Abstract: A mechanism is described for facilitating learning and application of neural network topologies in machine learning at autonomous machines. A method of embodiments, as described herein, includes monitoring and detecting structure learning of neural networks relating to machine learning operations at a computing device having a processor, and generating a recursive generative model based on one or more topologies of one or more of the neural networks. The method may further include converting the generative model into a discriminative model.

Abstract: A property vector representing extractable measurable properties, such as musical properties, of a file is mapped to semantic properties for the file. This is achieved by using artificial neural networks “ANNs” in which weights and biases are trained to align a distance dissimilarity measure in property space for pairwise comparative files back towards a corresponding semantic distance dissimilarity measure in semantic space for those same files. The result is that, once optimised, the ANNs can process any file, parsed with those properties, to identify other files sharing common traits reflective of emotional-perception, thereby rendering a more liable and true-to-life result of similarity/dissimilarity. This contrasts with simply training a neural network to consider extractable measurable properties that, in isolation, do not provide a reliable contextual relationship into the real-world.

Abstract: Methods and systems for language processing includes initializing a word embedding matrix based on pre-determined word classes, such that matrix entries associated with a class of which a word is a member are initialized to a non-zero value and other entries are initialized to zero. A neural network is trained based on the initialized word embedding matrix to generate a neural network language model. A language processing task is performed using the neural network language model.

Abstract: Techniques of forecasting web metrics involve generating, prior to the end of a period of time, a probability of a metric taking on an anomalous value, e.g., a value indicative of an anomaly with respect to web traffic, at the end of the period based on previous values of the metric. Such a probability is based on a distribution of predicted values of the metric at some previous period of time. For example, a web server may use actual values of the number of bounces collected at hourly intervals in the middle of a day to predict a number of bounces at the end of the current day. Further, the web server may also compute a confidence interval to determine whether a predicted end-of-day number of bounces may be considered anomalous. The width of the confidence interval indicates the probability that a predicted end-of-day number of bounces has an anomalous value.

Abstract: Embodiments of the present disclosure allow accuracy of prediction of pollution to be improved. In operation, a prediction of pollution in a future time period is determined. The prediction of pollution indicates predicted data related to a pollution index. Then, matching historical data for the predicted data is determined from historical data related to the pollution index. The matching historical data is obtained in a historical time period corresponding to the future time period. Based on the matching historical data, the prediction of pollution is refined.

Abstract: A method for ranking detected anomalies is disclosed. The method includes generating a graph based on a plurality of rules, wherein the graph comprises nodes representing metrics identified in the rules, edges connecting nodes where metrics associated with connected nodes are identified in a given rule, and edge weights of the edges each representing a severity level assigned to the given rule. The method further includes ranking nodes of the graph based on the edge weights. The method further includes ranking detected anomalies based on the ranking of the nodes corresponding to the metrics associated with the detected anomalies.

Abstract: The subject-matter described herein relates to a computer-implemented method of enabling interoperability between a first knowledge base and a second knowledge base. Each knowledge base is graphically represented and includes a plurality of nodes each defining a concept and a plurality of relations linking the plurality of nodes. The first knowledge base and the second knowledge base are encoded using different coding standards. The method comprises: identifying an entity from the plurality of entities in the second knowledge base; obtaining a mapping between the identified entity from the second knowledge base and a matching entity from the first knowledge base; and creating and storing a link between the identified entity from the second knowledge base and the matching entity from the first knowledge base.

Abstract: The technology disclosed provides a quasi-recurrent neural network (QRNN) encoder-decoder model that alternates convolutional layers, which apply in parallel across timesteps, and minimalist recurrent pooling layers that apply in parallel across feature dimensions.

Abstract: A property vector representing extractable measurable properties, such as musical properties, of a file is mapped to semantic properties for the file. This is achieved by using artificial neural networks “ANNs” in which weights and biases are trained to align a distance dissimilarity measure in property space for pairwise comparative files back towards a corresponding semantic distance dissimilarity measure in semantic space for those same files. The result is that, once optimised, the ANNs can process any file, parsed with those properties, to identify other files sharing common traits reflective of emotional-perception, thereby rendering a more liable and true-to-life result of similarity/dissimilarity. This contrasts with simply training a neural network to consider extractable measurable properties that, in isolation, do not provide a reliable contextual relationship into the real-world.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory. One of the systems includes a memory interface subsystem that is configured to perform operations comprising determining a respective content-based weight for each of a plurality of locations in an external memory; determining a respective allocation weight for each of the plurality of locations in the external memory; determining a respective final writing weight for each of the plurality of locations in the external memory from the respective content-based weight for the location and the respective allocation weight for the location; and writing data defined by the write vector to the external memory in accordance with the final writing weights.

Abstract: A method of avoiding harmful chemical emission concentration levels, the method comprising implementing a cognitive suite of workplace hygiene and injury predictors (WHIP) that has learned to identify chemical emission sources and indicators of harmful chemical emission concentration levels, detecting an indicator, and implementing a corrective action by at least one of altering the operation of a chemical emissions source, modifying a time of a scheduled task, or changing prescribed personal protective equipment.

Abstract: According to an embodiment, a processing network is configured to access a reputation system, provide a first user interface, provide a second user interface, receive a request from a user through the second user interface, retrieve user information from the reputation system, assign a plurality of human intelligence tasks based on the request, receive a plurality of results from the plurality of human intelligence tasks, confirm an identity and a status of the user based on the user information and the plurality of results, execute the request based on confirming the identity and the status of the user, and store evidence of execution of the request as an immutable data entry in a permanent database. The first user interface includes information from the reputation system, and the plurality of human intelligence tasks are assigned to a plurality of participants through the first user interface.

Abstract: Training method and apparatus for loan fraud detection model and a computer device are provided, wherein the training method for loan fraud detection model includes: acquiring identity information and user's bank statement information of a plurality of sample users, and fraud label information corresponding to each user; constructing an identity feature vector and a behavior pattern vector according to the identity information; constructing a statement feature vector according to the behavior pattern vector, a second vector transformation matrix and the user's bank statement information; generating a target feature vector according to the behavior pattern vector and the statement feature vector; feeding a target neural network with the target feature vector to acquire a fraud detection result of the target feature vector; and training the target neural network, the first vector transformation matrix and the second vector transformation matrix to obtain a loan fraud detection model.

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 with dedicated storage and a routing element. Each router enables communication with nearest neighbors in a 2D mesh. The communication is via wavelets in accordance with a representation comprising an index specifier, a virtual channel specifier, a task specifier, a data element specifier, and an optional control/data specifier. The virtual channel specifier and the task specifier are associated with one or more instructions. The index specifier and the data element are optionally associated with operands of the one or more instructions.

Abstract: According to an embodiment, a machine learning apparatus includes an interlayer accelerator. The interlayer accelerator includes interlayer units that generate, based on (a) an input vector of a first layer included in a neural network that includes three or more layers and (b) a learning weight matrix of the first layer, an input vector of a second layer next to the first layer. Each of the interlayer units includes a coupled oscillator array. The coupled oscillator array includes oscillators that oscillate at frequencies corresponding to differences between elements of the input vector of the first layer and elements of a row vector that is one row of the learning weight matrix, and combines oscillated signals generated by the oscillators to obtain a calculated signal.

Abstract: Embodiments of the present invention relate to apparatuses, systems, methods and computer program products for a technology configuration system. Specifically, the system typically provides operational data processing of a plurality of records associated with information technology operational activities, for dynamic transformation of data and evaluation of interdependencies of technology resources. In other aspects, the system typically provides technical language processing of the plurality of records for transforming technical and descriptive data, and constructing categorical activity records. The system may be configured to achieve significant reduction in memory storage and processing requirements by performing categorical data encoding of the plurality of records.