Abstract: A method, a system, and a computer program product for predicting an outcome expected for a particular positional value is provided. In the method, an input set of data records, each having a label and a positional value, and a target positional value are obtained. The label of each data record is one in a label set. A learning model that includes an output layer, an input layer corresponding to the label set and a network structure provided therebetween is read. In the learning model, the network structure has a plurality of functions trained so as to evaluate influence from each label in the label set depending on a relationship between the target positional value and a representative positional value associated with the label in the label set. A target outcome is estimated for the target positional value from the input set using the learning model.

Abstract: Systems and methods for presenting configurable machine learning systems through graphical user interfaces are disclosed. In an embodiment, a machine learning server computer stores one or more machine learning configuration files. A particular machine learning configuration file of the one or more machine learning configuration files comprises instructions for configuring a machine learning system of a particular machine learning type with one or more first machine learning parameters. The machine learning server computer displays through a graphical user interface, a plurality of selectable parameter options, each of which defining a value for a machine learning parameter. The machine learning server computer receives a particular input dataset.

Abstract: Entities and relations associated with source code of a program are extracted. An entity completion on the extracted entities and relationships is performed to produce a knowledge graph of the source code. Repeated patterns of relationships are identified from the knowledge graph across the source code.

Abstract: A predicting device of a production system includes a machine learning device that learns the relationship between a change in measurement data indicating the state of a power supply and a failure which occurs in the power supply. The machine learning device learns the measurement data including at least a measurement value of electric power consumption in a factory by correlating a state variable indicating the current state of an environment with judgment data indicating a failure notification indicating the occurrence of a failure. A control device of the production system includes a receiving section that receives a prediction notification of a failure which occurs in the power supply, the failure being predicted based on a change in the measurement data indicating the state of the power supply, and a retracting operation control section that makes a working machine transition to a safely retracted state when receiving the prediction notification.

Abstract: The technology disclosed relates to evolving deep neural network structures. A deep neural network structure includes a plurality of modules with submodules and interconnections among the modules and the submodules. In particular, the technology disclosed relates to storing candidate genomes that identify respective values for a plurality of hyperparameters of a candidate genome. The hyperparameters include global topology hyperparameters, global operational hyperparameters, local topology hyperparameters, and local operational hyperparameters. It further includes evolving the hyperparameters by training, evaluating, and procreating the candidate genomes and corresponding modules and submodules.

Abstract: The technology disclosed relates to evolving a deep neural network based solution to a provided problem. In particular, it relates to providing an improved cooperative evolution technique for deep neural network structures. It includes creating blueprint structures that include a plurality of supermodule structures. The supermodule structures include a plurality of modules. The modules are neural networks. A first loop of evolution executes at the blueprint level. A second loop of evolution executes at the supermodule level. Further, multiple mini-loops of evolution execute at each of the subpopulations of the supermodules. The first loop, the second loop, and the mini-loops execute in parallel.

Abstract: The present subject matter discloses a system and method to enable a machine learning based analytics platform. The method may comprise generating a graphical user interface to enable one or more stakeholders to generate and manage a model for predictive analysis. The method may further comprise enabling a business user to define the business problem, and generate models to perform predictive analysis. The method may further comprise deploying the model, in a distributed environment, over a target platform. The method may further comprise monitoring the model to identify at least one error in the model and re-training the model for performing predictive analysis based on the at least one error, thereby enabling the machine learning based analytics platform.

Abstract: A novel and useful augmented artificial neural network (ANN) incorporating an existing artificial neural network (ANN) coupled to a supplemental ANN and a first-in first-out (FIFO) stack for storing historical output values of the network. The augmented ANN exploits the redundant nature of information present in an input data stream. The addition of the supplemental ANN along with a FIFO enables the augmented network to look back into the past in making a decision for the current frame. It provides context aware object presence as well as lowers the rate of false detections and misdetections. The output of the existing ANN is stored in a FIFO to create a lookahead system in which both past output values of the supplemental ANN and ‘future’ values of the output of the existing ANN are used in making a decision for the current frame. In addition, the mechanism does not require retraining the entire neural network nor does it require data set labeling.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for environment simulation. In one aspect, a system comprises a recurrent neural network configured to, at each of a plurality of time steps, receive a preceding action for a preceding time step, update a preceding initial hidden state of the recurrent neural network from the preceding time step using the preceding action, update a preceding cell state of the recurrent neural network from the preceding time step using at least the initial hidden state for the time step, and determine a final hidden state for the time step using the cell state for the time step. The system further comprises a decoder neural network configured to receive the final hidden state for the time step and process the final hidden state to generate a predicted observation characterizing a predicted state of the environment at the time step.

Abstract: A surveillance system is coupled to a plurality of sensor data sources arranged at locations within a plurality of regions of a site under surveillance. The surveillance system accesses a threat model that identifies contextual events classified as threats. The surveillance system identifies at least one contextual event for a site in real-time by processing sensor data generated by the sensor data sources, and co-occurring contextual data for at least one of the regions. Each identified contextual event is classified as one of a threat and a non-threat by using the threat model.

Abstract: Techniques to mimic a target food item using artificial intelligence are disclosed. A formula generator learns from open source and proprietary databases of ingredients and recipes. The formula generator is trained using features of the ingredients and using recipes. Given a target food item, the formula generator determines a formula that matches the given target food item and a score for the formula. The formula generator may generate, based on user-provided control definitions, numerous formulas that match the given target food item and may select an optimal formula from the generated formulas based on score.

Abstract: A method, system and computer-usable medium are disclosed for the use of a text simplification in a question answering (QA) system to improve ingestion quality and QA performance. A source corpus is processed to generate a parsed source corpus, which in turn is processed to generate a shadow corpus of simplified text. The parsed source corpus and the shadow corpus are then processed to generate derived data resources. A user query is processed to generate a set of merged candidate answer variants which are in turn processed to generate a corresponding converged feature vector representing each merged candidate answer variant. Feature values associated with each converged feature vector are then used to rank the merged candidate answer variants. A ranked set of merged candidate answer variants is then provided to the user.

Abstract: A system for classification using expert data includes at least a server. The system includes an expert submission processing module operating on the at least a server, the expert submission processing module designed and configured to receive at least an expert submission relating constitutional data to ameliorative recommendation data. The system includes a model generator operating on the at least a server, the model generator designed and configured to generate, using the at least an expert submission, and a constitutional inquiry, an ameliorative output. The system includes a client-interface module operating on the at least a server, the client-interface module designed and configured to receive, from a user client device, the constitutional inquiry and transmit, to the user client device, the ameliorative output.

Abstract: A method of configuring a hardware implementation of a Convolutional Neural Network (CNN), the method comprising: determining, for each of a plurality of layers of the CNN, a first number format for representing weight values in the layer based upon a distribution of weight values for the layer, the first number format comprising a first integer of a first predetermined bit-length and a first exponent value that is fixed for the layer; determining, for each of a plurality of layers of the CNN, a second number format for representing data values in the layer based upon a distribution of expected data values for the layer, the second number format comprising a second integer of a second predetermined bit-length and a second exponent value that is fixed for the layer; and storing the determined number formats for use in configuring the hardware implementation of a CNN.

Abstract: An input data set with a plurality of item descriptors comprising respective time series observations is identified. A routing directive indicating a predicate to be evaluated to determine whether a particular item descriptor is to be included in a training data set for a first learning algorithm is obtained. A plurality of learning algorithms are trained using training data sets derived from the input data set according to respective routing directives, and the trained algorithms are stored.

Abstract: Some aspects are directed to a method of operating an apparatus, the apparatus comprising a first quantum system having a plurality of coherent quantum states, the first quantum system being coupled to a second quantum system, the method comprising providing an input energy signal to the second quantum system that stimulates energy transfer between the first quantum system and the second quantum system and that causes net dissipation of energy to be output from the second quantum system, wherein the input energy signal includes at least two components having different frequencies and each having an amplitude and a phase, and adiabatically varying the amplitude and the phase of the at least two components of the input energy signal to cause a change in one or more of the plurality of coherent quantum states of the first quantum system.

Abstract: A method for generating an output comprising one or more segments includes obtaining a plurality of profiles derived from unstructured data associated with a plurality of users, wherein a given one of the profiles corresponds to a respective one of the users; repetitively executing at least one machine learning technique on the plurality of profiles, each execution producing a respective set of one or more segments from the plurality of profiles; generating a complete graph by performing pairwise comparisons between sets of segments from respective executions; applying at least one persistency graph algorithm to the complete graph to find one or more coherent clusters comprising one or more segments that are persistent across the repetitive executions of the machine learning technique; and producing the output at least in part by selecting at least one of the segments from at least one of the coherent clusters.

Abstract: A method includes generating, by a processor of a computing device, an output set of models corresponding to a first epoch of a genetic algorithm and based on an input set of models of the first epoch. The input set and the output set includes data representative of a neural network. The method includes determining a particular model of the output set based on a fitness function. A first topological parameter of a first model of the input set is modified to generate the particular model of the output set. The method includes modifying a probability that the first topological parameter is to be changed by a genetic operation during a second epoch of the genetic algorithm that is subsequent to the first epoch. The method includes generating a second output set of models corresponding to the second epoch and based on the output set and the modified probability.

Abstract: A system for identifying a causal link, the system including a diagnostic generator module configured to receive a first user symptom datum, receive diagnostic training data, and generate using a supervised machine-learning process a diagnostic model that outputs a first prognosis. The system includes a prognostic chaining module configured to receive an expert input dataset, receive the first user symptom datum and the first prognosis, generate a gaussian mixture clustering model and identify a first causal link chained to the first prognosis. The system includes a causal link module configured to receive the first prognosis chained to the first causal link, receive a second prognosis chained to a second causal link, and evaluate the first causal link and the second causal link to calculate a degree of similarity between the first causal link and the second causal link.

Abstract: A method for generating an output comprising one or more segments includes obtaining a plurality of profiles derived from unstructured data associated with a plurality of users, wherein a given one of the profiles corresponds to a respective one of the users; repetitively executing at least one machine learning technique on the plurality of profiles, each execution producing a respective set of one or more segments from the plurality of profiles; generating a complete graph by performing pairwise comparisons between sets of segments from respective executions; applying at least one persistency graph algorithm to the complete graph to find one or more coherent clusters comprising one or more segments that are persistent across the repetitive executions of the machine learning technique; and producing the output at least in part by selecting at least one of the segments from at least one of the coherent clusters.