Abstract: Systems and/or devices for efficient and intuitive methods for implementing artificial neural networks specifically designed for parallel AI processing are provided herein. In various implementations, the disclosed systems, devices, and methods complement or replace conventional systems, devices, and methods for parallel neural processing that (a) greatly reduce neural processing time necessary to process more complex problem sets; (b) implement neuroplasticity necessary for self-learning; and (c) introduce the concept and application of implicit memory, in addition to explicit memory, necessary to imbue an element of intuition. With these properties, implementations of the disclosed invention make it possible to emulate human consciousness or awareness.

Abstract: This disclosure relates to systems and methods for determining predicted risk for a flight path of an unmanned aerial vehicle. A previously stored three-dimensional representation of a user-selected location may be obtained. The three-dimensional representation may be derived from depth maps of the user-selected location generated during previous unmanned aerial vehicle flights. The three-dimensional representation may reflect a presence of objects and object existence accuracies for the individual objects. The object existence accuracies for the individual objects may provide information about accuracy of existence of the individual objects within the user-selected location. A user-created flight path may be obtained for a future unmanned aerial flight within the three-dimensional representation of the user-selected location. Predicted risk may be determined for individual portions of the user-created flight path based upon the three-dimensional representation of the user-selected location.

Abstract: Contemplated systems and methods allow for prediction of chemotherapy outcome for patients diagnosed with high-grade bladder cancer. In particularly preferred aspects, the prediction is performed using a model based on machine learning wherein the model has a minimum predetermined accuracy gain and wherein a thusly identified model provides the identity and weight factors for omics data used in the outcome prediction.

Abstract: A record extraction request for a data set is received at a machine learning service. A plan to perform one or more chunk-level operations (such as sampling, shuffling, splitting or partitioning for parallel computation) on chunks of the data set is generated. A set of data transfers that results in a particular chunk being stored in a particular server's memory is initiated to implement the first chunk-level operation of the sequence. A second operation such as another filtering operation or a feature processing operation is performed on a result set of the first chunk-level operation.

Abstract: A computing device predicts occurrence of an event or classifies an object using distributed unlabeled data. A Laplacian matrix is computed using a kernel function. A predefined number of eigenvectors is selected from a decomposed Laplacian matrix to define a decomposition matrix. A gradient value is computed as a function of the defined decomposition matrix, a plurality of sparse coefficients, and a label matrix, a value of each coefficient of the plurality of sparse coefficients is updated based on the computed gradient value, and the computations are repeated until a convergence parameter value indicates the plurality of sparse coefficients have converged. A classification matrix is defined using the plurality of sparse coefficients to determine the target variable value for each observation vector of the plurality of unclassified observation vectors. The target variable value for each observation vector of the plurality of unclassified observation vectors is output.

Abstract: An electronic device may determine whether a machine-learning model is operating within predefined limits. In particular, the electronic device may receive, from another electronic device, instructions for the machine-learning model, a reference input and a predetermined output of the machine-learning model for the reference input. Note that the instructions may include an architecture of the machine-learning model, weights associated with the machine-learning model and/or a set of pre-processing transformations for use when executing the machine-learning model on images. In response, the electronic device may configure the machine-learning model based on the instructions. Then, the electronic device may calculate an output of the machine-learning model for the reference input. Next, the electronic device may determine whether the machine-learning model is operating within predefined limits based on the output and the predetermined output.

Abstract: An artificial intelligence system for communicating predicted hours of operation to a client device. The system may include a processor in communication with a client device and a database; and a storage medium storing instructions.

Abstract: A processor-implemented method, system, and/or computer program product improves operation of a computer. One or more processors receive a question from a user of a computer, which requests a solution to improve operations of the computer. Based on an interpretation derived from the context of the request, the processor(s) retrieve multiple child solution instances to the question, where the multiple child solution instances are derived from a parent solution instance. The processor(s) direct the computer to simultaneously display the multiple child solution instances on the computer, and then receive a selected child solution instance from the user. In response to receiving the selected child solution instance, the processor(s): discard other solution instances from the multiple child solution instances; designate the selected child solution instance as a primary solution instance; and store the primary solution instance. The processor(s) then direct execution of the primary solution instance.

Abstract: A control device which predicts the timing of disconnection of a power supply is provided with a machine learning device configured to learn the disconnection timing of the power supply. The machine learning device is provided with a state observation unit configured to observe an operation content for the control device for each user as one of state variables representative of a present state of an environment, a determination data acquisition unit configured to acquire determination data which indicates that power disconnection of the control device is commanded by the user, and a learning unit configured to learn the operation content for each user and a command for the power disconnection in association with each other by using the state variable and the determination data.

Abstract: A system and method in which a device will search for and work collaboratively with an expert to respond to a request that the device is unable to respond to on its own. The expert may be one or more of, or a combination of, a human, a virtual persona, a robot or another device.

Abstract: A method and system for an AI-based communication training system for individuals and organizations is disclosed. A video analyzer is used to convert a video signal into a plurality of human morphology features with an accompanying audio analyzer converting an audio signal into a plurality of human speech features. A transformation module transforms the morphology features and the speech features into a current multi-dimensional performance vector and combinatorial logic generates an integration of the current multi-dimensional performance vector and one or more prior multi-dimensional performance vectors to generate a multi-session rubric. Backpropagation logic applies a current multi-dimensional performance vector from the combinatorial logic to the video analyzer and the audio analyzer.

Abstract: Time-series projections can be analyzed and manipulated via an interactive graphical user interface generated by a system. The graphical user interface can include a graph depicting an aggregated time-series projection (ATSP) over a future time. The ATSP can be generated by aggregating multiple time-series. The system can receive user input indicating that an existing value in the ATSP is to be overridden with an override value. In response, the system can adjust the ATSP using the override value to generate an updated version of the ATSP. The system can display the updated version of the ATSP in the graphical user interface. The system can also propagate the impact of overriding the existing value with the override value through the multiple time-series. The system can display an impact analysis portion within the graphical user interface indicating the impact of overriding the existing value with the override value on the multiple time-series.

Abstract: An analog neuromorphic circuit is disclosed having resistive memories that provide a resistance to an input voltage signal as the input voltage signal propagates through the resistive memories generating a first output voltage signal and to provide a resistance to a first error signal that propagates through the resistive memories generating a second output voltage signal. A comparator generates the first error signal that is representative of a difference between the first output voltage signal and the desired output signal and generates the first error signal so that the first error signal propagates back through the plurality of resistive memories. A resistance adjuster adjusts a resistance value associated with each resistive memory based on the first error signal and the second output voltage signal to decrease the difference between the first output voltage signal and the desired output signal.

Abstract: Methods and apparatus to generate data for geographic areas are disclosed. An example method includes identifying a first geographic area for which a database does not include a model, determining a first data element of the first geographic area, identifying a first trained model corresponding to a second geographic area with the first data element, identifying a second trained model corresponding to a third geographic area with the first data element, mixing the first trained model and the second trained model to generate a composite model, and using the composite model to represent the first geographic area in the database.

Abstract: Disclosed herein are system, method, and computer program product embodiments for performing a regression analysis on lawfully collected personal data records. The analysis enables discovery of individuals likely to perform certain actions based on their personal data records and the personal data records and actions of others. The disclosed system, method, and computer program product may process vast quantities of data, including personal data records with thousands of categories and lawfully stored databases with millions of personal data records. Through the regression analysis, the disclosed system, method, and computer program product learn the most relevant categories for predicting an individual's actions based on input data provided by a user. The analysis then analyzes the categories of personal data records stored in a lawfully stored database to predict actions of individuals associated with those records and outputs results to the user.

Abstract: Computer-based models can be developed, deployed, and managed in an automated manner. For example, a model building tool can be selected based on the model building tool being compatible with one or more parameters. A first machine-learning model can be generated using the model building tool and trained using a training dataset. The first machine-learning model can then be used to perform a task. Thereafter, a new model-building tool can be selected based on the new model-building tool being compatible with the one or more parameters. A second machine-learning model can be generated using the new model-building tool and trained using the training dataset. The accuracy of the first machine-learning model can be compared to the accuracy of the second machine-learning model. Based on the second machine-learning model being more accurate, the second machine-learning model can be used to perform the particular task rather than the first machine-learning model.

Abstract: A method of generating the knowledge base used for a programmable fuzzy controller comprising the steps of determining the relevant input and output variables to be controlled; creating artificial potential fields for each of said variables; sampling each of said potential fields in order to generate fuzzy membership functions; compiling said fuzzy membership functions into fuzzy sets; and mapping inputs fuzzy set to output fuzzy sets through a rule base. The relevant input and output variables are including: minimum, maximum, and equilibrium values; an importance weight; a non-linearity value; a control direction; and information as to whether said variable is an input or output variable. Further provided is a programmable fuzzy controller whose fuzzy knowledge base is obtained by the method described.

Abstract: A learning method for providing a functional safety by warning a driver about a potential dangerous situation by using an explainable AI which verifies detection processes of a neural network for an autonomous driving is provided.

Abstract: A method for inferring a location where each textual message was posted by a test user method includes partitioning an area into a plurality of sub-areas, associating textual messages posted by training users with respective sub-areas where each textual message was posted, extracting a keyword characterizing each sub-area among one or more keywords obtained from each textual message posted by the training users associated with each sub-area, constructing a feature vector of the given sub-area based on each extracted keyword, computing a transition probability for the given sub-area by time-series of location information associated with the textual messages posted by the training user, computing a plurality of scores of each location, using the feature vector, where each textual message was posted by the test user, and computing, based on the plural scores and the transition probability, time-series of locations where each textual message was posted by the test user.

Abstract: An apparatus comprises a processing platform configured to implement a machine learning system for automated classification of documents comprising text data of at least one database. The machine learning system comprises a clustering module configured to assign each of the documents to one or more of a plurality of clusters corresponding to respective topics identified from the text data in accordance with at least one topic model, and an interface configured to present portions of documents assigned to a particular one of the clusters by the clustering module and to receive feedback regarding applicability of the corresponding topic to each of one or more of the presented portions on a per-portion basis. The topic model is updated based at least in part on the received feedback. The feedback may comprise, for example, selection of a confidence level for applicability of the topic to a given one of the presented portions.