Abstract: An apparatus is disclosed for oscillator leakage calibration. In example aspects, the apparatus includes a mixer circuit and calibration circuitry. The mixer circuit has a first stage including at least one transistor coupled between a mixer input and a mixer output and a second stage including one or more transistors coupled between the at least one transistor and the mixer output. The mixer circuit also has tuning circuitry coupled to the at least one transistor. The calibration circuitry includes at least one resistor coupled between a power distribution node and at least one mixer node, with the at least one mixer node coupled between the at least one transistor and the one or more transistors, and at least one switch coupled between the power distribution node and the at least one mixer node. The calibration circuitry also includes controller circuitry coupled between the mixer node and the tuning circuitry.

Abstract: Certain aspects of the present disclosure generally relate to electronic circuits, and more particularly, to wireless transmitters. One example apparatus generally includes: an in-phase direct-current (DC) level shifter; a quadrature DC level shifter; an in-phase voltage-to-current (V2I) converter having an input coupled to an output of the in-phase DC level shifter; a quadrature V2I converter having an input coupled to an output of the quadrature V2I converter; a bias control circuit having inputs coupled to the in-phase V2I converter and the quadrature V2I converter, an output of the bias control circuit being coupled to at least one of the in-phase DC level shifter or the quadrature DC level shifter; an in-phase mixer having an input coupled to an output of the in-phase V2I converter; and a quadrature mixer having an input coupled to an output of the quadrature V2I converter.

Abstract: A head switch architecture for a stacked transistor structure including a first head switch located in an active path, the first head switch configured to provide a supply voltage to a first cascode path, and a second head switch located in an inactive path, the second head switch configured to provide a reduced supply voltage to a second cascode path.

Abstract: The layers of a neural network model are traversed in sequence one or more times while generating a plurality of relevance scores each time based on neuron weights and neuron biases of the neuron network model. Each relevance score of the plurality of relevance scores quantifies a relevance of a neuron in a lower layer of the sequence of layers to a higher layer of the sequence of layers. One or more relevance vectors can be populated from the plurality of relevance scores generated at the one or more times. Each of the relevance scores in each relevance vector quantifies a relevance of one of the input features to a task for which the neural network model is trained to perform. An explanation of a behavior of the neural network as a whole is generated based on the one or more relevance vectors.

Abstract: A network output is generated by feeding an input vector to an input layer of a neural network model having a plurality of neurons arranged in a sequence of layers, a plurality of neuron weights, and a plurality of neuron biases. The network output is used to determine an output relevance score. Relevance scores at a last layer of the sequence of layers are generated. Relevance scores are obtained at a first layer of the sequence of layers by reverse propagating the relevance scores generated at the last layer through the sequence of layers other than the last layer using the neuron weights and neuron biases. A feature relevance vector is formed based on the input vector and the relevance scores obtained at the first layer and included in a local explainability dataset, which is then used to generate a local explanation of a prediction of the neural network model.

Abstract: Methods, systems, and computer-readable storage media for providing a binary classifier include receiving a biased dataset, the biased data set including a plurality of records, each record being assigned to a class of a plurality of classes, one class including a majority class, performing data engineering on at least a portion of the biased dataset to provide a revised dataset, providing a trained deep autoencoder (DAE) by training a DAE using only records assigned to the majority class from the revised dataset, the trained DAE including a binary classifier that classifies records into one of the majority class and a minority class, validating the trained DAE using validation data that is based on at least a portion of the biased dataset, and providing the trained DAE for production use within a production system.

Abstract: Methods, systems, and computer-readable storage media for providing a binary classifier include receiving a biased dataset, the biased data set including a plurality of records, each record being assigned to a class of a plurality of classes, one class including a majority class, performing data engineering on at least a portion of the biased dataset to provide a revised dataset, providing a trained deep autoencoder (DAE) by training a DAE using only records assigned to the majority class from the revised dataset, the trained DAE including a binary classifier that classifies records into one of the majority class and a minority class, validating the trained DAE using validation data that is based on at least a portion of the biased dataset, and providing the trained DAE for production use within a production system.

Abstract: A system for enabling management and sharing of health records of a first user with a second user, wherein system includes a health record upload module that enables uploading of the health record onto a central repository, and a health record sharing module that enables the first user to select the second user from a list of a plurality of users and share the uploaded health record with the second user. The system is further configured with an interface that enables the first user to post any a combination of a comment, an image, a discussion topic, an update, a message, and a reply message.

Abstract: A system for enabling management and sharing of health records of a first user with a second user, wherein system includes a health record upload module that enables uploading of the health record onto a central repository, and a health record sharing module that enables the first user to select the second user from a list of a plurality of users and share the uploaded health record with the second user. The system is further configured with an interface that enables the first user to post any a combination of a comment, an image, a discussion topic, an update, a message, and a reply message.

Abstract: A system for enabling management and sharing of health records of a first user with a second user, wherein system includes a health record upload module that enables uploading of the health record onto a central repository, and a health record sharing module that enables the first user to select the second user from a list of a plurality of users and share the uploaded health record with the second user. The system is further configured with an interface that enables the first user to post any a combination of a comment, an image, a discussion topic, an update, a message, and a reply message.

Abstract: A differential amplifier comprises a first differential circuitry structure including a first part comprising at least one branch of transistors and a second part comprising at least one branch of transistors, and a second circuitry structure. The second circuitry structure has a first non-linear device and a second non-linear device. The non-linear devices each comprise a transistor having a control node connected to a differential output terminals of the differential amplifier. A common center node of the non-linear devices is connected to a control node of one of the transistors of each branch of the first part having a differential output terminal. Amplifier applications, communication devices and network nodes are also disclosed.

Abstract: Combined color and depth data for a field of view is received. Thereafter, using at least one bounding polygon algorithm, at least one proposed bounding polygon is defined for the field of view. It can then be determined, using a binary classifier having at least one machine learning model trained using a plurality of images of known objects, whether each proposed bounding polygon encapsulates an object. The image data within each bounding polygon that is determined to encapsulate an object can then be provided to a first object classifier having at least one machine learning model trained using a plurality of images of known objects, to classify the object encapsulated within the respective bounding polygon.

Abstract: RGB-D data generated by at least one optical sensor for a field of view is received. Thereafter, the RGB-D data is bifurcated into (i) RGB data and (ii) depth data for the field of view. One or more bounding polygons are defined within the depth data that each characterize a window within the field of view encapsulating an object. The RGB data is then cropped using the bounding polygon(s). Image processing can later be applied to the cropped RGB data to identify at least one object therein. Related apparatus, systems, techniques and articles are also described.

Abstract: Image color data for a field of view is received. Thereafter, color segmentation can be performed on the image color data to define at least one bounding polygon that minimizes an amount of free space within each bounding polygon. The at least one bounding polygon is then used to crop the image color data to result in cropped image color data. Image processing can then be applied to the cropped image color data to identify at least one object therein. Related apparatus, systems, techniques and articles are also described.

Abstract: A differential amplifier comprises a first differential circuitry structure including a first part comprising at least one branch of transistors and a second part comprising at least one branch of transistors, and a second circuitry structure. The second cicuitry structure has a first non-linear device and a second non-linear device. The non-linear devices each comprise a transistor having a control node connected to a differential output terminals of the differential amplifier. A common centre node of the non-linear devices is connected to a control node of one of the transistors of each branch of the first part having a differential output terminal. Amplifier applications, communication devices and network nodes are also disclosed.

Abstract: RGB-D data generated by at least one optical sensor for a field of view is received. Thereafter, the RGB-D data is bifurcated into (i) RGB data and (ii) depth data for the field of view. One or more bounding polygons are defined within the depth data that each characterize a window within the field of view encapsulating an object. The RGB data is then cropped using the bounding polygon(s). Image processing can later be applied to the cropped RGB data to identify at least one object therein. Related apparatus, systems, techniques and articles are also described.

Abstract: Combined color and depth data for a field of view is received. Thereafter, using at least one bounding polygon algorithm, at least one proposed bounding polygon is defined for the field of view. It can then be determined, using a binary classifier having at least one machine learning model trained using a plurality of images of known objects, whether each proposed bounding polygon encapsulates an object. The image data within each bounding polygon that is determined to encapsulate an object can then be provided to a first object classifier having at least one machine learning model trained using a plurality of images of known objects, to classify the object encapsulated within the respective bounding polygon.

Abstract: Image color data for a field of view is received. Thereafter, color segmentation can be performed on the image color data to define at least one bounding polygon that minimizes an amount of free space within each bounding polygon. The at least one bounding polygon is then used to crop the image color data to result in cropped image color data. Image processing can then be applied to the cropped image color data to identify at least one object therein. Related apparatus, systems, techniques and articles are also described.

Abstract: A system for enabling management and sharing of health records of a first user with a second user, wherein system includes a health record upload module that enables uploading of the health record onto a central repository, and a health record sharing module that enables the first user to select the second user from a list of a plurality of users and share the uploaded health record with the second user. The system is further configured with an interface that enables the first user to post any a combination of a comment, an image, a discussion topic, an update, a message, and a reply message.

Abstract: A central node connected to a remote network node via a fiber optic link controls an antenna switch in the remote network node by controlling the DC bias current of the laser providing an optical transmission signal from the central network node to the remote network node via the fiber optic link. The remote network node converts the received optical transmission signal to an electrical transmission signal, and detects the DC level of the electrical transmission signal. If the detected DC level satisfies a predetermined condition, the remote network node connects the antenna port of the antenna switch, and thus the antenna, to a reception signal path of the remote network node. Otherwise, the remote network node connects the antenna port of the antenna switch, and thus the antenna, to a transmission signal path of the remote network node.