Patents Issued in December 24, 2020
-
Publication number: 20200401886Abstract: The present disclosure provides methods and systems for providing machine learning model service. The method may comprise: (a) generating, by a first computing system, a first output data using a first machine learning model, wherein the first machine learning model is trained on a first training dataset; (b) transmitting the first output data to a second computing system, wherein the first training dataset and the first machine learning model are inaccessible to the second computing system; (c) creating an input data by joining the first output data with a selected set of input features accessible to the second computing system; and (d) generating a second output data using a second machine learning model to process the input data.Type: ApplicationFiled: June 17, 2020Publication date: December 24, 2020Inventors: Jian Gong Deng, Ikkjin Ahn, Daeseob Lim, Bokyung Choi, Sechan Oh, William Kanaan
-
Publication number: 20200401887Abstract: A method and system for automatically deriving and analyzing quantitative Deep Learning Best Value Index data is provided. The method and system to rank business processes based on multi-factorials and multi-facets parameters of best practice and using Artificial Intelligence (AI) to interpret and verify commonly used individual parameter data-points for specific business processes, weighted with predefined order and class (ranking), in which the sum of the total weight of all the parameters will be the dynamically morphing, applying AI deep learning output to create a dynamic value index (BVI—Best Value Index).Type: ApplicationFiled: June 18, 2020Publication date: December 24, 2020Inventors: Budi Kusnoto, ARYO HANDONO
-
Publication number: 20200401888Abstract: This disclosure relates generally to system and method for time series prediction using a sparse recurrent mixture density network (RMDN), such as sparse LSTM-MDN and a sparse ED-MDN, for accurate forecasting of a high variability time series. The disclosed sparse RMDN has the ability to handle high-dimensional input features, capture trend shifts and high variability present in the data, and provide a confidence estimate of the forecast. A high-dimensional time series data is passed through a feedforward layer, which performs dimensionality reduction in an unsupervised manner by inducing sparsity on weights of the feedforward layer. The resultant low-dimensional time series is fed through recurrent layers to capture temporal patterns. These recurrent layers also aid in learning latent representation of the input data. Thereafter, a mixture density network (MDN) is used to model the variability and trend shifts present in the input and it also estimates the confidence of the predictions.Type: ApplicationFiled: June 23, 2020Publication date: December 24, 2020Applicant: Tata Consultancy Services LimitedInventors: Narendhar GUGULOTHU, Easwara Naga SUBRAMANIAN, Sanjay Purushottam BHAT
-
Publication number: 20200401889Abstract: The present disclosure relates to an artificial intelligence (AI) system that utilizes a machine learning algorithm, and applications therefore. Disclosed is an electronic device. The electronic device comprises: a storage unit which stores therein an artificial intelligence model trained to determine parameters for a plurality of filters used for image processing on the basis of a deep neural network (DNN); and a processor for determining, through the artificial intelligence mode, parameters for each of the plurality of filters used for image processing for an input image, and performing, through the plurality of filters, filtering of the input image on the basis of the determined parameters so as to perform image processing for the input image.Type: ApplicationFiled: March 6, 2019Publication date: December 24, 2020Inventors: Cheon LEE, Sungho KANG, Hyungdal KWON, Yunjae LIM
-
Publication number: 20200401890Abstract: The disclosure provides a collaborative deep learning method and a collaborative deep learning apparatus. The method includes: sending an instruction for downloading a global model to a plurality of user terminals; receiving a set of changes from each user terminal; storing the set of changes; recording a hash value of the set of changes into a blockchain; obtaining a storage transaction number from the blockchain for the hash value of the set of changes; sending the set of changes and the storage transaction number to the plurality of user terminals; receiving the set of target user terminals from the blockchain; updating the current parameters of the global model based on sets of changes corresponding to the set of target user terminals; and returning the sending the instruction, to update the global model until the global model meets a preset condition.Type: ApplicationFiled: September 4, 2020Publication date: December 24, 2020Inventors: Ke XU, Zhichao ZHANG, Bo WU, Qi LI, Songsong XU
-
Publication number: 20200401891Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed for hardware-aware machine learning model training. An example apparatus includes a configuration determiner to determine a hardware configuration of a target hardware platform on which the machine learning model is to be executed, a layer generator to assign sparsity configurations to layers of the machine learning model based on the hardware configuration, and a deployment controller to deploy the machine learning model to the target hardware platform in response to outputs of the machine learning model satisfying respective thresholds, the outputs including a quantity of clock cycles to execute the machine learning model with the layers having the assigned sparsity configurations.Type: ApplicationFiled: September 4, 2020Publication date: December 24, 2020Inventors: Xiaofan Xu, Cormac Brick, Zsolt Biro
-
Publication number: 20200401892Abstract: A behavior planner for a vehicle generates a plurality of conditional action sequences of the vehicle using a tree search algorithm and heuristics obtained from one or more machine learning models. Each sequence corresponds to a sequence of anticipated states of the vehicle. At least some of the action sequences are provided to a motion selector of the vehicle. The motion selector generates motion-control directives based on the received conditional action sequences and on data received from one or more sensors of the vehicle, and transmits the directives to control subsystems of the vehicle.Type: ApplicationFiled: September 4, 2020Publication date: December 24, 2020Applicant: Apple Inc.Inventors: Joshua D. Redding, Luke B. Johnson, Martin Levihn, Nicolas F. Meuleau, Sebastian Brechtel
-
Publication number: 20200401893Abstract: Generally, the present disclosure is directed to systems and methods that perform adaptive optimization with improved convergence properties. The adaptive optimization techniques described herein are useful in various optimization scenarios, including, for example, training a machine-learned model such as, for example, a neural network. In particular, according to one aspect of the present disclosure, a system implementing the adaptive optimization technique can, over a plurality of iterations, employ an adaptive effective learning rate while also ensuring that the effective learning rate is non-increasing.Type: ApplicationFiled: September 8, 2020Publication date: December 24, 2020Inventors: Sashank Jakkam Reddi, Sanjiv Kumar, Manzil Zaheer, Satyen Chandrakant Kale
-
Publication number: 20200401894Abstract: In some aspects, a computing system can generate and optimize a neural network for risk assessment. The neural network can be trained to enforce a monotonic relationship between each of the input predictor variables and an output risk indicator. The training of the neural network can involve solving an optimization problem under a monotonic constraint. This constrained optimization problem can be converted to an unconstrained problem by introducing a Lagrangian expression and by introducing a term approximating the monotonic constraint. Additional regularization terms can also be introduced into the optimization problem. The optimized neural network can be used both for accurately determining risk indicators for target entities using predictor variables and determining explanation codes for the predictor variables. Further, the risk indicators can be utilized to control the access by a target entity to an interactive computing environment for accessing services provided by one or more institutions.Type: ApplicationFiled: September 8, 2020Publication date: December 24, 2020Inventors: Matthew TURNER, Lewis JORDAN, Allan JOSHUA
-
Publication number: 20200401895Abstract: Systems and methods for structured-pruning, zero-skipping and accelerated processing of an artificial neural network (ANN) are described. The ANN may include one or more convolution layers. 2D channels in filters of the convolution layers comprise fully pruned channels (FPCs), each containing only zero weights, and mixed channels (MCs), each containing at least one non-zero weight. At least a portion of the MCs satisfy a limited zero sequence (LZS) condition limiting the number and location of zeroes in the MC. The LZS condition may be based on a number of weights that a zero-skipping circuit of a computing system for processing the ANN is configured to evaluate and skip in a single cycle. Thus, when processing the structurally-pruned ANN using the zero-skipping method, the computing system may avoid processing zero weights. This may allow speeding up the ANN processing and reducing the power required for processing.Type: ApplicationFiled: June 21, 2019Publication date: December 24, 2020Inventors: SHAI LITVAK, EYAL HOCHBERG
-
Publication number: 20200401896Abstract: The specification describes methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a larger neural network from a smaller neural network. One of the described methods includes obtaining data specifying an original neural network and generating a larger neural network from the original neural network. The larger neural network has a larger neural network structure than the original neural network structure. The values of the parameters of the original neural network units and the additional neural network units are initialized so that the larger neural network generates the same outputs from the same inputs as the original neural network, and the larger neural network is trained to determine trained values of the parameters of the original neural network units and the additional neural network units from the initialized values.Type: ApplicationFiled: June 29, 2020Publication date: December 24, 2020Inventors: Ian Goodfellow, Tianqi Chen, Jonathon Shlens
-
Publication number: 20200401897Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for modifying a computational graph to include send and receive nodes. Communication between unique devices performing operations of different subgraphs of the computational graph can be handled efficiently by inserting send and receive nodes into each subgraph. When executed, the operations that these send and receive nodes represent may enable pairs of unique devices to conduct communication with each other in a self-sufficient manner. This shifts the burden of coordinating communication away from the backend, which affords the system that processes this computational graph representation the opportunity to perform one or more other processes while devices are executing subgraphs.Type: ApplicationFiled: September 9, 2020Publication date: December 24, 2020Inventors: Vijay Vasudevan, Jeffrey Adgate Dean, Sanjay Ghemawat
-
Publication number: 20200401898Abstract: Certain aspects of the present disclosure provide techniques for receiving data defining a neural network; analyzing the data to determine a depth-first cut point for a depth-first traversal portion of an overall network traversal; performing depth-first traversal for the depth-first portion of the overall network traversal; and performing layer-based traversal for a layer-based portion of the overall network traversal.Type: ApplicationFiled: June 18, 2020Publication date: December 24, 2020Inventor: Meghal VARIA
-
Publication number: 20200401899Abstract: A method for receiving training data for training a neural network to perform a machine learning task and for searching for, using the training data, an optimized neural network architecture for performing the machine learning task is described. Searching for the optimized neural network architecture includes: maintaining population data; maintaining threshold data; and repeatedly performing the following operations: selecting one or more candidate architectures from the population data; generating a new architecture from the one or more selected candidate architectures; for the new architecture: training a neural network having the new architecture until termination criteria for the training are satisfied; and determining a final measure of fitness of the neural network having the new architecture after the training; and adding data defining the new architecture and the final measure of fitness for the neural network having the new architecture to the population data.Type: ApplicationFiled: June 20, 2019Publication date: December 24, 2020Inventors: David Martin Dohan, David Richard So, Chen Liang, Quoc V. Le
-
Publication number: 20200401900Abstract: A method of performing a class incremental learning in a neural network apparatus, the method including training an autoencoder using first input embeddings with respect to a first class group, calculating a contribution value of each of parameters of the autoencoder and calculating a representative value with respect to each of at least one first class included in the first class group in the training of the autoencoder, retraining the autoencoder using second input embeddings with respect to a second class group, and updating the contribution value of the each of the parameters and calculating a representative value with respect to each of at least one second class included in the second class group in the retraining the autoencoder.Type: ApplicationFiled: March 26, 2020Publication date: December 24, 2020Applicants: Samsung Electronics Co., Ltd., Seoul National University R&DB FoundationInventors: Donghyun LEE, Euntae CHOI, Kyungmi LEE, Kiyoung CHOI
-
Publication number: 20200401901Abstract: A user device that receives plural strings of data corresponding to physiological data, generated from a training model trained in an unsupervised manner using concurrently implemented loss functions, and using a distance metric, relative to a threshold, applied between the plural strings to provide an indication of authenticity.Type: ApplicationFiled: May 8, 2020Publication date: December 24, 2020Inventors: MUSTAFA GHASSAN RADHA, LUCAS JACOBUS FRANCISCUS GEURTS, MARK ANTHONY HENNESSY, MARK THOMAS JOHNSON
-
Publication number: 20200401902Abstract: A container manager used in a method for configuring a deep learning program acquires deep learning program, and analyzes at least one performance indicator from the acquired deep learning program and sends the at least one performance indicator to a server. The server determines a hardware configuration and a container image according to the at least one performance indicator, generates a label containing the name of the server, the determined hardware configuration, and the container image, and sends the label to the container manager. The container manager receives the label from the server, and determines whether the label contain the name of the server, and deploys a container for the deep learning program if the label contains the name of the server.Type: ApplicationFiled: July 26, 2019Publication date: December 24, 2020Inventor: CHENG-YUEH LIU
-
Publication number: 20200401903Abstract: Methods and systems for encoding digital information in nucleic acid (e.g., deoxyribonucleic acid) molecules without base-by-base synthesis, by encoding bit-value information in the presence or absence of unique nucleic acid sequences within a pool, comprising specifying each bit location in a bit-stream with a unique nucleic sequence and specifying the bit value at that location by the presence or absence of the corresponding unique nucleic acid sequence in the pool But, more generally, specifying unique bytes in a bytestream by unique subsets of nucleic acid sequences. Also disclosed are methods for generating unique nucleic acid sequences without base-by-base synthesis using combinatorial genomic strategies (e.g., assembly of multiple nucleic acid sequences or enzymatic-based editing of nucleic acid sequences).Type: ApplicationFiled: August 31, 2020Publication date: December 24, 2020Inventors: Nathaniel Roquet, Hyunjun Park, Swapnil P. Bhatia
-
Publication number: 20200401904Abstract: Methods, apparatus, systems and articles of manufacture to provide a mutatable machine genetic structure are disclosed. An example apparatus includes memory including instructions for execution by a processor and a machine genetic structure specifying composition, performance, and health of a machine; and at least one processor. The processor is to execute the instructions to at least: evaluate the machine genetic structure with respect to an operating condition of the machine to identify a discrepancy and/or an opportunity for improvement for the machine genetic structure to satisfy the operating condition; determine a mutation of the machine genetic structure from a first sequence to a second sequence to address the discrepancy and/or opportunity for improvement to satisfy the operating condition; and set the machine genetic structure from the first sequence to the mutation of the second sequence to configure the machine for operation according to the machine genetic structure.Type: ApplicationFiled: June 24, 2019Publication date: December 24, 2020Inventors: Anurag Voleti, Sridhar Nuthi
-
Publication number: 20200401905Abstract: Systems, computer-implemented methods, and computer program products that can facilitate computing environment migration plan recommendation based on one or more latent entity computing property preferences are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an analysis component that employs a model to discover a latent computing property preference of an entity operating in a first computing environment. The computer executable components can further comprise a recommendation component that recommends a computing environment migration plan to a second computing environment based on the latent computing property preference of the entity. In some embodiments, the recommendation component recommends discovered latent computing property preferences of the entity to construct the computing environment migration plan.Type: ApplicationFiled: June 20, 2019Publication date: December 24, 2020Inventors: Jinho Hwang, Maja Vukovic, John Rofrano, Anup Kalia, Ya Bin Dang, Jie Ma, Lijun Mei
-
Publication number: 20200401906Abstract: Methods and systems are provided for communicating an announcement to passengers on a transportation vehicle. One method includes receiving by a first device, an input from a passenger of a transportation vehicle, the input reporting a problem at the transportation vehicle; transmitting the input by the first device to a second device; evaluating by the second device whether the problem identified by the input is to be resolved at the transportation vehicle; generating a response by the second device to address the problem, when the evaluation indicates that the problem can be resolved at the transportation vehicle; and updating a data structure by the second device for addressing the problem after the transportation vehicle has reached a destination, when the evaluation indicates that the problem cannot be resolved at the transportation vehicle.Type: ApplicationFiled: June 21, 2019Publication date: December 24, 2020Inventors: Philip Watson, Steven Bates
-
Publication number: 20200401907Abstract: A method, computer system, and computer program product for generating clothing suggestions for a user. In an embodiment, the method comprises capturing environmental information, using a computer system, for the user for one or more designated places during a time period; analyzing, using cognitive analysis using the computer system, specified thermal requirements of the user; generating, by the computer system, clothing suggestions for the user, based on the captured environmental information and the analyzed thermal requirements, for the one or more designated places during the time period; and communicating the clothing suggestions to the user. In embodiments, the generating clothing suggestions includes receiving clothing options for the user from a populated database of the user's clothing which is available for use; receiving an inventory of the clothing the user is wearing; and generating the clothing suggestions based on the clothing options and the clothing the user is wearing.Type: ApplicationFiled: June 24, 2019Publication date: December 24, 2020Inventors: Stan Kevin Daley, Craig M. Trim, Michael Bender, Jeremy R. Fox
-
Publication number: 20200401908Abstract: A method includes generating one or more graphs representing automatic content recognition (ACR) data associated with a computing device; identifying one or more paths representing at least a portion of the one or more graphs; training one or more models based on inputting the one or more paths into one or more machine-learning algorithms; producing one or more embeddings from the one or more models; and clustering the one or more embeddings to provide at least one cluster corresponding to a behavioral profile associated with the computing device.Type: ApplicationFiled: March 4, 2020Publication date: December 24, 2020Inventors: Andres Ortega, Ashwin Chandra, David Ho Suk Chung
-
Publication number: 20200401909Abstract: A method for selectively generating suggested default values for I/O configurations is provided. The method identifies a first selection including a first input value for an I/O configuration. The method determines a set of remaining input options based on the first selection. The method accesses a set of decision trees based on the set of remaining input options and selects a decision tree of the set of decision trees based on the first input value. The method generates a suggested value for a subsequent selection for the I/O configuration and causes presentation of the suggested value and a user interface element representing the subsequent selection.Type: ApplicationFiled: June 24, 2019Publication date: December 24, 2020Inventors: Norman Christopher Böwing, Qais Noorshams, Pradeep Parameshwaran, Marco Selig
-
Publication number: 20200401910Abstract: Embodiments are provided for intelligent causal knowledge analysis from data sources in a computing system by a processor. Multiple communications may be identified from one or more data sources. One or more causal statements having a cause-effect relationship may be extracted from the plurality of communications.Type: ApplicationFiled: June 18, 2019Publication date: December 24, 2020Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Oktie HASSANZADEH, Michael PERRONE, Shirin SOHRABI ARAGHI, Mark FEBLOWITZ, Debarun BHATTACHARJYA, Michael KATZ, Kavitha SRINIVAS
-
Publication number: 20200401911Abstract: The disclosed embodiments provide a system for processing data. During operation, the system receives, over a set of event streams, a set of logging events for actions performed between members and jobs over multiple channels. Next, the system aggregates a subset of the logging events spanning a logging window by a reference identifier (ID) generated based on a user session of a member, a first member ID for the member, and a first job ID for a job. The system then creates, based on a unified data logic, a record containing a subset of the actions represented by the logging events and contexts for the subset of the actions. Finally, the system outputs the record for use in subsequent analysis associated with the member and the job.Type: ApplicationFiled: June 24, 2019Publication date: December 24, 2020Applicant: Microsoft Technology Licensing, LLCInventors: Hang Zhang, Girish Kathalagiri Somashekariah, Nadia Fawaz, Caleb T. Johnson
-
Publication number: 20200401912Abstract: A system may receive events derived from historical sensor data. The system may generate repeat event records based on the events. The system may cluster the repeat event records into repeat event clusters. The system may determine filter ranges for the repeat event clusters. The system may generate a binarization filter comprising instructions to generate a binary sequence indicative of at least one of the filter ranges. The system may execute the binarization filter to generate binary sequences corresponding to the repeat event records, respectively. The system may train a prediction model based on the binary sequences. The system may deploy the binarization filter and the prediction model to a real-time platform.Type: ApplicationFiled: June 19, 2019Publication date: December 24, 2020Applicant: Accenture Global Solutions LimitedInventors: Onur Can Sert, Perikles Rammos, Md Faisal Zaman
-
Publication number: 20200401913Abstract: A resource configuration method and apparatus for heterogeneous cloud services are provided. The method may include: establishing a basic model with a general structure for at least two heterogeneous cloud services, where the basic model comprises a trend model and a periodic model; determining a cloud service in the at least two cloud services as a target cloud service, and acquiring a target historical data set of the target cloud service; training the trend model and the periodic model using the target historical data set; generating a target prediction model corresponding to the target cloud service based on the trained trend model and the trained periodic model; and generating, based on the target prediction model, a resource amount demanded by the target cloud service in a future time period, and configuring resources for the target cloud service according to the demanded resource amount.Type: ApplicationFiled: December 2, 2019Publication date: December 24, 2020Inventors: Xiaoxu Chen, Feng Liu, Tao Yang, Xiang Gao, Geng Li, Xianghui Zhang
-
Publication number: 20200401914Abstract: Systems and methods for automatically detecting annotation discrepancies in annotated training data samples and repairing the annotated training data samples for a machine learning-based automated dialogue system include evaluating a corpus of a plurality of distinct training data samples; identifying one or more of a slot span defect and a slot label defect of a target annotated slot span of a target training data sample of the corpus based on the evaluation; and automatically correcting one or more annotations of the target annotated slot span based on the identified one or more of the slot span defect and the slot label defect.Type: ApplicationFiled: June 8, 2020Publication date: December 24, 2020Inventors: Stefan Larson, Anish Mahendran, Parker Hill, Jonathan K. Kummerfeld, Michael A. Laurenzano, Lingjia Tang, Jason Mars
-
Publication number: 20200401915Abstract: A systems implements a gradient descent calculation, regression calculation, or other machine learning calculation on a dataset (e.g., a global dataset) using a coordination node including coordination circuitry that coordinates multiple worker nodes to create a distributed calculation architecture. In some cases, the worker nodes each hold a portion of the dataset and operate on their respective portion. In some cases, the gradient descent calculation, regression calculation, or other machine learning calculation is used to implement a targeted maximum likelihood scheme for causal inference estimation. The targeted maximum likelihood scheme may be used to conduct causal analysis of the observational data.Type: ApplicationFiled: June 19, 2020Publication date: December 24, 2020Applicant: Accenture Global Solutions LimitedInventors: Teresa Sheausan Tung, Mohamad Mehdi Nasr-Azadani, Yao A. Yang, Zaid Tashman, Maziyar Baran Pouyan
-
Publication number: 20200401916Abstract: Generative and inference machine learning models with discrete-variable latent spaces are provided. Discrete variables may be transformed by a smoothing transformation with overlapping conditional distributions or made natively reparametrizable by definition over a GUMBEL distribution. Models may be trained by sampling from different models in the positive and negative phase and/or sample with different frequency in the positive and negative phase. Machine learning models may be defined over high-dimensional quantum statistical systems near a phase transition to take advantage of long-range correlations. Machine learning models may be defined over graph-representable input spaces and use multiple spanning trees to form latent representations. Machine learning models may be relaxed via continuous proxies to support a greater range of training techniques, such as importance weighting. Example architectures for (discrete) variational autoencoders using such techniques are also provided.Type: ApplicationFiled: February 7, 2019Publication date: December 24, 2020Inventors: Jason T. Rolfe, Amir H. Khoshaman, Arash Vahdat, Mohammad H. Amin, Evgeny A. Andriyash, William G. Macready
-
Publication number: 20200401917Abstract: This disclosure relates generally to method and system for designing the formulated products. Conventional techniques for designing the formulated products, meeting final functional properties, are limited. Further, understanding user requirements and active incorporation of the user requirements during design phase is quite challenging. The present disclosure herein provides method and system that solve the technical problem of extracting the functional requirement by establishing continuous conversation with the user. An optimal prediction function for each functional requirement is determined by using a plurality of prediction models. An optimization technique along with an objective function is employed to determine optimized solutions comprising list of ingredients, possible concentration level of each ingredient, the process parameters, and the operating parameters for obtaining the desired formulation based on the user requirement.Type: ApplicationFiled: June 23, 2020Publication date: December 24, 2020Applicant: Tata Consultancy Services LimitedInventors: Santosh Vasant DAWARE, Rinu CHAKO, Deepak Shyamsunder JAIN, Shankar Balajirao KAUSLEY, Shally GUPTA, Pallavi BANDI, Dharmendra KUMAR, Beena RAI, Amit BHOWMIK, Umesh SINGH, Chelan Premkumar MALHOTRA, Purushottham Gautham BASAVARSU
-
Publication number: 20200401918Abstract: The present disclosure provides a recommendation to a user through a computer-based advice facility to rank search results by performing steps of receiving a search request from a user; retrieving a list of search results; ascertaining preferences of the user to create a taste and preference profile for the user; matching the user to other users with similar taste and preference profiles; and providing the search results to the user, wherein the search results are ranked according to the matched results selected by other users with similar taste and preference profiles. In embodiments, tastes and preferences of a user may be based on information inferred from a user's activity on a social network or augmented through other users that have a connection to the user through a social network.Type: ApplicationFiled: September 2, 2020Publication date: December 24, 2020Applicant: eBay Inc.Inventors: Thomas Pinckney, Christopher Dixon, Matthew Ryan Gattis
-
Publication number: 20200401919Abstract: Example methods disclosed herein include accessing common homes data for a group of common homes, the common homes data including return path data and panel meter data. Disclosed example methods also include accessing common homes data for a group of common homes, the common homes data including first return path data and corresponding panel meter data associated with respective ones of the common homes, grouping the common homes data into view segments, classifying the view segments based on whether the return path data in respective ones of the view segments has matching panel meter data to determine labeled view segments, generating features from the labeled view segments, training a machine learning algorithm based on the features, and applying second return path data to the trained machine learning algorithm to determine whether a media device associated with the second return path data is on or off.Type: ApplicationFiled: November 27, 2019Publication date: December 24, 2020Inventors: Michael Grotelueschen, Michael Evan Anderson, Fatemehossadat Miri, Demetrios Fassois, Tushar Chandra, David J. Kurzynski
-
Publication number: 20200401920Abstract: An apparatus includes a plurality of processing layers coupled in series. Each processing layer in the plurality of processing layers includes a Gaussian unit configured to perform a linear transformation on an input signal including a plurality of optical modes. The Gaussian unit includes a network of interconnected beamsplitters and phase shifters and a plurality of squeezers operatively coupled to the network of interconnected beamsplitters and phase shifters. Each processing layer also includes a plurality of nonlinear gates operatively coupled to the Gaussian unit and configured to perform a nonlinear transformation on the plurality of optical modes. The apparatus also includes a controller operatively coupled to the plurality of processing layers and configured to control a setting of the plurality of processing layers.Type: ApplicationFiled: June 18, 2019Publication date: December 24, 2020Inventors: Nathan KILLORAN, Thomas R. BROMLEY, Juan Miguel ARRAZOLA, Maria SCHULD, Nicolas QUESADA
-
Publication number: 20200401921Abstract: A quantum computing device is formed using a first chip and a second chip, the first chip having a first substrate, a first set of pads, and a set of Josephson junctions disposed on the first substrate. The second chip has a second substrate, a second set of pads disposed on the second substrate opposite the first set of pads, and a second layer formed on a subset of the second set of pads. The second layer is configured to bond the first chip and the second chip. The subset of the second set of pads corresponds to a subset of the set of Josephson junctions selected to avoid frequency collision between qubits in a set of qubits. A qubit is formed using a Josephson junction from the subset of Josephson junctions and another Josephson junction not in the subset being rendered unusable for forming qubits.Type: ApplicationFiled: June 19, 2019Publication date: December 24, 2020Applicant: International Business Machines CorporationInventors: JERRY M. CHOW, SAMI ROSENBLATT
-
Publication number: 20200401922Abstract: A qubit assembly includes a first superconducting loop comprising a first Josephson junction and a second Josephson junction, a second superconducting loop comprising the second Josephson junction and a third Josephson junction, and a third superconducting loop comprising the third Josephson junction and a fourth Josephson junction. A flux source is configured to provide a control flux to the second superconducting loop, such that the effective commutation relations between a first quantum operator corresponding to current in the first superconducting loop and a second quantum operator corresponding to current in the third superconducting loop can be changed by changing a magnitude of the control flux provided to the second superconducting loop by the flux source.Type: ApplicationFiled: June 19, 2019Publication date: December 24, 2020Applicant: NORTHROP GRUMMAN SYSTEMS CORPORATIONInventor: DAVID JAMES CLARKE
-
Publication number: 20200401923Abstract: A quantum circuit generator for a quantum computer includes a controller; and a plurality of analog conversion units (ACUs) operatively connected to the controller, each ACU being operatively connected to a corresponding qubit of a plurality of qubits, wherein each ACU is configured to convert a digital input from the controller into an analog input at a microwave frequency to control a quantum state of the corresponding qubit. The controller is configured to generate a quantum circuit using at least two qubits of the plurality of qubits, the at least two qubits being selected by the controller based on corresponding classical bits being mapped by the controller and based on latency of the generated quantum circuit so that the generated quantum circuit has a latency less than a threshold latency.Type: ApplicationFiled: June 19, 2019Publication date: December 24, 2020Inventors: Ali Javadiabhari, Scott D. Lekuch, Ken Inoue
-
Publication number: 20200401924Abstract: A modular superconducting quantum processor includes a first superconducting chip including a first plurality of qubits each having substantially a first resonance frequency and a second plurality of qubits each having substantially a second resonance frequency, the first resonance frequency being different from the second resonance frequency, and a second superconducting chip including a third plurality of qubits each having substantially the first resonance frequency and a fourth plurality of qubits each having substantially the second resonance frequency. The quantum processor further includes an interposer chip connected to the first superconducting chip and to the second superconducting chip. The interposer chip has interposer coupler elements configured to couple the second plurality of qubits to the fourth plurality of qubits.Type: ApplicationFiled: June 21, 2019Publication date: December 24, 2020Inventors: Hanhee Paik, Jae-Woong Nah, Paul S. Andry, Martin O. Sandberg
-
Publication number: 20200401925Abstract: Systems, computer-implemented methods, and computer program products that can facilitate quantum circuit topology selection based on frequency collisions between qubits, are described. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a simulation component that simulates operation of qubits in a subgraph topology of a graph representing a topology of a quantum circuit to determine a quantity of frequency collisions between the qubits. The computer executable components can further comprise a selection component that selects a quantum circuit topology based on the quantity of frequency collisions between the qubits.Type: ApplicationFiled: June 24, 2019Publication date: December 24, 2020Inventors: Jared Barney Hertzberg, Rasit Onur Topaloglu
-
Publication number: 20200401926Abstract: A system is presented for emulating sampling of a quantum computer having a plurality of qubits arranged in a grid topology with N columns. The system includes a classical processor that is configured by operational instructions to perform operations that include producing final weights and variable assignments for the N columns based on N iterative passes through the grid topology, wherein each of the N iterative passes generates preliminary weights and variable assignments for a corresponding subset of the N columns, wherein the preliminary weights and variable assignments for a selected column of the corresponding subset based on the preliminary weights and variable assignments generated for a column adjacent to the selected column of the corresponding subset, and wherein the sampling of the plurality of qubits is emulated by a sample based on the final weights and variable assignments for each of the N columns.Type: ApplicationFiled: March 31, 2020Publication date: December 24, 2020Applicant: Beit Inc.Inventors: Marcin Brianski, Witold Jarnicki, Lukasz Czerwinski
-
Publication number: 20200401927Abstract: A method for obtaining a plurality of entangled qubits represented by a lattice structure that includes a plurality of contiguous lattice cells. A respective edge of a respective lattice cell corresponds to one or more edge qubits, and a respective face of the respective lattice cell corresponding to one or more face qubits. Each face qubit is entangled with adjacent edge qubits. A first face of the respective lattice cell corresponds to two or more face qubits, and/or a first edge corresponds to two or more edge qubits. A device for obtaining the plurality of entangled qubits represented by the above-described lattice structure is also described.Type: ApplicationFiled: September 4, 2020Publication date: December 24, 2020Inventors: Naomi NICKERSON, Terence RUDOLPH
-
Publication number: 20200401928Abstract: The disclosed embodiments provide a system for processing data. During operation, the system applies a hash function to a first term to produce a first index into a term offset table. Next, the system obtains, from a first entry at the first index in the term offset table, a first offset of a first record in a log-structured record store. The system retrieves a first UID for the first term from the first record and/or another record that is linked to the first record via a corresponding mapping to the first index. Finally, the system outputs the first UID in association with the first term.Type: ApplicationFiled: June 19, 2019Publication date: December 24, 2020Applicant: Microsoft Technology Licensing, LLCInventor: Sanjay Sachdev
-
Publication number: 20200401929Abstract: The present disclosure is directed to methods and systems for knowledge distillation.Type: ApplicationFiled: June 19, 2019Publication date: December 24, 2020Inventors: Thomas J. Duerig, Hongsheng Wang, Scott Alexander Rudkin
-
Publication number: 20200401930Abstract: Disclosed herein are system, method, and computer program product embodiments for classifying a new record. An embodiment operates by receiving a dataset unique to a user, wherein the dataset includes a plurality of records separate from the new record, and receiving a dataset schema. Thereafter, the dataset is validated based on the dataset schema. Subsequently, a request for creating a machine learning model based on a selected model template and dataset is received. After creating the custom machine learning model, a request for classifying the new record based on the created machine learning model is received. Upon determining the classification of the new record based on the custom machine learning model, the classification for the new record is outputted to the user.Type: ApplicationFiled: June 19, 2019Publication date: December 24, 2020Inventors: Sergey SMIRNOV, Francesco ALDA, Evgeny ARNAUTOV, Michael HAAS, Amrit RAJ, Ekaterina SUTTER
-
Publication number: 20200401931Abstract: Technologies for generating a graph containing clusters of feature attribute values for training a machine learning model for content item selection and delivery are provided. The disclosed techniques include, for each entity, of a plurality of entities, a system identifies transitions from one geographic location to another geographic location. A graph is generated based on the transitions associated with each entity. The graph comprises nodes representing geographic locations and edges connecting the nodes. Each of the edges connects two nodes, represents a transition from one geographic location to another geographic location, and each edge represents an edge weight value that is based on frequencies of transitions between geographic locations represented by the two connected nodes. The system generates a plurality of clusters from the nodes based upon the edge weight value of each edge. The system includes the plurality of clusters as features in a machine learning model.Type: ApplicationFiled: June 20, 2019Publication date: December 24, 2020Inventors: Qing Duan, Xiaowen Zhang, Xiaoqing Wang, Junrui Xu
-
Publication number: 20200401932Abstract: Techniques for enhancing actionable opportunities through machine learning are disclosed. In some embodiments, a system includes an event listener for detecting an opportunity to perform an action using one or more computing resources. When a new opportunity is detected, the system generates a set of search criteria, which is used to search a set of external web resources for current events. The system may then generate, using a machine learning model as a function of one or more features extracted from current events satisfying the search criteria, a score representing a likelihood of success that the action leads to an optimal result. The system may tune the machine learning model based on feedback received that is indicative of how the current events affected the likelihood of success for the action.Type: ApplicationFiled: June 20, 2019Publication date: December 24, 2020Applicant: Oracle International CorporationInventors: Vivek Kumar, Catherine You Francis, Meeten Bhavsar
-
Publication number: 20200401933Abstract: A system includes a virtual reality system configured to enable a user to interact with a virtual environment, a plurality of biofeedback sensors configured to monitor a user, and a computer system including a virtual reality module configured to generate at least a view of the virtual environment, a biofeedback module configured to fuse output of the plurality of biofeedback sensors with a plurality of events within the virtual environment, a training module configured to generate a model of user behavior, wherein the training module executed by the computer system enables the computer system to make a prediction of a user response of the user based on a corpus of biofeedback data, and an alert module configured to generate at least one alert to the user via the virtual reality system based on the user response predicted by the computer system.Type: ApplicationFiled: June 21, 2019Publication date: December 24, 2020Inventors: Jenna Reinen, Aldis Sipolins, Patrick Watson, Ravi Tejwani, Marco Cavallo, Hui Wu
-
Publication number: 20200401934Abstract: An artificial intelligence-based method includes calculating, by a wearable device, a biometric index based on a plurality of biometric indicators associated with a user of the wearable device, based on the biometric index exceeding a threshold, identifying a change in a context of the user, determining whether the calculated biometric index is associated with the change in the context, based on the calculated biometric index being associated with the change, searching for an Internet of Things device available within the context, transmitting a notification to the Internet of Things device requesting assistance to the user, and in response to transmitting the notification, measuring a change in the biometric index.Type: ApplicationFiled: June 21, 2019Publication date: December 24, 2020Inventors: Craig M. Trim, Jeremy R. Fox, Zachary A. Silverstein, Sarbajit K. Rakshit
-
Publication number: 20200401935Abstract: A cognitive assignment engine (CAE) system attempts to infer semantic meaning from textual content of an incoming message in order to use the inferred meaning to assign the message to an appropriate responder. If the message contains insufficient textual content, the system identifies ontological structures comprised by the message's graphical content and classifies each structure as a function of the structure's location within the graphical content or of an intrinsic characteristic of the structure. The system then generates a message identifier by performing a computation on these classifications and uses the identifier to retrieve a previously stored graphical template that comprises ontological structures similar to those of the incoming message. The system associates the incoming message with a semantic meaning previously associated with the template, enabling the system to classify the message and to assign the message to the correct responder.Type: ApplicationFiled: June 24, 2019Publication date: December 24, 2020Applicants: INTERNATIONAL BUSINESS MACHINES CORPORATION, INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Nikhil Malhotra, Atri Mandal, Giriprasad Sridhara, Vijay Ekambaram