Walker Digital, LLC

Raytheon Company

Groupon, Inc.

Inventor Holdings, LLC

Peter Kim

Jay S Walker

James Jorasch

Geoffrey M Gelman

Andrew P Golden

Russell Pratt Sammon

Daniel E Tedesco

Keith Bemer

Timothy A Palmer

Peter J Vogel

Magdalena Mik Fincham

Kathleen M Van Luchene

Michael J Sand

John M Packes, Jr

Norman C Gilman

Michael D Downs

Scott B Allison

Raymod J Mueller

Raymond Jay Mueller

Terry E Mayfield

Matthew D Hollenbeck

Dean P Alderucci

Stephen C Tulley

Steven M Santisi

Jason Reis Chaves

Ryan Quiller

Justin A Fishbone

Mark S Berlin

A computing machine receives a real synthetic aperture radar (SAR) image including one or more targets. The real SAR image is one of a plurality of real SAR images in a training set. The computing machine generates, for the real SAR image, a model-based target shadow background (TSB) image using a three-dimensional (3D) model of the target. The computing machine generates, for the real SAR image and using an auto-encoder engine, an auto-encoder-generated TSB image using an artificial neural network (ANN). The computing machine computes, using a discriminator engine, an image difference between the auto-encoder-generated TSB image and the model-based TSB image. The computing machine adjusts weights in the auto-encoder engine based on the computed image difference.

Generative adversarial network-based target identification

A dynamic reconfiguration training machine learning computer architecture is disclosed. According to some aspects, a computing machine accesses a configuration file. The configuration file specifies parameters for a machine learning session. The computing machine trains a machine learning module to solve a problem, where the machine learning module operates according to the parameters specified in the configuration file. The computing machine generates an output representing the trained machine learning module.

Dynamic reconfiguration training computer architecture

A computer architecture for artificial image generation is disclosed. According to some aspects, a computing machine receives a voxel model of a target object. The target object is to be recognized using an image recognizer. The computing machine generates, based on the voxel model, a set of TSB (target shadow background-mask) images of the target object. The computing machine receives, at an auto-encoder, a set of real images of the target object. The computing machine generates, using an auto-encoder and based on the set of real images, one or more artificial images of the target object based on the set of TSB images. The computing machine provides, as output, the generated one or more artificial images of the target object.

Computer architecture for artificial image generation

A computer architecture for artificial image generation is disclosed. According to some aspects, a computing machine receives a voxel model of a first set of objects different from a target object. The target object is to be recognized using an image recognizer. The computing machine generates, based on the voxel model, a set of TSB (target shadow background-mask) images of the first set of objects. The computing machine receives, at an auto-encoder, a set of real images of the first set of objects. The computing machine generates, using the auto-encoder, one or more artificial images of the target object based on the set of TSB images. The auto-encoder learns differences between the target object and the first set of objects. The computing machine provides, as output, the generated one or more artificial images of the target object.

Computer architecture for artificial image generation using auto-encoder

A machine trains a first neural network using a first set of images. Training the first neural network comprises computing a first set of weights for a first set of neurons. The machine, for each of one or more alpha values in order from smallest to largest, trains an additional neural network using an additional set of images. The additional set of images comprises a homographic transformation of the first set of images. The homographic transformation is computed based on the alpha value. Training the additional neural network comprises computing an additional set of weights for an additional set of neurons. The additional set of weights is initialized based on a previously computed set of weights. The machine generates a trained ensemble neural network comprising the first neural network and one or more additional neural networks corresponding to the one or more alpha values.

Neural network trained by homographic augmentation

According to one described embodiment, a method is provided in which transaction information is determined. The transaction information is associated with (i) a buyer who has arranged to purchase a product from a central controller at a first price established between the buyer and the central controller and (ii) a merchant that offers the product for sale at a second price, different from the first price, without offering the product for sale to buyers at the first price. Information is transmitted that facilitates the acquisition of the product by the buyer, in exchange for payment provided by the buyer to the central controller. An amount based on the second price is provided to the merchant.

Retail system for selling products based on a flexible product description

In accordance with some embodiments, a method provides for facilitating play of a game on a mobile device by recognizing inputs provided by a user, at least one of the inputs causing progress in the game. In accordance with one embodiment, a code is received at the mobile device, in response to which code access to an outcome is provided. Upon an outcome redemption request being received, a benefit associated with the outcome may be provided. The benefit may, in some embodiments, be capable of changing play of the game by the user.

Method and apparatus for conducting or facilitating a promotion

A method and apparatus for conducting a promotion and for distributing promotions to potential users provide a merchant or promotion organizer flexibility in the way they conduct the promotion as well as an ability to change one or more aspects of the promotion during the operation of the promotion. One or more outcomes are generated by a controller and provided to a user. In addition, one or more codes which allow the outcomes to be revealed or unlocked are generated by the controller and provided to an intermediary. In exchange for completing or satisfying a qualifying action or criteria, the user may receive a code from the intermediary. The user can then unlock an outcome to reveal a prize, benefit, symbol, value, etc., associated with the unlocked outcome. The user may provide a redemption request to either the controller or the intermediary based on the unlocked outcome to receive a benefit or prize associated with the unlocked outcome.

Systems and methods are provided to associate a transferable item price with a first consumer and to determine that a second consumer is entitled to purchase an item in exchange for payment of an amount based on the transferable item price. In one embodiment, the first consumer arranges to purchase an item at a first price. The merchant transmits a transferable item price code to the first consumer. The first consumer sends the transferable item price code to the second consumer, such as by including the transferable item price code in an e-mail message. The second consumer transmits the transferable item price code to the merchant to establish that he or she is entitled to purchase the item at the first price.

Systems and methods for providing transferable item prices

A method and apparatus for conducting a promotion and for distributing promotions to potential users provide a merchant or promotion organizer flexibility in the way they conduct the promotion as well as an ability to change one or more aspects of the promotion during the operation of the promotion. In accordance with one embodiment, such a promotion may provide for a game on a mobile device, wherein a locked outcome of the game may be unlocked using an unlock code. In one embodiment, a result of the locked outcome may correspond to an intra-game benefit.

Systems and methods are provided for resolving a hand of blackjack played by a player. If it is determined that the hand of blackjack has resulted in a push, then it is determined if the player has won the hand of blackjack based on a random outcome. For example, a dealer may receive from the player an indication of a wager amount associated with a hand of blackjack. The hand of blackjack may then be played according to traditional rules. If it is determined that the hand has resulted in a push, an indication of a random outcome may be received. The random outcome may be, for example, statistically independent of the hand of blackjack. Based on the random outcome, it is determined if the player has won the hand of blackjack. If the player has won, he or she receives payment of a winning amount based on the wager amount.

Growing community of inventors

Stamford, CT, United States of America

Peter Kim