Abstract: A system for teaching compositionality to convolutional neural networks includes an unmasked convolutional neural network comprising a first set of convolutional neural network layers; a first masked convolutional neural network comprising a second set of convolutional neural network layers; the unmasked convolutional neural network and the first masked convolutional network sharing convolutional neural network weights; the system training the unmasked and first masked convolutional neural networks simultaneously based on an objective function that seeks to reduce both discriminative loss and compositional loss.

Abstract: After analyzing images or videos, a computer system may display or present visual performance feedback with an interactive visual representation of a data-analysis pipeline, where the visual representation includes separate and coupled data-analysis operations in a set of data-analysis operations that includes the one or more machine-learning models. Moreover, in response to a user-interface command the specifies a given data-analysis operation, the computer system may display or present a group of images or videos and associated performance information for the given data-analysis operation, where a given image or video corresponds to an instance of the given data-analysis operation. Furthermore, when the computer system receives user feedback about one at least one of the images or videos in the group of images or videos, the computer system performs a remedial action based at least in part on the user feedback. For example, the computer system may dynamically modify the data-analysis pipeline.

Abstract: A computer system may train and use a machine-learning model to quantitatively analyze an image. In particular, the computer system may generate the machine-learning model based on a set of reference images that include content with instances of a quantitative feature attribute and one or more feedback metrics that specify locations of the instances of the quantitative feature attribute in the reference images and numerical values associated with the instances of the quantitative feature attribute. Then, after receiving the image from an electronic device, the computer system may analyze the image using the machine-learning model to perform measurements of one or more additional instances of the quantitative feature attribute in the image. Moreover, the computer system may provide a measurement result for the image, the measurement result including a second numerical value associated with the one or more additional instances of the quantitative feature attribute in the image.

Abstract: A computer system may train and use a machine-learning model to quantitatively analyze an image. In particular, the computer system may generate the machine-learning model based on a set of reference images that include content with instances of a quantitative feature attribute and one or more feedback metrics that specify locations of the instances of the quantitative feature attribute in the reference images and numerical values associated with the instances of the quantitative feature attribute. Then, after receiving the image from an electronic device, the computer system may analyze the image using the machine-learning model to perform measurements of one or more additional instances of the quantitative feature attribute in the image. Moreover, the computer system may provide a measurement result for the image, the measurement result including a second numerical value associated with the one or more additional instances of the quantitative feature attribute in the image.

Abstract: A system for teaching compositionality to convolutional neural networks includes an unmasked convolutional neural network comprising a first set of convolutional neural network layers; a first masked convolutional neural network comprising a second set of convolutional neural network layers; the unmasked convolutional neural network and the first masked convolutional network sharing convolutional neural network weights; the system training the unmasked and first masked convolutional neural networks simultaneously based on an objective function that seeks to reduce both discriminative loss and compositional loss.

Abstract: An electronic device may determine whether a machine-learning model is operating within predefined limits. In particular, the electronic device may receive, from another electronic device, instructions for the machine-learning model, a reference input and a predetermined output of the machine-learning model for the reference input. Note that the instructions may include an architecture of the machine-learning model, weights associated with the machine-learning model and/or a set of pre-processing transformations for use when executing the machine-learning model on images. In response, the electronic device may configure the machine-learning model based on the instructions. Then, the electronic device may calculate an output of the machine-learning model for the reference input. Next, the electronic device may determine whether the machine-learning model is operating within predefined limits based on the output and the predetermined output.

Abstract: A system may use a configurable detected to identify a feature in a received image and an associated candidate tag based on user-defined items of interest, and to determine an associated accuracy metric. Moreover, based on the accuracy metric, costs of requesting the feedback from one or more individuals and a feedback threshold, the system may use a scheduler to selectively obtain feedback, having a feedback accuracy, about the candidate tag from the one or more individuals. Then, the system may generate a revised tag based on the feedback when the feedback indicates the candidate tag is incorrect. Next, the system presents a result with the feature and the candidate tag or the revised tag to another electronic device. Furthermore, based on a quality metric, the system may update labeled data that are to be used to retrain the configurable detector.

Abstract: A system may use a configurable detected to identify a feature in a received image and an associated candidate tag based on user-defined items of interest, and to determine an associated accuracy metric. Moreover, based on the accuracy metric, costs of requesting the feedback from one or more individuals and a feedback threshold, the system may use a scheduler to selectively obtain feedback, having a feedback accuracy, about the candidate tag from the one or more individuals. Then, the system may generate a revised tag based on the feedback when the feedback indicates the candidate tag is incorrect. Next, the system presents a result with the feature and the candidate tag or the revised tag to another electronic device. Furthermore, based on a quality metric, the system may update labeled data that are to be used to retrain the configurable detector.

Abstract: A system may use a configurable detected to identify a feature in a received image and an associated candidate tag based on user-defined items of interest, and to determine an associated accuracy metric. Moreover, based on the accuracy metric, costs of requesting the feedback from one or more individuals and a feedback threshold, the system may use a scheduler to selectively obtain feedback, having a feedback accuracy, about the candidate tag from the one or more individuals. Then, the system may generate a revised tag based on the feedback when the feedback indicates the candidate tag is incorrect. Next, the system presents a result with the feature and the candidate tag or the revised tag to another electronic device. Furthermore, based on a quality metric, the system may update labeled data that are to be used to retrain the configurable detector.

Abstract: Systems and methods for instituting redistribution of wireless clients to improve service, comprising via access point (AP), multiple APs acting in concert, and/or a central entity, in connection with a network, allowing a client to associate; deciding that an associated client should be redistributed based on a connection metric, wherein the decision is based on at least one of, a probability calculation, network metric and a threshold comparison; and via the AP, sending the associated client a trigger, wherein the trigger is at least one of, a redistribution request and a disconnect message.

Abstract: Authorized access by a user to an application server in a wireless local area network is obtained by printing machine-readable indicia on a portable, physical ticket, and by presenting the ticket to an electro-optical reader for reading the indicia.

Abstract: Described is an arrangement including a receiver and an enveloped detection arrangement. The receiver receives radio frequency signals generated according to a predetermined wireless communication protocol. The envelope detection arrangement screens the radio frequency signals for a predetermined signal which utilizes the predetermined wireless communication protocol and has a predetermined envelope sequence. Upon detection of the predetermined signal, the arrangement transmits a further signal to a computing device coupled thereto. The further signal is an instruction for the computing device to execute a predetermined action.

Abstract: Described is a system and method for resilient coverage in a wireless environment. The system may include a first wireless device having a first wireless transceiver; a second wireless device having a second wireless transceiver; and an envelope detection arrangement (“EDA”) coupled to the second device. The second wireless device has a first communication mode and a second communication mode, The second wireless transceiver conducts wireless communications with the first wireless transceiver using a predetermined wireless communication protocol (e.g., IEEE 802.11/16) only when the second wireless device is in the first communication mode. The second wireless transceiver is in a low-power state when in the second communication mode. The EDA screens radio frequency signals for a signal having a predetermined envelope sequence; the signal is generated according to the same predetermined wireless communication protocol.

Abstract: A method that enables the power saving frame transmission comprising an AP informing a plurality of stations within its range in a WLAN about a plurality of scheduled service periods during which the AP has access to a channel in a scheduled service time, receiving the information about the plurality of scheduled service periods by the plurality of stations and deciding about initiating or not initiating a frame transmission, whether or not an acknowledgement and an immediate response expected from other APs pertaining to said WLAN are received prior to a subsequent scheduled service time, wherein the frame is transmitted in a cooperative frame transmission scenario.

Abstract: Described is a method and system for fast roaming of a mobile unit in a wireless network. An access point receives a packet from a wireless computing unit which includes unit identifying data and an association request to establish communications via the access point. The packet is processed to initiate an authentication procedure of the unit using the unit identifying data. The authentication procedure is performed by at least one of the access point and an authentication server connected to the access point. Wireless transmissions of further packets between the unit and the access point (e.g., the further packets being related to the authentication procedure) are prioritized. The authentication procedure is completed to determine if the association request of the unit be granted.

Abstract: Described are a system and method for battery conservation in a wireless station. Initially, a wireless station switches, according to a predetermined time schedule, from a first communications mode into a second communications mode. The station is capable of at least one of receiving and transmitting data packets only when the station is in the second communications mode. The first mode is a power conservation mode. When the station is in the second mode, a wireless access point obtains a priority access to a radio channel. Then, the access point reserves the radio channel for wireless communications between the access point and the station. Wireless communications are conducted between the access point and the station over the radio channel. Upon a termination condition, the station switches into the first mode.

Abstract: A semiconductor device for securely controlling access to a cryptographic processor including a semiconductor package with a biometric data capture device therein operative to acquire data associated with predetermined biometric characteristic of a user and store it as a biometric key, and a processing unit in the package coupled to the data capture device. An encryption/decryption circuit is also disposed in the semiconductor package and is operative to perform encryption or decryption on input data utilizing the biometric key.

Abstract: Unauthorized use of a wireless local area network is detected, wherein the network includes mobile units that communicate with at least one server computer through access points. The messages transmitted over the wireless local area network are analyzed for compliance with rules set out in the specification for the selected wireless local area network protocol. If an inconsistency is detected, an alarm is generated to indicate a possible intruder access attempt to the wireless local area network.

Abstract: A system and method for detecting unauthorized use of a wireless local area network is described, wherein the network includes mobile units that communicate with at least one access point. First network traffic data is accumulated at a mobile unit. Second network traffic data is accumulated at an access point. The first and second traffic data is communicated to a computer and is correlated by the computer to identify non-correlated traffic data. An alarm condition is signaled when the non-correlated traffic data exceeds a threshold.

Abstract: A intrusion detection method is disclosed for use in a wireless local area data communications system, wherein mobile units communicate with access points, and wherein the system is arranged to locate transmitters using signals transmitted by the transmitters. A database relating authorized transmitters to location is maintained. Selected signals are detected at the access points and location data corresponding to the selected signals for use in locating a source of the signals is recorded. The source location is determined using the location data, and the source location is compared to a corresponding location in the database. An alarm is signaled if the source location is inconsistent with the corresponding database location.