Abstract: Methods, systems, and storage media are disclosed herein for determining objects in image data that match a plurality of captured images, in which one or more of the captured images from among the plurality of captured images may depict only a portion of an object. A computing device may extract a first feature from at least one block of the plurality of blocks from a captured image; determine a second feature; and determine a third feature. The computing device may determine, as a matching image, a stored image from among a plurality of stored images including an object that has greatest maximum correlation with the third feature. The computing device may similarly determine a matching image for each of the captured images of the plurality of images; and determine a final matching image from among the candidate matching images that best matches the combination of the plurality of captured images.

Abstract: Methods, systems, and storage media are described for detecting objects in image data are provided. In embodiments, a computing device may generate a plurality of blocks from a captured image. Each block may represent a corresponding region of the captured image. The computing device may extract a first feature from at least one block of the plurality of blocks; determine a second feature based at least on the first feature; and determine a third feature based on the second feature. The computing device may determine, as a matching image, a stored image from among a plurality of stored images including an object that has greatest maximum correlation with the third feature. Other embodiments may be described and/or claimed.

Abstract: A method and apparatus for providing a point-to-point connection are disclosed. The method queries for a next available label for a first provider edge router and a next available label for a second provider edge router, performs a first configuration at the first provider edge router and a second configuration at the second provider edge router, wherein the performing the first configuration comprises configuring a first interface and configuring a label for using at least one tunnel by a second interface, wherein the performing the second configuration comprises configuring a third interface and configuring a label for using the at least one tunnel by a fourth interface, and performs a first mapping for the first provider edge router from the first interface to the second interface, and a second mapping for the second provider edge router from the third interface to the fourth interface.

Abstract: A router may include a central processing unit-based line card storing a forwarding table that includes a first set of entries, a network processing unit-based line card storing a partial forwarding table that includes a second set of entries comprising a subset of the first set of entries, where the second set of entries comprises entries that are most utilized by a plurality of line cards of the router, and a route controller for updating the second set of entries to comprise the entries that are the most utilized. The network processing unit-based line card may forward a packet when an entry in the partial forwarding table matches the packet and may forward the packet to the central processing unit-based line card to forward the packet when there is no entry in the partial forwarding table of the network processing-unit based line card that matches the packet.

Abstract: A CMOS imager integrated circuit using compressive sensing and bio-inspired detection is presented which integrates novel functions and algorithms within a novel hardware architecture enabling efficient on-chip implementation.

Abstract: A CMOS imager integrated circuit using compressive sensing and bio-inspired detection is presented which integrates novel functions and algorithms within a novel hardware architecture enabling efficient on-chip implementation.

Abstract: Differential mobility spectrometer with spatial ion detector and methods related thereto are disclosed. The use of one or more spatial detector within differential mobility spectrometry can provide for the identification and separation of ions with similar mobility and mass.

Abstract: A method for object recognition using shape and color features of the object to be recognized. An adaptive architecture is used to recognize and adapt the shape and color features for moving objects to enable object recognition.

Abstract: A system and method for cognitive processing of sensor data. A processor array receiving analog sensor data and having programmable interconnects, multiplication weights, and filters provides for adaptive learning in real-time. A static random access memory contains the programmable data for the processor array and the stored data is modified to provide for adaptive learning.

Abstract: A system and method for cognitive processing of sensor data. A processor array receiving analog sensor data and having programmable interconnects, multiplication weights, and filters provides for adaptive learning in real-time. A static random access memory contains the programmable data for the processor array and the stored data is modified to provide for adaptive learning.

Abstract: Differential mobility spectrometer with spatial ion detector and methods related thereto are disclosed. The use of one or more spatial detector within differential mobility spectrometry can provide for the identification and separation of ions with similar mobility and mass.

Abstract: A method for object recognition using shape and color features of the object to be recognized. An adaptive architecture is used to recognize and adapt the shape and color features for moving objects to enable object recognition.

Abstract: A process for object identification comprising extracting object shape features and object color features from digital images of an initial object and storing the extracted object shape features and object color features in a database where said extracted object shape features and object color features are associated with a unique identifier associated with said object and repeating the first step for a plurality of different objects. Then extracting object shape features and object color features from a digital image of an object whose identity is being sought and correlating the extracted object shape features and object color features of the object whose identity is being sought with the extracted object shape features and object color features previously stored in the database.

Abstract: The present invention relates to a space-invariant independent component analysis and electronic nose for detection of selective chemicals in an unknown environment, and more specifically, an approach to analysis of sensor responses to mixtures of unknown chemicals by an electronic nose in an open and changing environment. It is intended to fill the gap between an alarm, which has little or no ability to distinguish among chemical compounds causing a response, and an analytical instrument, which can distinguish all compounds present but with no real-time or continuous event monitoring ability.

Abstract: A process for object identification comprising extracting object shape features and object color features from digital images of an initial object and storing the extracted object shape features and object color features in a database where said extracted object shape features and object color features are associated with a unique identifier associated with said object and repeating the first step for a plurality of different objects. Then extracting object shape features and object color features from a digital image of an object whose identity is being sought and correlating the extracted object shape features and object color features of the object whose identity is being sought with the extracted object shape features and object color features previously stored in the database.

Abstract: The present invention relates to a space-invariant independent component analysis and electronic nose for detection of selective chemicals in an unknown environment, and more specifically, an approach to analysis of sensor responses to mixtures of unknown chemicals by an electronic nose in an open and changing environment

Abstract: A neural network circuit is provided having a plurality of circuits capable of charge storage. Also provided is a plurality of circuits each coupled to at least one of the plurality of charge storage circuits and constructed to generate an output in accordance with a neuron transfer function. Each of a plurality of circuits is coupled to one of the plurality of neuron transfer function circuits and constructed to generate a derivative of the output. A weight update circuit updates the charge storage circuits based upon output from the plurality of transfer function circuits and output from the plurality of derivative circuits. In preferred embodiments, separate training and validation networks share the same set of charge storage circuits and may operate concurrently.

Abstract: A circuit is used with an imager that is capable of capturing an image. The circuit includes a memory that is configured to during a first time interval, store a first representation of a first subimage of the image from the imager and during a second time interval, receive an update from the imager and use the update and the first representation to store a second representation of a second subimage of the image. The first subimage partially overlaps the second subimage, and the update represents a portion of the second subimage that is not present in the first subimage. The circuit also has an output circuit that is configured to during the first time interval, use the first representation to generate output signals representative of the first subimage and during the second time interval, use the second representation to generate output signals representative of the second subimage.

Abstract: High-speed, analog, fully-parallel and asynchronous building blocks are cascaded for larger sizes and enhanced resolution. A hardware-compatible algorithm permits hardware-in-the-loop learning despite limited weight resolution. A computation-intensive feature classification application has been demonstrated with this flexible hardware and new algorithm at high speed. This result indicates that these building block chips can be embedded as application-specific-coprocessors for solving real-world problems at extremely high data rates.

Abstract: This invention is a novel high-speed neural network based processor for solving the "traveling salesman" and other global optimization problems. It comprises a novel hybrid architecture employing a binary synaptic array whose embodiment incorporates the fixed rules of the problem, such as the number of cities to be visited. The array is prompted by analog voltages representing variables such as distances. The processor incorporates two interconnected feedback networks, each of which solves part of the problem independently and simultaneously, yet which exchange information dynamically.