer of processing for balancing or weighting the outputs and selecting a final caller-agent match. The two or more methods may include conventional queue based routing, performance based routing, pattern matching algorithms, affinity matching, and the like. The output or scores of the two or more methods may be processed be the second layer of processing to select a caller-agent pair and cause the caller to be routed to a particular agent.

A system and method for monitoring an apparatus or process asset including partitioning an unpartitioned training data set into a plurality of training data subsets each having an operating mode associated thereto; creating a process model comprised of a plurality of process submodels each trained as a function of at least one of the training data subsets; acquiring a current set of observed signal data values from the asset; determining an operating mode of the asset for the current set of observed signal data values; selecting a process submodel from the process model as a function of the determined operating mode of the asset; calculating a current set of estimated signal data values from the selected process submodel for the determined operating mode; and outputting the calculated current set of estimated signal data values for providing asset surveillance and/or control.

A method monitors a weld signature of a welding apparatus by processing the signature through a neural network to recognize a pattern, and by classifying the weld signature in response to the pattern. The method determines if the weld signature is sufficiently different from training weld signatures stored in a database, and records the weld signature in the database when sufficiently different. The method tests a weld joint to determine values of different weld joint properties, and then correlates the signature with the weld data to validate the database. An apparatus monitors a weld signature during a welding process to predict welding joint quality, and includes a welding gun, a power supply, and a sensor for detecting welding voltage, current, and wire feed speed (WFS). A neural network receives the welding process values and classifies the signature into different weld classifications each corresponding to a predicted welding joint quality.

A method controls a welding apparatus by using a neural network to recognize an acceptable weld signature. The neural network recognizes a pattern presented by the instantaneous weld signature, and modifies the instantaneous weld signature when the pattern is not acceptable. The method measures a welding voltage, current, and wire feed speed (WFS), and trains the neural network using the instantaneous weld signature when the instantaneous weld signature is different from each of the different training weld signatures. A welding apparatus for controlling a welding process includes a welding gun, a power supply for supplying a welding voltage and current, and a sensor for detecting values of a plurality of different welding process variables. A controller of the apparatus has a neural network for receiving the welding process variables and for recognizing a pattern in the weld signature. The controller modifies the weld signature when the pattern is not recognized.

Methods and systems for determining a suitability for a mobile client to display information are disclosed. A particular exemplary method includes receiving a plurality of sets of one or more first keywords on a mobile client, each set of first keywords associated with one or more respective first messages, monitoring user interaction of the respective first messages on the mobile client, determining a user selection rate for each unique first keyword of the plurality of sets of first keywords, receiving a set of target keywords associated with a target message, performing one or more matching operations between the set of target keywords and corresponding user selection rates to produce a set of one or more matching parameters, and displaying the target message on the mobile client dependent upon the matching parameters.

The invention discloses a convolution neural network parallel processing method based on a large-scale high-performance cluster. The method comprises the steps that (1) a plurality of copies are constructed for a network model to be trained, model parameters of all the copies are identical, the number of the copies is identical with the number of nodes of the high-performance cluster, each node is provided with one model copy, one node is selected to serve as a main node, and the main node is responsible for broadcasting and collecting the model parameters; (2) a training set is divided into a plurality of subsets, the training subsets are issued to the rest of sub nodes except the main mode each time to conduct parameter gradient calculation together, gradient values are accumulated, the accumulated value is used for updating the model parameters of the main node, and the updated model parameters are broadcast to all the sub nodes until model training is ended. The convolution neural network parallel processing method has the advantages of being capable of achieving parallelization, improving the efficiency of model training, shortening the training time and the like.

Techniques for implementing message passing decoders, e.g., LDPC decoders, are described. To facilitate hardware implementation messages are quantized to integer multiples of ½ ln2. Messages are transformed between more compact variable and less compact constraint node message representation formats. The variable node message format allows variable node message operations to be performed through simple additions and subtractions while the constraint node representation allows constraint node message processing to be performed through simple additions and subtractions. Variable and constraint nodes are implemented using an accumulator module, subtractor module and delay pipeline. The accumulator module generates an accumulated message sum. The accumulated message sum for a node is stored and then delayed input messages from the delay pipeline are subtracted there from to generate output messages. The delay pipeline includes a variable delay element making it possible to sequentially perform processing operations corresponding to nodes of different degrees.

A system and method which partitions a parameter estimation model, a fault detection model, and a fault classification model for a process surveillance scheme into two or more coordinated submodels together providing improved diagnostic decision making for at least one determined operating mode of an asset.

The invention discloses a remote sensing monitoring system for automotive exhaust emission of an urban road network. The system is mainly composed of a remote measurement device layer, a site selection and position arrangement layer, and a data processing layer. Through mobile, horizontal and vertical exhaust remote measurement devices, real-time data of the automotive exhaust emission in running is obtained; by adopting an advanced site selection and position arrangement method, the remote measurement devices are scientifically networked; and in combination with external data of weather, traffic, geographic information and the like, the real-time remote measurement data of the automotive exhaust emission is subjected to intelligent analysis and data mining by adopting big data processing and analysis technologies such as deep learning and the like, and key indexes and statistical data with optimal identification performance are obtained, so that effective support is provided for government departments to make related decisions.

Methods for training machines to categorize data, and/or recognize patterns in data, and machines and systems so trained. More specifically, variations of the invention relates to methods for training machines that include providing one or more training data samples encompassing one or more data classes, identifying patterns in the one or more training data samples, providing one or more data samples representing one or more unknown classes of data, identifying patterns in the one or more of the data samples of unknown class(es), and predicting one or more classes to which the data samples of unknown class(es) belong by comparing patterns identified in said one or more data samples of unknown class with patterns identified in said one or more training data samples. Also provided are tools, systems, and devices, such as support vector machines (SVMs) and other methods and features, software implementing the methods and features, and computers or other processing devices incorporating and/or running the software, where the methods and features, software, and processors utilize specialized methods to analyze data.

Method and apparatus for combining a plurality of overlapping policy-based controllers. System also applicable to policy-based process servers. System combines controllers by combining the respective policy information. System combines a plurality of policy-based sub-controllers by combining the associated distributional information contained in the associated sub-policies. An iterative mixture mechanism with temporal persistence regulates the relative contribution of the sub-policies smoothly over time thereby allowing smooth transition of control from one control regime to another. The system provides for modular detection and resolution of conflicts that may arise as a result of combining otherwise incompatible sub-policies. Preferred embodiment performs mixture method in policy space. Another embodiment applies mixture method to value functions associated with each sub-server.

The present invention relates to a method of managing a network. The method steps includes extracting a signature from a first traffic flow of a plurality of traffic flows on the network based on layer-3/layer-4 information of the first traffic flow, storing the signature and an identification of a layer-7 application associated with the signature in a signature repository, identifying a second traffic flow of the plurality of traffic flows being associated with the layer-7 application by correlating the second traffic flow to the signature, and managing the network based on layer-7 application identification of the plurality of traffic flows.

A new method, system and apparatus is provided that enables muscle signals that correspond to muscle contractions to be mapped to one or more functions of an electronic device such as a prosthetic device or gaming apparatus. Muscle signals are classified in real-time from self-selected intentional movements. A self-training protocol allows users to select and label their own muscle contractions, and is operable to automatically determine the discernible and repeatable muscle signals generated by the user. A visual display means is used to provide visual feedback to users illustrating the responsiveness of the system to muscle signals generated by the user.

Methods and apparatus for analyzing tasks performed by computer users by (i) gathering usage data, (ii) converting logged usage data into a uniform format, (iii) determining or defining task boundaries, and (iv) determining a task analysis model by "clustering" similar tasks together. The task analysis model may be used to (i) help users complete a task (such help, for example, may be in the form of a gratuitous help function), and/or (ii) to target marketing information to users based on user inputs and the task analysis model. The present invention also provides a uniform semantic network for representing different types of objects in a uniform way.

An apparatus and method for monitoring a process involve development and application of a statistically qualified neuro-analytic (SQNA) model to accurately and reliably identify process change. The development of the SQNA model is accomplished in two stages: deterministic model adaption and stochastic model modification of the deterministic model adaptation. Deterministic model adaption involves formulating an analytic model of the process representing known process characteristics, augmenting the analytic model with a neural network that captures unknown process characteristics, and training the resulting neuro-analytic model by adjusting the neural network weights according to a unique scaled equation error minimization technique. Stochastic model modification involves qualifying any remaining uncertainty in the trained neuro-analytic model by formulating a likelihood function, given an error propagation equation, for computing the probability that the neuro-analytic model generates measured process output. Preferably, the developed SQNA model is validated using known sequential probability ratio tests and applied to the process as an on-line monitoring system. Illustrative of the method and apparatus, the method is applied to a peristaltic pump system.

The embodiment of the invention discloses a lane line data processing method and a lane line data processing device. The method comprises the following steps of: obtaining an original image and positioning data of the original image; using a deep neural network model for calculating the pixel confidence degree of each pixel, conforming to lane line features, in the original image; determining the lane line outlines from the original image, and using the lane line outlines as candidate lane line; calculating the lane line confidence degree of the candidate lane lines; screening the candidate lane lines according to the lane line confidence degree of the candidate lane lines; recognizing the attribute information of the lane line by aiming at the screened lane line; and determining map data of the lane line according to the attribute information of the lane line and positioning data during the original image shooting. The lane line data processing method and the lane line data processing device provided by the embodiment have the advantages that the lane line data can be efficiently and precisely determined; the labor cost in high-precision map production is greatly reduced; and the large-scale high-precision map production can be realized.

Systems, apparatus, and methods for determining groups of similar consumers and for identifying a trend in consumer behavior are provided. Likelihoods of a transaction being initiated at various times by one consumer can be calculated based on previous transactions of the consumer. The likelihoods for different consumers can be used to determine a group of similar consumers as a demographic. The likelihoods of a transaction being initiated at various times by a consumer of a demographic (or other entity) can be used to forecast trends (such as a demand for a product) and make business decisions, such as for marketing campaigns, inventory levels (e.g. at particular stores or for all stores), pricing, and store locations. Such likelihoods when focused to a particular category of transactions can provide even greater accuracy.

A video quality evaluation method based on artificial neural network, which belongs to the field of computer digital video processing. The evaluation algorithm computes damage extent of an image by analyzing spatial characters (blur, entropy, blocking effect, frequency-domain energy analysis, saturation) and time behaviors (frame-to-frame differences). Evaluation effect of the algorithm can be effectively modified by using colour space saturation as one of the parameters for non-reference evaluation algorithm. The system is designed based on artificial neural network, therefore, training process and testing process of the network are included in realization of the algorithm. To the selected training sample (video image sequence), firstly extracts six parameters of the sample, then obtains expected output (subjective evaluation result) in training through subjective evaluation. Characteristic parameters of the training sample and the corresponding subjective evaluation result are inputted to the artificial neural network as training parameters. The experiment shows that evaluation result obtained by the objective evaluation system is highly-consistent with visual sense of human eyes.

The invention discloses an automated design method, device and optimization method applied for a neural network processor. The method comprises the steps that neural network model topological structure configuration files and hardware resource constraint files are obtained, wherein the hardware resource constraint files comprise target circuit area consumption, target circuit power consumption and target circuit working frequency; a neural network processor hardware architecture is generated according to the neural network model topological structure configuration files and the hardware resource constraint files, and hardware architecture description files are generated; according to a neural network model topological structure, the hardware resource constraint files and the hardware architecture description files, modes of data scheduling, storage and calculation are optimized, and corresponding control description files are generated; according to the hardware architecture description files and the control description files, cell libraries meet the design requirements are found in constructed reusable neural network cell libraries, corresponding control logic and a corresponding hardware circuit description language are generated, and the hardware circuit description language is transformed into a hardware circuit.

User authentication apparatus controlling access to systems, inputs owner's login name and password and then extracts the owner's timing vectors from keystroke characteristics with which the owner forms a training set. A semantic network uses multiple links to indicate that different pattern components of user's behavioral access create different kinds of relationships and “symbolic representations”. A neural network is trained by using each of the owner's timing vectors in the training set as an input. When a user inputs the owner's login name and password, it's checked and the user's timing vector is extracted to type the user's password if checked and demoted in confidence level if otherwise. The user's timing vector is applied to neural network and difference between the input/output is compared with a predetermined threshold; and if the difference is greater than the threshold, is prohibited. Preferably this is aided by response time to personal questions.

The invention discloses a vehicle detection method based on a convolutional neural network. The method includes the step S1 of collecting vehicle samples and non-vehicle samples and classifying the vehicle samples, the step S2 of preprocessing the samples, the step S3 of training a CNN vehicle detector, the step S4 calculating an average similarity table of a characteristic pattern, the step S5 of constructing a similarity characteristic pattern set, the step S6 of obtaining a CNN-OP vehicle detector, the step S7 of obtaining detection images, the step S8 of preprocessing the obtained detection images, the step S9 of constructing an image pyramid for the detection images, the step S10 of extracting characteristics, the step S11 of scanning characteristic patterns, the step S12 of classifying the characteristics, and the step S13 of combining detection windows and conducting output. An offline optimization scheme is put forward, the convolutional neural network which is completely trained is optimized, the strategy of scanning the windows after extracting the characteristics is adopted at the detection stage, and therefore the characteristics are prevented from being repeatedly calculated, and the detection speed of the system is increased.

A method and a device for training a DNN model includes: at a device including one or more processors and memory: establishing an initial DNN model; dividing a training data corpus into a plurality of disjoint data subsets; for each of the plurality of disjoint data subsets, providing the data subset to a respective training processing unit of a plurality of training processing units operating in parallel, wherein the respective training processing unit applies a Stochastic Gradient Descent (SGD) process to update the initial DNN model to generate a respective DNN sub-model based on the data subset; and merging the respective DNN sub-models generated by the plurality of training processing units to obtain an intermediate DNN model, wherein the intermediate DNN model is established as either the initial DNN model for a next training iteration or a final DNN model in accordance with a preset convergence condition.