Abstract: A system for confirming an advisory interaction with an artificial intelligence platform. The system includes a constitutional generator module configured to receive a first advisory input, retrieve an expert input, select a machine-learning process as a function of the expert input, and generate a therapeutic corrector. The system includes a constitutional advisory module configured to display a therapeutic corrector on a graphical user interface and receive a second advisory input. The system includes a best practices module the best practices module designed and configured to retrieve from an expert database a best practices training set, calculate an optimal vector output, generate an optimal vector output containing an expected therapeutic corrector implementation response, authenticate a second advisory input, and update the best practices module.

Abstract: A neural network system is proposed to select actions to be performed by an agent interacting with an environment to perform a task in an attempt to achieve a specified result. The system may include a controller to receive state data and context data, and to output action data. The system may also include an imagination module to receive the state and action data, and to output consequent state data. The system may also include a manager to receive the state data and the context data, and to output route data which defines whether the system is to execute an action or to imagine. The system may also include a memory to store the context data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a machine learning model that has been trained through reinforcement learning to select a content item. One of the methods includes receiving first data characterizing a first context in which a first content item may be presented to a first user in a presentation environment; and providing the first data as input to a long-term engagement machine learning model, the model having been trained through reinforcement learning to: receive a plurality of inputs, and process each of the plurality of inputs to generate a respective engagement score for each input that represents a predicted, time-adjusted total number of selections by the respective user of future content items presented to the respective user in the presentation environment if the respective content item is presented in the respective context.

Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing counterfactual regret minimization (CFR) for strategy searching in strategic interaction between parties. One of the methods includes: identifying N1 possible actions of a first party in a first state of the first party; sampling a possible action out of the N1 possible actions in the first state of the first party with a first sampling probability; identifying N2 possible actions of the first party in a second state of the first party, wherein the first state of the first party is closer to a beginning state of the IIG than the second state of the first party; sampling a possible action out of the N2 possible actions in the second state of the first party with a second sampling probability, wherein the first sampling probability is less than the second sampling probability.

Abstract: Techniques are described for classifying seasonal patterns in a time series. In an embodiment, a set of time series data is decomposed to generate a noise signal and a dense signal, where the noise signal includes a plurality of sparse features from the set of time series data and the dense signal includes a plurality of dense features from the set of time series data. A set of one or more sparse features from the noise signal is selected for retention. After selecting the sparse features, a modified set of time series data is generated by combining the set of one or more sparse features with a set of one or more dense features from the plurality of dense features. At least one seasonal pattern is identified from the modified set of time series data. A summary for the seasonal pattern may then be generated and stored.

Abstract: Mechanisms for automatically modifying a set of instructions based on an expanded domain specific knowledge base are provided. The mechanisms generate a domain specific knowledge base comprising a set of entities and corresponding domain specific attributes and expand the domain specific knowledge base to include values for the domain specific attributes through an automated bootstrap learning process that performs natural language processing and analysis of natural language content using a set of pre-condition annotated action terms. The mechanisms receive electronic content comprising an initial set of instructions to perform an operation and evaluate the initial set of instructions based on the expanded domain specific knowledge base to identify a missing instruction. The mechanisms modify the initial set of instructions to include an additional instruction based on the missing instruction and thereby generate a modified set of instructions.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model, wherein the machine learning model has been trained on training data to perform a plurality of machine learning tasks including the first machine learning task, and wherein the machine learning model has been configured through training to process the augmented model input to generate a machine learning model output of the first type for the model input.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model. An exemplary system applying implicit bridging for machine learning tasks, as described in this specification, trains a machine learning model to perform certain types of machine learning tasks without requiring explicit training data for the certain types of machine learning tasks to be used during training.

Abstract: An information processing apparatus generates multiple combinations of sensor data inputted to a machine learning apparatus, inputs the combinations of sensor data to the machine learning apparatus, and generates a recognizer corresponding to each of the combinations of sensor data. Further, the performance of the recognizers is evaluated in accordance with expected performance required for the recognizers, and the combinations of sensor data corresponding to the recognizers satisfying the expected performance are outputted. Thus, the rates of contribution of two or more pieces of sensor data inputted to the machine learning apparatus are evaluated, and the configuration of sensors is optimized.

Abstract: A schedule management method is provided. The schedule management method includes acquiring user schedule information, extracting at least one piece of expected event information based on the user schedule information, collecting event information generated through near field communication, comparing the collected event information and the expected event information, and providing guidance information corresponding to the collected event information based on a result of the comparison.

Abstract: Mechanisms are provided in which a first knowledge graph, comprising nodes representing entities and edges between nodes indicative of a relationship between the entities, is received. The mechanisms identify a candidate missing edge connecting a node of the first knowledge graph to another node not present in the first knowledge graph and evaluate the candidate missing edge to determine if the candidate missing edge should be added to the first knowledge graph. The mechanisms expand the first knowledge graph to include the candidate missing edge connecting the node to a newly added node that is newly added to the first knowledge graph, to thereby generate an expanded knowledge graph, in response to the evaluation indicating that the candidate missing edge should be added to the first knowledge graph. The mechanisms then perform an operation on the expanded knowledge graph to generate a knowledge output.

Abstract: A recycle bin management method, system, and non-transitory computer readable medium, include a cognitive detection circuit configured to detect a cognitive state and a cognitive characteristic of a user at a time when the user is performing a first deletion of a file to a recycle bin and a file tagging circuit configured to tag the file with a cognitive indicator based on the cognitive state and cognitive characteristic of the user, the cognitive indicator altering a visual display of the file in the recycle bin to indicate the cognitive state and the cognitive characteristic of the user before the user performs a second deletion to delete the file from the recycle bin.

Abstract: Provided herein is a method, a programmed computer and an article of manufacture for predicting a prenatal, neonatal, obstetric or childhood clinical event, disease or disorder, as well as a method for generating in-utero fetal and placental growth curves, using a continuous recursive algorithm housed in a computer and data periodically collected during pregnancy.

Abstract: A neuromorphic memory circuit including a memory cell with a programmable resistive memory element. A postsynaptic capacitor builds up a leaky integrate and fire (LIF) charge. An axon LIF pulse generator activates a LIF discharge path from the postsynaptic capacitor through the resistive memory element when the axon LIF pulse generator generates axon LIF pulses. A postsynaptic comparator compares the capacitor voltage to a threshold voltage and generates postsynaptic output pulses when the capacitor voltage passes the threshold voltage. The postsynaptic output pulses include a postsynaptic firing characteristic dependent on a frequency of the axon LIF pulses. A refractory circuit prevents the postsynaptic comparator from generating additional postsynaptic output pulses until a refractory time passes since a preceding postsynaptic output pulse. A training circuit adjusts the postsynaptic firing characteristic to match a target firing characteristic.

Abstract: Weighted population code in neuromorphic systems is provided. According to an embodiment, a plurality of input values is received. For each of the plurality of values, a plurality of spikes is generated. Each of the plurality of spikes has an associated weight. A consumption time is determined for each of the plurality of spikes. Each of the plurality of spikes is sent for consumption at its consumption time.

Abstract: Executing a neural network includes generating an output tile of a first layer of the neural network by processing an input tile to the first layer and storing the output tile of the first layer in an internal memory of a processor. An output tile of a second layer of the neural network can be generated using the processor by processing the output tile of the first layer stored in the internal memory.

Abstract: A system for filtering data for a traffic control center includes: a plurality of data sources, comprising a plurality of traffic-related data sources and a weather-related data source; one or more network computing devices, configured to process data from the plurality of data sources to predict causes associated with predicted traffic incidents, and to select data from the plurality of data sources to be output to the traffic control center based on the predicted causes; and one or more output devices, located at the traffic control center, configured to display respective data selected by the one or more network computing devices.

Abstract: A spiking neural network having a plurality layers partitioned into a plurality of frustums using a first partitioning may be implemented, where each frustum includes one tile of each partitioned layer of the spiking neural network. A first tile of a first layer of the spiking neural network may be read. Using a processor, a first tile of a second layer of the spiking neural network may be generated using the first tile of the first layer while storing intermediate data within an internal memory of the processor. The first tile of the first layer and the first tile of the second layer belong to a same frustum.

Abstract: In an example embodiment, for each of one or more input documents: a first value is determined for the first metric for a first transformation of the input document by passing the first transformation to s first Deep Convolutional Neural Network (DCNN), a second transformation of the input document is determined by passing the input document to a second DCNN, the second transformation of the input document is passed to the first DCNN, obtaining a second value for the first metric for the second transformation of the input document, the first and second transformations being of the first transformation type, and a difference between the first value and the second value for the input document is determined. Then it is determined whether to change the system over from the first DCNN to the second DCNN based on the difference between the first value and the second value.

Abstract: Disclosed herein is a method and system for recommending one or more events based on mood of a person. The method comprises receiving activity data associated with one or more activities of the person and personal information of the person from data sources. The received activity data is classified into one or more predefined categories. An event profile of the person is generated based on the classified activity data. Thereafter, a sensitivity score of the person is determined based on impact of a current event on the person, activity score of the person and correlation of the current event with one or more events occurred simultaneously with the current event. Further, a mood score of the person is determined based on the sensitivity score and the event profile of the person. Furthermore, events are recommended to the person based on the sensitivity score and the mood score of the person.