Robert Boschgmbh

Carnegie Mellon University

A9.com, Inc.

Po-Wei Wang

Jeremy Zico Kolter

Csaba Domokos

Filipe J Cabrita Condessa

Devin T Willmott

Inderjit Dhillon

Daria Stepanova

Chirag Pabbaraju

Priya L Donti

Vijai Mohan

A system for applying a neural network to an input instance. The neural network includes an optimization layer for determining values of one or more output neurons from values of one or more input neurons by a joint optimization parametrized by one or more parameters. An input instance is obtained. The values of the one or more input neurons to the optimization layer are obtained and input vectors for the one or more input neurons are determined therefrom. Output vectors for the one or more output neurons are computed from the determined input vectors by jointly optimizing at least the output vectors with respect to the input vectors to solve a semidefinite program defined by the one or more parameters. The values of the one or more output neurons are determined from the respective computed output vectors.

Neural network with a layer solving a semidefinite program

A system and computer implemented method for learning rules from a data base including entities and relations between the entities, wherein an entity is either a constant or a numerical value, and a relation between a constant and a numerical value is a numerical relation and a relation between two constants is a non-numerical relation. The method includes: deriving aggregate values from said numerical and/or non-numerical relations; deriving non-numerical relations from said aggregate values; adding said derived non-numerical relations to the data base; constructing differentiable operators, wherein a differentiable operator refers to a non-numerical or a derived non-numerical relation of the data base, and extracting rules from said differentiable operators.

Method and system for learning rules from a data base

A system for controlling a physical system via segmentation of an image includes a controller. The controller may be configured to receive an image of n pixels from a first sensor, and an annotation of the image from a second sensor, form a coupling matrix, k class vectors each of length n, and a bias coefficient based on the image and the annotation, generate n pixel vectors each of length n based on the coupling matrix, class vectors, and bias coefficient create a single segmentation vector of length n from the pixel vectors wherein each entry in the segmentation vector identifies one of the k class vectors, output the single segmentation vector; and operate the physical system based on the single segmentation vector.

Image segmention via efficient semidefinate-programming based inference for binary and multi-class Markov Random Fields

Community detection for a network using low-cardinality semidefinite programming is described. Data descriptive of a set of nodes of a network is received. The data includes a set of nodes representing entities of a system and edges representing connections between the entities of the system. A modularity maximization is performed to assign each node of the set of nodes to one or more communities to generate multiple-cardinality embeddings. The multiple-cardinality embeddings are rounded to unit cardinality to recover a community assignment with maximum modularity. The community assignment is refined and aggregated to create an aggregate network defining a set of connected communities of the network. The network is operated on in accordance with the community assignment.

Community detection using fast low-cardinality semidefinite programming

Various embodiments of systems and methods allow unsupervised, deep learning, character-level language models to complete and correct search engine queries, given arbitrary search prefixes. Embodiments use a multi-layer, character-level, recurrent neural network trained on query logs to generate query suggestions for the user. Integrated is an error correction framework. More particularly, approaches disclosed herein for query error correction and completion combine the character-level language models with an edit-distance-based potential function calibrated to generate spelling corrections, linking the two using a tree-based beam search algorithm that can exploit the potential functions and efficiently rank the suggestions. Optimizations are made to the predictive system, and efficient processor-based computations complete the queries, with error correction, in real-time. The embodiments substantially increase hit rate over standard approaches and are capable of handling tail queries.

Growing community of inventors

Pittsburgh, PA, United States of America

Po-Wei Wang