Robert Boschgmbh

Carnegie Mellon University

Priya L Donti

Jeremy Zico Kolter

Jeremy Zieg Kolter

Julia Vinogradska

Po-Wei Wang

Csaba Domokos

Melrose Roderick

A controller for generating a control signal for a computer-controlled machine. A neural network may be applied to a current sensor signal, the neural network being configured to map the sensor signal to a raw control signal. A projection function may be applied to the raw control signal to obtain a stable control signal to control the computer-controllable machine.

Controller with neural network and improved stability

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

Growing community of inventors

Pittsburgh, PA, United States of America

Priya L Donti