Abstract: Methods and systems are disclosed for updating learned models. An embodiment comprises receiving a plurality of data sets representing sensed data from one or more devices and determining, using one or more local learned models, local parameters based on the received data sets. Another operation may comprise generating a combined data set by combining the plurality of data sets and, determining, using one or more local learned models, global parameters based on the combined data set. Another operation may comprise transmitting, to a remote system, the global parameters for determining updated global parameters using one or more global learned models based at least partially on the global parameters, and receiving, from the remote system, the updated global parameters. Another operation may comprise updating the one or more local learned models using both the local parameters and updated global parameters.

Abstract: Broadly speaking, embodiments of the present techniques provide a method and system for personalising machine learning models on resource-constrained devices by using conditional neural networks. In particular, the present techniques allow for resource-efficient use of a conditioning vector by incorporating the conditioning vector into weights learned during training. This reduces the computational resources required at inference time.

Abstract: Broadly speaking, the present techniques generally relate to a system, computer-implemented method and apparatus for training a machine learning, ML, model to perform sound enhancement for a target user in real-time, and to a method and apparatus for using the trained ML model to perform sound enhancement of audio signals in real-time. Advantageously, the present techniques are suitable for implementation on resource-constrained devices that capture audio signals, such as smartphones and Internet of Things devices.

Abstract: In some examples, software CoBot engineering, execution, and monitoring may include extracting a CoBot requirement from a requirement specification for a CoBot that is to be implemented. Based on application of a CoBot description language to the CoBot requirement, a CoBot workflow that specifies a plurality of tasks to be performed by the CoBot may be generated. A determination may be made as to whether a task is to be performed by a bot or by a human. A team that includes a plurality of bots and at least one human may be generated to execute the CoBot workflow. The bots of the team may be prioritized to identify a bot that is a best match to the CoBot requirement. The CoBot that includes configured bots may be deployed in an operational environment to perform the CoBot workflow.

Abstract: This specification describes methods for performing inferencing based on input data, the methods comprising: initialising a neural network based on a set of stored model information, which defines a plurality of orthogonal binary basis vectors which are to be used to implement kernels in one or more hidden layers of the neural network, and plural sets of plural coefficients, each set of plural coefficients corresponding to a respective one of the kernels, wherein each of the coefficients in a given set of coefficients is associated with a respective one of the one or more orthogonal binary basis vectors; passing input data through the neural network such that convolution operations between the kernels and data arriving at the kernels are performed, wherein each of the kernels is implemented using a respective set of coefficients and the orthogonal binary basis vectors with which the coefficients in the set are associated; and outputting data from the neural network, the output data representing an inference c

Abstract: In one embodiment, the method includes obtaining, by a first processing device, energy demand data representative of the energy consumption of respective tasks of a processing pipeline, obtaining, by the first processing device, battery availability data representative of the available energy of the batteries of other respective processing devices, for respective tasks of the processing pipeline, selecting, by the first processing device, one of the processing devices for executing the task, as a function of the energy demand data and the battery availability data, and controlling, by the first processing device, the execution of the respective tasks on the selected processing devices.

Abstract: Broadly speaking, the present techniques provide methods for conditioning a neural network, which not only improve the generalizable performance of conditional neural networks, but also reduce model size and latency significantly. The resulting conditioned neural network is suitable for on-device deployment due to having a significantly lower model size, lower dynamic memory requirement, and lower latency.

Abstract: A method and system for parking enforcement, can include graphically displaying in a graphical user interface, a mixed reality display of data including some augmented reality data including parking enforcement information and real-time navigational cues for a navigation that account for a current location of a parking enforcement officer and one or more zones allocated to the parking enforcement officer, capturing license plate information to determine compliance with curbside regulations, and integrating a payment data source and a citation issuance application to issue a citation based on the license plate information.

Abstract: In some examples, software CoBot engineering, execution, and monitoring may include extracting a CoBot requirement from a requirement specification for a CoBot that is to be implemented. Based on application of a CoBot description language to the CoBot requirement, a CoBot workflow that specifies a plurality of tasks to be performed by the CoBot may be generated. A determination may be made as to whether a task is to be performed by a bot or by a human. A team that includes a plurality of bots and at least one human may be generated to execute the CoBot workflow. The bots of the team may be prioritized to identify a bot that is a best match to the CoBot requirement. The CoBot that includes configured bots may be deployed in an operational environment to perform the CoBot workflow.

Abstract: In one embodiment, the method includes obtaining, by a first processing device, energy demand data representative of the energy consumption of respective tasks of a processing pipeline, obtaining, by the first processing device, battery availability data representative of the available energy of the batteries of other respective processing devices, for respective tasks of the processing pipeline, selecting, by the first processing device, one of the processing devices for executing the task, as a function of the energy demand data and the battery availability data, and controlling, by the first processing device, the execution of the respective tasks on the selected processing devices.

Abstract: A method, performed by an electronic device, of generating a speech signal corresponding to at least one text is provided. The method includes obtaining feature information with respect to a first sample included in the speech signal, based on the at least one text, obtaining condition information related to a condition under which a bunching operation, in which one or more sample values included in the speech signal are obtained, is performed, based on the feature information, configuring one or more bunching blocks for performing the bunching operation, based on the condition information, obtaining the one or more sample values based on the feature information with respect to the first sample by using the one or more bunching blocks, and generating the speech signal based on the obtained one or more sample values.

Abstract: A method and system for parking enforcement, can include graphically displaying in a graphical user interface, a mixed reality display of data including some augmented reality data including parking enforcement information and real-time navigational cues for a navigation that account for a current location of a parking enforcement officer and one or more zones allocated to the parking enforcement officer, capturing license plate information to determine compliance with curbside regulations, and integrating a payment data source and a citation issuance application to issue a citation based on the license plate information.

Abstract: Disclosed are an electronic device and a method for controlling thereof.

Abstract: Methods and systems are disclosed for updating learned models. An embodiment comprises receiving a plurality of data sets representing sensed data from one or more devices and determining, using one or more local learned models, local parameters based on the received data sets. Another operation may comprise generating a combined data set by combining the plurality of data sets and, determining, using one or more local learned models, global parameters based on the combined data set. Another operation may comprise transmitting, to a remote system, the global parameters for determining updated global parameters using one or more global learned models based at least partially on the global parameters, and receiving, from the remote system, the updated global parameters. Another operation may comprise updating the one or more local learned models using both the local parameters and updated global parameters.

Abstract: This specification describes methods for performing inferencing based on input data, the methods comprising: initialising a neural network based on a set of stored model information, which defines a plurality of orthogonal binary basis vectors which are to be used to implement kernels in one or more hidden layers of the neural network, and plural sets of plural coefficients, each set of plural coefficients corresponding to a respective one of the kernels, wherein each of the coefficients in a given set of coefficients is associated with a respective one of the one or more orthogonal binary basis vectors; passing input data through the neural network such that convolution operations between the kernels and data arriving at the kernels are performed, wherein each of the kernels is implemented using a respective set of coefficients and the orthogonal binary basis vectors with which the coefficients in the set are associated; and outputting data from the neural network, the output data representing an inference c

Abstract: A system, medium and method for automatically generating test data to be applied to test a target software code is disclosed. Input parameter data is received from a user via a displayed user interface, wherein the input parameter data is directed to a user selected data type, the data type being a Boolean, string, or integer. One or more preestablished stored testing algorithms is automatically selected based on the user selected data type and one or more values are applied to the selected one or more preestablished stored testing algorithms in accordance with the user selected data type. At least one set of test data from the one or more identified applicable testing algorithms is automatically generated, wherein the at least one set of test data generated from the identified testing algorithms can be used as inputs for testing the target software code.

Abstract: This disclosure generally relates to computer security, and more particularly to methods and systems for application programming interface (API)-level intrusion detection. In some embodiments, a computer-readable medium is disclosed, storing instructions for: receiving an API call for a service at an API sandbox module; parsing the API call to extract at least one of: an API call name; and or one or more API call parameters; generating a copy of the at least one of: the API call name and or the one or more API call parameters; determining, via an intrusion detection rules execution engine, whether the API call violates one or more security rules obtained from a security rules object, using the copy of the at least one of: the API call name and or the one or more API call parameters; and providing an indication of whether the API call violates the one or more security rules.

Abstract: A system, medium and method for automatically generating test data to be applied to test a target software code is disclosed. Input parameter data is received from a user via a displayed user interface, wherein the input parameter data is directed to a user selected data type, the data type being a Boolean, string, or integer. One or more preestablished stored testing algorithms is automatically selected based on the user selected data type and one or more values are applied to the selected one or more preestablished stored testing algorithms in accordance with user selected data type. At least one set of test data from the one or more identified applicable testing algorithms is automatically generated, wherein the at least one set of test data generated from the identified testing algorithms can be used as inputs for testing the target software code.

Abstract: This disclosure generally relates to computer security, and more particularly to methods and systems for application programming interface (API)-level intrusion detection. In some embodiments, a computer-readable medium is disclosed, storing instructions for: receiving an API call for a service at an API sandbox module; parsing the API call to extract at least one of: an API call name; and or one or more API call parameters; generating a copy of the at least one of: the API call name and or the one or more API call parameters; determining, via an intrusion detection rules execution engine, whether the API call violates one or more security rules obtained from a security rules object, using the copy of the at least one of: the API call name and or the one or more API call parameters; and providing an indication of whether the API call violates the one or more security rules.